RU2792947C2 - Method and system for audio signal supplement - Google Patents

Abstract

FIELD: audio processing.

SUBSTANCE: method and system for supplement of an audio clip to include data suitable for determination of identification information of an evaluating person. The method includes: reception of an audio clip; reception of an identifier of an evaluating person, to which the audio clip should be transmitted, while the identifier is represented with a unique bit sequence; generation, based on the unique bit sequence, of an identification watermark related to the evaluating person and to be included in the audio clip to generate of a supplemented audio signal by means of changing the audio signal so that it has a predetermined energy level at each of at least two different frequency levels to indicate the presence of a given bit of the unique bit sequence related to the evaluating person in the supplemented audio clip; and transmission of the supplemented audio clip to an electronic device related to the evaluating person.

EFFECT: increase in the quality of detection of identification watermarks in audio signals of records, which are part of the intellectual property of organizations related to a virtual assistant application.

20 cl, 10 dwg

Description

The technical field to which the invention belongs

[001] The present invention relates to the field of signal processing in general and, in particular, to a method and system for supplementing an audio clip.

State of the art

[002] Electronic devices such as smartphones and tablets can access a growing and diverse number of applications and processing services and/or access different types of information. However, novice and/or disabled users and/or users may not be able to interact effectively with such devices primarily due to the variety of functions provided by these devices or the inability to use the machine user interfaces provided by such devices (e.g., keyboard). For example, a driver or visually impaired user may not be able to use the touch screen or keyboard associated with some of these devices.

[003] Virtual assistant applications have been designed to perform functions in response to such user requests. Such virtual assistant applications can be used for information retrieval, navigation, and a wide range of commands, for example. A typical virtual assistant application (such as a Siri™ virtual assistant, Alexa™ virtual assistant application, etc.) can receive the user's voice in the form of a digital audio signal from an electronic device and perform a wide range of tasks for the user. For example, the user may communicate with the virtual assistant application by providing verbal cues to query, such as what the weather is like now, where the nearest mall is, and so on. In response, the virtual assistant application can provide the user with an appropriate response, such as "Rockland Mall is only 7 minutes away from you" or "It's warm and sunny outside, you don't need to take an umbrella."

[004] In order for the virtual assistant application to provide such responses, first of all, a machine learning algorithm (MLA) can be trained based on the training dataset to generate appropriate responses in response to user commands. For example, the training data set may include different training objects, one of which may include an indication of a training user command and a label including an indication of a corresponding training response. Since the training dataset may include a large number of training objects (e.g., thousands or even tens or hundreds of thousands), the training dataset can be obtained by assigning digital tasks to scoring people through crowdsourcing platforms such as the Amazon Mechanical crowdsourcing platform. Turk™, crowdsourcing platform Yandex Toloka™, etc., who were provided with instructions for labeling training user commands.

[005] In addition, once the MLA has been trained to generate responses, the responses may be recorded and the same or other evaluators may be provided with the recordings and given instructions to, for example, decode them for the virtual assistant application and/or check if the the virtual assistant application works, providing the expected responses to sample user commands.

[006] However, some evaluators may intentionally or unintentionally make publicly available records that they have been given to perform digital tasks, as described above. For example, evaluators can re-record entries using their personal electronic devices and subsequently post copies of the entries so generated on their social media pages.

[007] As can be understood, leaked recordings may reveal new features of the virtual assistant application prior to their official release and may be further modified and/or misused by other users, causing reputational and financial damage to the organization owning the virtual assistant application.

[008] Several prior art approaches have been proposed to solve the above technical problem.

[009] BUS Patent No: 9,299,356-B2issued March 29, 2016 to the copyright holder Fraunhofer Gesellschaft zur Vorderung der Angewandten Forschung eV entitled "Watermark Decoder and Method for Providing Binary Message Data" discloses a watermark decoder including a time-frequency domain representation provider, a memory unit, a timing determiner, and a watermark extractor. . The Time-Frequency-Domain Representation Provider provides a watermarked frequency-domain representation of a signal for a plurality of time blocks. The memory unit stores the frequency domain representation of the watermarked signal for a plurality of time blocks. In addition, the timing determiner identifies a time alignment block based on the frequency domain representation of the watermarked signal of the plurality of time blocks. The watermark extractor provides binary message data based on the stored frequency domain representations of the watermarked signal of time blocks temporally preceding the identified time justification block, taking into account the distance to the identified time justification block.

[0010] BUS Patent No. 8,300,820-B2issued on October 30, 2012 to the copyright holder CUGATE AG titled "Method of Embedding a Digital Watermark in a Useful Signal", methods of embedding a digital watermark in a useful signal are disclosed, wherein the watermark bit sequence is embedded in the frequency domain of the useful signal with using adaptive frequency modulation of two given frequencies by tracking the amplitudes of the selected frequencies of the original signal and changing them in accordance with the current bit of the watermark bit sequence.

[0011] U.S. Patent Application Publication No: 2020/220,935-A1 published July 9, 2020, owned by Amazon Technologies Inc. titled “Speech Processing Performed with respect to First and Second User Profiles in a Dialog Session”), techniques for implementing a “short-term” user identifier are disclosed. The system receives the first input audio data and determines the first results of speech processing based on them. The system also determines the first user who spoke the utterance represented in the first audio input. The system establishes a multi-turn conversational session with the first content source and receives the first output from the first content source based on the first speech processing results and the first user. The system causes the device to present the first output content associated with the first output. The system then receives the second audio input and determines the results of processing the second speech based on it. The system also determines that the second audio input corresponds to the same multi-turn dialog session. The system determines the second user who spoke the utterance represented in the second audio input and receives the second output from the first content source based on the results of processing the second speech and the second user. The system causes the device to present the second output content associated with the second output.

The essence of the invention

[0012] The purpose of the present invention is to eliminate at least some of the inconveniences found in the prior art.

[0013] The developers of the present invention have found that personalized records to be sent to the respective scoring people, by adding identification watermarks to them, including the identification information of the scoring people (for example, their identification number on their crowdsourcing platform), can help identify evaluating the person from whom the information was leaked, and potentially prevent damage suffered by the person owning the virtual assistant application in the event of unauthorized disclosure of his records.

[0014] More specifically, developers have developed systems and methods for adding an identification watermark to a respective audio signal of a given recording by equally modulating the energy levels of the respective audio signal at a respective set of predetermined frequency levels for each bit of the identification watermark.

[0015] Thus, once an identification watermark is added to the original audio of a recording, it can be further detected when the recording is played near an electronic device capable of performing the methods described herein. More specifically, upon receiving a recording audio signal to recognize a given bit of the identification watermark therein, such an electronic device may be configured to (1) determine energy levels in the received audio signal at each of a respective set of predetermined frequency levels associated with a given bit; (2) determining a combined value indicating specific energy levels; and (3) comparing the combined value with a predetermined threshold value.

[0016] Thus, developers have found that, in contrast to the approach in which the value of each given bit corresponds to the energy level at a single corresponding frequency level of the corresponding audio signal, the present methods of adding an identification watermark can increase the reliability of their detection with respect to different types of noise, superimposed on the original audio signal during its transmission, playback and conversion. As a result, the present methods and systems may improve the detection of identification watermarks in the audio signals of recordings that are part of the intellectual property of organizations associated with the virtual assistant application, which may further allow the identification of NDA violating raters. In addition, after unscrupulous evaluators are identified, preventive measures can be taken against them in a timely manner, such as restricting further access to their accounts on crowdsourcing platforms, in order to prevent further leakage of information.

[0017] As can be understood, the present methods and systems for identifying NDA violating users are not limited solely to records used in virtual assistant applications; rather, they can be used to protect different types of audio clips from illegal disclosure, such as audio clips from audio recording companies, music subscription apps, and the like.

[0018] More specifically, in accordance with the first broad aspect of the present invention, a computer-implemented method is provided.

[0019] More specifically, in accordance with a first broad aspect of the present invention, there is provided a computer-implemented method for augmenting an audio clip to be provided to an evaluator for performing one or more digital tasks. The addendum is intended to modify the audio clip to include data suitable for determining the identification information of the scoring person to determine the relationship between the audio clip and the scoring person. The method is run on a production server. The method comprises: receiving an audio clip by a production server, wherein the audio clip has been pre-recorded; receiving by the production server an identification indicator of the scoring person to whom the audio clip is to be transmitted, the identification indicator being represented by a unique sequence of bits; generating by the production server, based on the unique bit sequence, an identification watermark associated with the scoring person and to be included in the audio clip to generate the augmented audio clip, wherein the generation includes: determining by the production server for a given bit a unique bit sequence of at least two different frequency levels from a predetermined audio spectrum for carrying the value of a given bit in an audio signal associated with the augmented audio clip, wherein the first of at least two different frequency levels is for indicating the value of the given bit; others of at least two different frequency levels are designed to duplicate the values indicated by the first of at least two frequencies; and the value of the specified bit is indicated by a predetermined energy level of the audio signal; modifying by the production server the audio signal to have a predetermined energy level at each of at least two different frequency levels to indicate the presence of a predetermined bit from the unique bit sequence associated with the scoring person in the augmented audio clip; and transmitting the augmented audio clip including the identification watermark to an electronic device associated with the scoring person to perform one or more digital tasks based on the evaluation of the augmented audio clip.

[0020] In some embodiments of the method, the value of a given bit is a binary value, wherein "0" is represented by the zero energy level of the audio signal associated with the augmented audio clip at each of at least two different frequency levels; and a change including excluding a corresponding portion of the audio signal at each of the at least two different frequency levels.

[0021] In some embodiments of the method, the exclusion of the corresponding part from the audio signal generates a silent gap when playing the augmented audio signal, and the silent gap is essentially not recognizable by the human ear.

[0022] In some implementations of the method, the exclusion includes applying an appropriate notch filter to the audio signal.

[0023] In some embodiments of the method, the predetermined audio spectrum comprises an audio spectrum recognizable by the human ear.

[0024] In some embodiments of the method, each of at least two different frequency levels is selected within a respective range of a predetermined audio spectrum.

[0025] In some embodiments of the method, each of the at least two different frequency levels is randomly selected.

[0026] In some embodiments of the method, each of the at least two different frequency levels has been preselected arbitrarily.

[0027] In some embodiments of the method, each of at least two different frequency levels is selected in a predetermined step.

[0028] In some embodiments of the method, modifying an audio signal includes first converting the audio signal into its time-frequency representation.

[0029] In some embodiments of the method, the transformation includes applying a Fourier transform to the audio signal.

[0030] In accordance with a second broad aspect of the present invention, a computer-implemented method for determining a relationship between a scoring person and a given audio clip is provided. The method is performed by an electronic device. The method includes: capturing by the electronic device an in-use audio signal generated in the vicinity of the electronic device in response to playing a predetermined audio clip; determining by the electronic device the presence of an identification watermark associated with the scoring person in the audio signal in use, the identification watermark having been generated based on the scoring person's identification indicator, the identification indicator being represented by a unique bit sequence; a respective value of a given bit from the unique bit sequence is indicated in the given audio clip by varying the respective energy levels of the original audio signal associated with it at at least two different frequency levels; determining a respective predetermined bit value includes: determining by the electronic device a respective primary energy level of the audio signal in use at each of at least two different frequency levels; determining by the electronic device a respective secondary energy level of the in-use audio signal at a respective adjacent frequency level for each of the at least two different frequency levels; determining by the electronic device, for each of the at least two different frequency levels, a respective difference between a respective primary energy level and a respective secondary energy level of the audio signal in use; combining by the electronic device the respective deltas associated with at least two different frequency levels to determine a combined delta value associated with a given bit; determining, based on the combined difference value, a corresponding value of a given bit to include in the in-use bit sequence associated with the in-use audio signal; and in response to matching the bit sequence in use to a unique bit sequence associated with the evaluator, determining the presence of the identification watermark in the audio signal in use, thereby determining the given audio clip as being personalized for the evaluator to transmit to him for performing one or more digital tasks. based on the rating of the given audio clip.

[0031] In some embodiments of the method, the corresponding value of a given bit is a binary value, combining the corresponding difference values includes: determining the first combined value as the sum of the corresponding difference values associated with the values of at least two different frequency levels, in which the corresponding primary levels energies indicate that the corresponding value of the given bit is "1"; determining the second combined value as the sum of the respective difference values associated with the values of at least two different frequency levels, at which the respective primary energy levels indicate that the respective value of the specified bit is "0"; determining the combined difference value as the difference between the first combined value and the second combined value; and wherein determining a corresponding value of a given bit based on the combined difference value includes: determining a corresponding value as "1" if the combined difference value is a positive value; and determining the corresponding value as "0" if the combined difference value is a non-positive value.

[0032] In some embodiments of the method, the method further comprises, for a given frequency level, from at least two different frequency levels, wherein the given frequency level is associated with the corresponding primary energy level of the audio signal in use at the given frequency level: determining a first corresponding secondary energy level at a first respective adjacent frequency level higher than the predetermined frequency level; determining a second respective secondary energy level at a second adjacent frequency level lower than the predetermined frequency level; determining a first respective difference value between the respective primary energy level and the first respective secondary energy level; determining a second respective difference between the respective primary energy level and the second respective secondary energy level, wherein: determining the respective difference includes determining the minimum of the first respective difference and the second respective difference.

[0033] In some embodiments of the method, the electronic device is an electronic device associated with the evaluator.

[0034] In some embodiments of the method, the method is performed by a server configured to receive a given audio clip, and an in-use audio signal is generated by the server by processing the given audio clip.

[0035] In some embodiments of the method, the server is configured to obtain a given audio clip by searching for at least one network resource for it.

[0036] In some embodiments of the method, determining the presence of an identification watermark in an audio signal in use includes first converting the audio signal in use into its time-frequency representation.

[0037] In some embodiments of the method, determining a given audio clip as personalized for the scoring person further includes generating a predefined notification by the electronic device for transmission to a subject associated with the production of the given audio clip.

[0038] In accordance with a third broad aspect of the present invention, a system is provided for supplementing an audio clip provided to an evaluator for performing one or more digital tasks. The addendum is intended to modify the audio clip to include data suitable for identifying the scoring person's identification information to determine the relationship between the audio clip and the scoring person. The system includes a production server including: a processor and a non-volatile computer-readable medium containing instructions. The processor, after executing the instructions, is adapted to: receive an audio clip, the audio clip having been pre-recorded; receive an identification indicator of the scoring person to whom the audio clip is to be transmitted, the identification indicator being represented by a unique sequence of bits; generate, based on the unique bit sequence, an identification watermark associated with the scoring person to be included in the audio clip to generate the augmented audio clip by: determining for a given bit from the unique bit sequence at least two different frequency levels from a predetermined audio spectrum to carry the value of the given a bit in the audio signal associated with the augmented audio clip, wherein the first of at least two different frequency levels is for indicating the value of the given bit; others of at least two different frequency levels are designed to duplicate the values indicated by the first of at least two frequencies; and the value of the specified bit is indicated by a predetermined energy level of the audio signal; modify the audio signal to have a predetermined energy level at each of at least two different frequency levels to indicate the presence of a given bit from the unique bit sequence associated with the rater in the augmented audio clip; and transmitting the augmented audio clip including the identification watermark to an electronic device associated with the scoring person to perform one or more digital tasks based on the evaluation of the augmented audio clip.

[0039] As used herein, the terms "audio clip" and "audio file" broadly refer to any digital audio file and/or analog audio tracks (including those that are part of a video) of any format and nature, including, but not limited to, advertisements , news feeds, blog video and TV show soundtracks, etc. Essentially, audio clips, as mentioned herein, are electronic media objects that represent electrical signals having frequencies corresponding to human hearing and suitable for transmission, reception, storage, and playback using suitable software and hardware.

[0040] As used herein, a "server" is a computer program that runs on appropriate hardware and is capable of receiving requests (eg, from client devices) over a network and fulfilling or causing those requests to be executed. The hardware may be one physical computer or one physical computer system, but neither is a requirement for the present invention. In the present context, the use of the term "server" does not imply that every task (e.g., received instructions or requests) or any particular task will be received, executed, or called for execution by the same server (i.e., the same software software and/or hardware); this expression implies that any number of software elements or hardware devices can be involved in receiving / sending, executing or calling to perform any task or request, or the consequences of any task or request; and all of this software and hardware may be a single server or multiple servers, both of which are included in the expression "at least one server".

[0041] As used herein, a "client device" is any computer hardware that is capable of executing software that is appropriate for the relevant task at hand. Thus, some (non-limiting) examples of client devices include personal computers (desktops, laptops, netbooks, etc.), smartphones and tablets, and network equipment such as routers, switches, and gateways. It should be noted that a device acting as a client device in the present context is not excluded from acting as a server for other client devices. The use of the term "client device" does not preclude the use of multiple client devices in receiving/sending, executing, or calling to perform any task or request, or the consequences of any task or request, or the steps of any method described herein.

[0042] As used herein, a "database" is any structured collection of data, regardless of its specific structure, database administration software, or computer equipment on which data is stored, implemented, or otherwise made available for use. The database may reside on the same hardware as the process that stores or uses the information stored in the database, or it may reside on separate hardware such as a dedicated server or multiple servers.

[0043] In the context of the present description, the expression "information" includes information of any nature or kind that is capable of being stored in the database in any way. Thus, information includes, but is not limited to, audiovisual works (images, films, sound recordings, presentations, etc.), data (location data, numerical data, etc.), text (opinions, comments, questions , messages, etc.), documents, spreadsheets, word lists, etc.

[0044] As used herein, unless specifically noted otherwise, the term "component" is intended to include software (as appropriate to a particular hardware context) that is both necessary and sufficient to implement a particular function(s), on which is being referenced.

[0045] As used herein, the expression "computer-used storage medium" is intended to include media of any kind and kind, including RAM, ROM, disks (CD-ROMs, DVDs, floppy disks, hard disk drives, etc.). .d.), USB keys, solid state drives, tape drives, etc.

[0046] In the context of the present description, the words "first", "second", "third", etc. are used as adjectives only to allow the nouns they modify to be distinguished from each other, and not to describe any particular relationship between such nouns. Thus, for example, it should be understood that the use of the terms "first server" and "third server" does not imply any particular order, type, chronology, hierarchy or ranking (for example) of such servers, nor does their use (in itself ) does not mean that some "second server" must necessarily exist in any given situation. Also, as discussed elsewhere in this document, reference to a "first" element and a "second" element does not exclude that the two elements are in fact the same real world element. Thus, for example, in some cases the "first" server and the "second" server may be the same software and/or hardware, in other cases they may be different software and/or hardware.

[0047] Each of the implementations of the present invention has at least one of the above aspects and/or objectives, but not necessarily all of them. It should be understood that some aspects of the present invention, which have arisen in an attempt to achieve the above goal, may not satisfy this goal and/or satisfy other goals that are not explicitly described in this document.

[0048] Additional and/or alternative features, aspects, and advantages of implementations of the present invention will become apparent from the following description, the accompanying drawings, and the appended claims.

BRIEF DESCRIPTION OF THE DRAWINGS

[0049] For a better understanding of the present invention, as well as other aspects and additional features thereof, reference is made to the following description, which is to be used in conjunction with the accompanying drawings, in which:

[0050] In FIG. 1 is a schematic diagram of an exemplary computer system for implementing some non-limiting embodiments of systems and/or methods of the present invention;

[0051] In FIG. 2 depicts a networked computing environment suitable for padding an audio clip with an appropriate identification watermark of a given rater, in accordance with some non-limiting embodiments of the present invention;

[0052] In FIG. 3 is a schematic diagram of a generation process by a server present in the networked computing environment shown in FIG. 2, a binary sequence based on the identities of a given estimator, which can then be used to generate a corresponding identity watermark, in accordance with some non-limiting embodiments;

[0053] In FIG. 4 is a schematic diagram of the generation step by the server present in the networked computing environment of FIG. 2, a time-frequency representation of the audio signal associated with the audio clip to be padded with the appropriate identification watermark of a given evaluator, in accordance with some non-limiting embodiments of the present invention;

[0054] In FIG. 5 is a schematic diagram of the generation step by the server present in the networked computing environment of FIG. 2 of the amplitude-time representation of the audio signal of the augmented audio clip of FIG. 4 to be communicated to a given evaluator, in accordance with some non-limiting embodiments of the present invention;

[0055] In FIG. 6 is a flowchart of a method for adding a server present in the networked computing environment shown in FIG. 2, an audio clip to be submitted to a given evaluator, in accordance with some non-limiting embodiments of the present invention;

[0056] In FIG. 7 is a schematic diagram of another implementation of the network computing environment of FIG. 2 suitable for determining a relationship between a given estimator and an in-use audio clip played near an electronic device, in accordance with some non-limiting embodiments of the present invention;

[0057] In FIG. 8 is a schematic diagram of a generation step by an electronic device present in the networked computing environment shown in FIG. 7 of a time-frequency representation of an audio signal associated with an audio clip in use, in accordance with some non-limiting embodiments of the present invention;

[0058] In FIG. 9 is a schematic diagram of a process for determining the network computing environment shown in FIG. 7, the presence of an appropriate identification watermark in an audio clip in use, in accordance with some non-limiting embodiments of the present invention. technology; And

[0059] In FIG. 10 is a flowchart of a method for determining a relationship between a given estimator and an in-use audio clip played in the vicinity of the electronic device of the networked computing environment of FIG. 7 in accordance with some non-limiting embodiments of the present invention.

Detailed description

[0060] The examples and conventions set forth herein are intended primarily to help the reader understand the principles of the present invention, and not to limit its scope to such specific examples and terms. It should be clear that specialists in this field will be able to develop various mechanisms that, although not explicitly described in this document, nevertheless embody the principles of the present invention and are included in its spirit and scope.

[0061] In addition, the following description may describe embodiments of the present invention in a relatively simplified manner for purposes of ease of understanding. Those skilled in the art will appreciate that various embodiments of the present invention may be more complex.

[0062] In some cases, examples of modifications of the present invention that are considered useful can also be set forth. This is done only to assist understanding and, again, not to strictly define the scope or delineate the boundaries of the present invention. These changes are not an exhaustive list, and the person skilled in the art can make other changes while still remaining within the scope of the present invention. In addition, cases where examples of modifications are not given should not be construed to mean that no modifications can be made and/or that what is described is the only way to implement such an element of the present invention.

[0063] In addition, all statements contained herein, which indicate the principles, aspects and implementations of the present invention, as well as their specific examples, are intended to cover both structural and functional equivalents, regardless of whether they are currently known time or will be developed in the future. Thus, for example, those skilled in the art will appreciate that any block diagrams herein represent conceptual views of an illustrative circuit embodying the principles of the present invention. Likewise, it will be understood that any flowcharts, sequence diagrams, state transition diagrams, pseudo-codes, and the like represent different processes that can be as such represented on computer-readable media and executed by a computer or processor, whether or not shown. such a computer or processor explicitly or not.

[0064] The functions of the various elements shown in the figures, including any functional block labeled "processor" or "graphics processing unit", can be provided by dedicated hardware, as well as hardware capable of executing software, in combination with proper software. When provided by a processor, the functions may be provided by one dedicated processor, one shared processor, and/or multiple separate processors, some of which may be shared. In some embodiments of the present invention, the processor may be a general purpose processor, such as a central control unit (CPU), or a processor dedicated to a specific purpose, such as a graphics processing unit (GPU). Moreover, explicit use of the term "processor" or "controller" should not be construed as referring solely to hardware capable of executing software, and may implicitly include, without limitation, digital signal processor (DSP) hardware, network processor, ASIC circuit (ASIC), field-programmable gate array (FPGA), read-only memory (memory) (ROM) for storing software, random access memory (RAM), and/or non-volatile (non-volatile) storage. Other hardware, traditional and/or specialized, may also be included.

[0065] Software modules, or simply modules, which may be understood as software, may be represented herein as any combination of flowchart elements or other elements indicating the execution of process steps and/or textual description. Such modules may be executed by hardware that is explicitly or implicitly shown.

[0066] With these fundamentals in mind, consider some non-limiting examples to illustrate different implementations of aspects of the present invention.

computer system

[0067] In FIG. 1 depicts a computer system 100 suitable for use with some embodiments of the present invention. Computer system 100 includes various hardware components including one or more single or multi-core processors collectively represented by processor 110, graphics processing unit (GPU) 111, solid state drive 120, random access memory 130, display interface 140, and I/O interface 150.

[0068] Communication between various components of the computer system 100 may be provided by one or more internal and/or external buses 160, including, for example, without limitation, a Peripheral Component Interconnect (PCI) bus, a universal serial bus (USB), an IEEE bus. 1394 "Firewire", Small Computer System Interface (SCSI) bus, Serial Attached Bus (SATA), and others to which various hardware components are electronically coupled.

[0069] I/O interface 150 may be associated with touch screen 190 and/or one or more internal and/or external buses 160. Touch screen 190 may be part of a display. In some embodiments, the touch screen 190 is a display. Touch screen 190 may also be referred to as screen 190. In the embodiments illustrated in FIG. 1, the touch screen 190 includes touch hardware 194 (e.g., pressure sensitive cells embedded in the display layer to detect physical interaction between the user and the display) and a touch input/output controller 192 enabling communication with the display interface 140 and/or one or more internal and/or external buses 160. In some embodiments, I/O interface 150 may be connected to a keyboard (not shown), mouse (not shown), or trackpad (not shown), allowing a user to interact with computer system 100 in in addition to or instead of touch screen 190. In some embodiments, computer system 100 may include one or more microphones (not shown). Microphones can record audio, such as user utterances. User utterances may be converted into commands to control computer system 100.

[0070] It should be noted that some components of the computer system 100 may be omitted in some non-limiting embodiments of the present invention. For example, touch screen 190 may be omitted, especially (but not limited to) when the computer system is implemented as a smart speaker device.

[0071] In accordance with embodiments of the present invention, the solid state drive 120 stores program instructions suitable for loading into random access memory 130 and execution by processor 110 and/or graphics processor 111. For example, the program instructions may be part of a library or application.

Networked Computing Environment

[0072] In FIG. 2 is a schematic diagram of a networked computing environment 200 suitable for use with certain non-limiting embodiments of the systems and/or methods of the present invention. In some non-limiting embodiments of the present invention, the networked computing environment 200 may include a server 202 configured to provide one or more digital tasks for further execution by a respective one of a plurality of evaluators 208.

[0073] To this end, the server 202 may be communicatively connected via the communication network 210 to the database 204 of the appraisers. In accordance with some non-limiting embodiments of the present invention, the estimator database 204 may contain the identification of each of a plurality of estimators 208 (such as evaluators) available to perform at least one digital task (also referred to herein as a "human task"). intelligence (HIT)”, a crowdsourcing task or just a task) that will be sent to him. In some non-limiting embodiments of the present invention, the identity indicator of a given rater 212 of the set of raters 208 includes specific data to uniquely identify a given rater 212 among the set of raters 208, which may include, without limitation, the name and surname of a given rater 212 , various abbreviations and aliases generated based on at least partial combinations of names and the unique identifier of a given evaluator 212, and the like. In some non-limiting embodiments of the present invention, the identification tag associated with a given estimator 212 may include a unique identification number previously generated for a given estimator 212.

[0074] In some non-limiting embodiments of the present invention, the appraiser database 204 may be managed and/or administered by a crowdsourcing service provider, such as Yandex LLC at 16 Lev Tolstoy Street, 119021, Russia. In alternative non-limiting embodiments of the present invention, the estimator database 204 may be managed by another entity.

[0075] The implementation of the estimator database 204 is not particularly limited, and as such, the estimator database 204 may be implemented using any suitable known technology as long as the functionality described herein is provided. In addition, although in the embodiments depicted in FIG. 2, the estimator database 204 is connected to the server 202 via the communication network 210, it should be noted that in alternative non-limiting embodiments of the present invention, the estimator database 204 may be connected to the server 202 directly via a suitable communication link.

[0076] It is contemplated that the appraiser database 204 may be stored at least in part on the server 202 and/or managed at least in part by the server 202. In accordance with non-limiting embodiments of the present invention, the appraiser database 204 contains sufficient information associated with the identities of at least some of the plurality of evaluators 208 to allow an entity having access to the evaluator database 204, such as a server 202, to designate and transmit one or more digital tasks to be performed by the evaluators.

[0077] In some non-limiting embodiments of the present invention, the server 202 may be controlled by the same entity that manages the evaluator database 204. In alternative non-limiting embodiments of the present invention, the server 202 may be controlled by an entity other than the one that manages the evaluator database 204.

[0078] In some non-limiting embodiments of the present invention, the server 202 may be implemented as a conventional computer server and thus may contain some or all of the components of the computer system 100 of FIG. 1. As a non-limiting example, server 202 may be implemented as a Dell™ PowerEdge™ server, running an operating room Microsoft™ Windows Server™ systems. Needless to say, the server 202 may be implemented in any other suitable hardware and/or software and/or firmware, or combinations thereof. In the illustrated non-limiting embodiment of the present invention, the server 202 is the only server. In alternative non-limiting embodiments of the present invention, the functionality of the server 202 may be distributed and may be implemented by multiple servers.

[0079] In addition, in accordance with some non-limiting embodiments of the present invention, the server 202 may be communicatively connected via an appropriate communication link to the task database 206 . As can be understood, in alternative non-limiting embodiments of the present invention, the task database 206 may be connected to the server 202 via the communication network 210. Although the task database 206 is schematically illustrated here as a single entity, it is contemplated that the task database 206 may be implemented in a distributed manner.

[0080] Generally speaking, task database 206 may be populated with digital tasks to be performed by at least some of the plurality of evaluators 208. How task database 206 is populated with tasks is not limited. Generally speaking, one or more task requesters (not shown separately) may submit one or more tasks for storage in the task database 206 . In some non-limiting embodiments of the present invention, one or more task requesters may indicate the type of evaluators to which the task is intended and/or the budget to be allocated to each of the plurality of evaluators 208 providing a result.

[0081] For example, a given task requestor could send to the task database 206 a given digital task 214; and the server 202 may be configured to retrieve a given digital task 214 from the task database 206 and assign the given digital task to one of a plurality of evaluators 208, such as a given evaluator 212. In addition, the server 202 may be configured to provide a given digital task 214 to a given evaluator 212 by transmitting an indication of the given digital task 214 via the communication network 210 to the corresponding electronic device (not separately labeled) of the given evaluator 212.

[0082] According to various non-limiting embodiments of the present invention, the respective electronic device (not indicated separately in FIG. 2) associated with a given estimator 212 of the plurality of estimators 208 may be a device including hardware running the respective software. software suitable for performing a respective current task (such as a given digital task 214), including, but not limited to, a personal computer, laptop computer, or smartphone, for example. To this end, a suitable electronic device may include some or all of the components of the computer system 100 depicted in FIG. 1.

[0083] Accordingly, to allow a given evaluator 212 to receive digital tasks from the server 202 and provide responses to them from its respective electronic device, in some non-limiting embodiments of the present invention, the server 202 may be configured to execute a crowdsourcing application (not shown). ). For example, a crowdsourcing application may have a client-server architecture, with most of its functionality running on the server 202; and the given estimator 212 may have a corresponding user account in the crowdsourcing application allowing it to receive digital tasks from the server 202 and send its responses to it. In a specific non-limiting example, a crowdsourcing application may be implemented as a crowdsourcing platform such as the Yandex Toloka™ crowdsourcing platform, or other proprietary or commercially available crowdsourcing platform.

[0084] In addition, in some non-limiting embodiments of the present invention, the given digital task 214 includes an audio clip 216. task 214 may be a classification task instructing a given evaluator 212 to determine a category of user that makes statements in a human voice, such as child, adult, and the like. For example, the response of a given estimator 212 to such a digital task can be used to generate an appropriate training dataset for further training an MLA to classify users of a given electronic device.

[0085] However, in other non-limiting embodiments of the present invention, audio clip 216 associated with a given digital task 214 may contain a recording of a predefined voice response to be used in a given voice service application in response to one or more user requests. For example, a given voice service application may include a virtual assistant application adapted to fulfill voice requests from a user of a given electronic device (eg, smart speaker) running the virtual assistant application. For example, the virtual assistant application may be implemented as an ALISA™ virtual assistant application (provided by Yandex LLC, 16 Lev Tolstoy St., Moscow, 119021 Moscow, Russia); however, other commercial or proprietary virtual assistant applications may also be provided without departing from the scope of the present invention.

[0086] Thus, in these embodiments, the given digital task 214 may include instructions for the given evaluator 212, for example, to convert a predefined voice response to its textual representation. In another example, the given digital task 214 may include instructions for the given evaluator 212 to translate a predefined voice response into another language. Furthermore, in yet another example, through performing a given digital task 214, a given evaluator 212 may be invited to evaluate the quality (e.g., using an appropriate quality scale) of the recording, e.g. a specific voice response, etc. In yet another example, the given digital task 214 may include instructions for determining matches between a predefined voice response and one or more user voice requests, in response to which the virtual assistant application may be further configured to generate a predefined voice response. It should be noted that the above examples are not an exhaustive list, and other examples of digital tasks in relation to the corresponding audio clip can also be provided without going beyond the scope of the present invention.

[0087] Thus, in accordance with some non-limiting embodiments of the present invention, upon receiving a given digital task 214 using a crowdsourcing application, a given estimator 212 can provide a response to it, which the corresponding electronic device of the given estimator 212 is configured to transmit to server 202. However, making audio clip 216 associated with a given digital task 214 available to a given evaluator 212 may allow him to misuse the audio clip 216. For example, a given evaluator 212 may record audio clip 216 associated with a given digital task 214 using their personal electronic devices. (not shown). In addition, the predetermined evaluator 212 may post the recorded audio clip to their private social network pages and/or forward the audio clip thus recorded to someone else. As can be appreciated, these actions may result in the unauthorized public disclosure of the audio clip 216 associated with a given digital task 214, which may further cause some financial and reputational damage to the organization that owns the virtual assistant application.

[0088] To this end, in accordance with some non-limiting embodiments of the present invention, the server 202 may be configured to personalize a given digital task 214 for execution by a given evaluator 212. More specifically, before sending a given digital task 214 to a given evaluator 212 in In some non-limiting embodiments of the present invention, the server 202 may be configured to add to the audio clip 216 associated with the given digital task 214, an identification watermark indicating the identification information of the given estimator 212 and thus allowing further determination of the relationship between it and the given digital task 214. digital task 214.

[0089] Thus, in some non-limiting embodiments of the present invention, the server 202 may be configured to (1) receive from the estimator database 204 at least one identification indicator 218 of a given estimator 212 to which the original audio clip of a given digital task 214 is intended ; (2) generate, based on at least one identification index 218 of the given evaluator 212, the corresponding identification watermark associated with it, to add to the original audio clip of the given digital task 214; (3) receive, from the task database 206, a given digital task 214; (3) extract from the given digital task 214 audio clip 216; (4) add to the audio clip 216 an appropriate identification watermark, thereby generating the augmented audio clip 220; and (5) include the augmented audio clip 220 in the given digital task 214 instead of the original audio clip 216 to pass the given digital task 214 to the given evaluator 212 for execution.

[0090] In some non-limiting embodiments of the present invention, in order to add an appropriate identification watermark, the server 202 may first be configured to represent at least one identification pointer 218 of a given estimator 212, such as its name and a unique identifier, as specified above, or its login name to the crowdsourced application, for example, as a unique binary sequence. To this end, for example, the server 202 may be configured to apply the encoding algorithm 302 as shown in FIG. 3 in accordance with some non-limiting embodiments of the present invention.

[0091] According to non-limiting embodiments of the present invention, how the encoding algorithm 302 is implemented is not limited; and in some non-limiting embodiments of the present invention may include a lossless coding algorithm such as an arithmetic coding algorithm, a Huffman coding algorithm, a Shannon coding algorithm, and the like. In other non-limiting embodiments of the present invention, encoding algorithm 302 may include a lossy encoding algorithm such as a linear prediction encoding algorithm, a discrete cosine transform encoding algorithm, and the like.

[0092] Thus, the encoding algorithm 302 may be configured to generate, based on at least the identification indicator 218, a binary sequence 304 that uniquely identifies a given estimator 212 among others from a plurality of estimators 208. Although in the depicted embodiments, the binary sequence 304 is 16 bits, it should be clearly understood that in other non-limiting embodiments of the present invention, binary sequence 304 may include 8, 32, or 64 bits, for example, without departing from the scope of the present invention.

[0093] Thus, in some non-limiting embodiments of the present invention, server 202 may be configured to encode binary sequence 304 into audio clip 216, thereby adding to it an appropriate identification watermark associated with a given estimator 212, and generating an augmented audio clip. 220. In addition, as will become apparent from the description below, after playback of the augmented audio clip 220, its augmented audio signal can be captured by an electronic device capable of recognizing the respective identification watermarks. Thus, in the event that a given evaluator 212 misused the augmented audio clip 220 in performing a given digital task 214, his identity can be established and appropriate preventive action can be taken against him, such as restricting access to his account in the crowdsourced application. , adding him to the black list of appraisers, initiating lawsuits against him, and the like.

[0094] How the server 202 can be configured to add an appropriate identification watermark to the audio clip 216 in accordance with some non-limiting embodiments of the present invention will be described below with reference to FIG. 4-6.

[0095] How a corresponding identification watermark can be recognized by an electronic device in accordance with some non-limiting embodiments of the present invention will be further described below with reference to Figures 7-10.

Communication network

[0096] In some non-limiting embodiments of the present invention, communication network 210 is the Internet. In alternative non-limiting embodiments of the present invention, communications network 210 may be implemented as any suitable local area network (LAN), wide area network (WAN), private communications network, and the like. It should be clearly understood that the implementations for the communication network are for purposes of illustration only. How a respective communication link (not individually numbered) is implemented between each of the servers 202 and a given one of the electronic devices of the set of estimators 208 and the communication network 210 will depend, among other things, on how each of the server 202 and the given one of the electronic devices of the set 208 appraisers implemented. Just by way of example, and not limitation, in those embodiments of the present invention where a given one of the respective electronic devices of the plurality of evaluators 208 is implemented as a wireless communication device, such as a smart speaker, the communication link may be implemented as a wireless communication link. Examples of wireless links include, but are not limited to, a 3G link, a 4G link, and the like. The communications network 210 may also use a wireless connection to the server 202 and each of the electronic devices of the plurality of evaluators 208.

Generating an identification watermark in an audio clip

[0097] As mentioned above, in order to generate an augmented audio clip 220 for a given estimator 212, in some non-limiting embodiments of the present invention, the server 202 may be configured to generate a corresponding identification watermark in the audio clip 216, which may be represented by a binary sequence 304. In others In other words, to generate the augmented audio clip 220, the server 202 may be configured to change the energy levels of the original audio signal of the audio clip 216 by encoding the binary sequence 304 therein.

[0098] To this end, first of all, according to some non-limiting embodiments of the present invention, the server 202 may be configured to generate a time-frequency representation of the initial audio signal associated with the audio clip 216. In FIG. 4 is a schematic diagram for a process for server 202 to generate time-frequency representation 404 associated with audio clip 216, in accordance with some non-limiting embodiments of the present invention.

[0099] In some non-limiting embodiments of the present invention, first of all, the server 202 may be configured to generate an amplitude-time representation 402 of the initial audio signal associated with the audio clip 216. To this end, the server 202 may be configured to use one or more sampling techniques to the initial audio signal. For example, but not limited to, the server 202 may be configured to use a sampling technique based on the Nyquist frequency.

[00100] In addition, in some non-limiting embodiments of the present invention, the server 202 may be configured to apply a Fourier transform to the amplitude-time representation 402 of the initial audio signal to generate the time-frequency representation 404 associated with it. Generally speaking, applying a Fourier transform allows one to demonstrate how the frequency components of a given audio signal (eg, the initial audio signal associated with audio clip 216) change over time.

[00101] In some non-limiting embodiments of the present invention, the Fourier transform may include a discrete Fourier transform (DFT). How the server 202 may be configured to calculate the DFT is not limited, and in various embodiments of the present invention may include the use of one of a family of Fast Fourier Transform (FFT) algorithms, further including a simple coefficient FFT algorithm, FFT algorithm Bruun, Ryder FFT, Bluestein FFT, and Hexagonal FFT.

[00102] In addition, it should be noted that in order to generate a time-frequency representation 404 of the initial audio signal, the server 202 can also be configured to apply other discrete transforms to it, including, but not limited to: a generalized DFT, a Fourier transform in discrete space, Z-transform, modified discrete cosine transform, discrete Hartley transform, etc.

[00103] In some non-limiting embodiments of the present invention, server 202 may be configured to apply a Fourier transform to amplitude-time representation 402 using a time-window accumulation approach. More specifically, the server 202 may be configured to segment the amplitude-time representation 402 into a plurality of parts thereof based on a predetermined time window 406 Δt. In addition, the server 202 may be configured to apply a Fourier transform to each of the plurality of portions corresponding to the duration of the predetermined time window 406.

[00104] It should be noted that this is not limited to how the length of the predetermined time window 406 is determined, and in some non-limiting embodiments of the present invention, the length of the predetermined time window 406 for audio clip 216 may be chosen based on a trade-off between temporal resolution and the frequency resolution of the time-frequency representation 404, for example, the "already" given time window 406, the better the time resolution and the worse the frequency resolution of the time-frequency representation 404 associated with the audio clip 216, and vice versa.

[00105] In addition, in some non-limiting embodiments of the present invention, the server 202 may be configured to change the time-frequency representation 404 in accordance with the binary sequence 304, thereby adding to it the appropriate identification watermark associated with a given estimator 212 .

[00106] For example, in accordance with some non-limiting embodiments of the present invention, the server 202 may be configured to encode the corresponding value of each bit of the binary sequence 304 in the time-frequency representation 404 by changing the original audio signal so that it has a corresponding predetermined level energy at a respective single predetermined frequency level within at least one instance of the predetermined time window 406.

[00107] However, in other non-limiting embodiments of the present invention, for a given bit of binary sequence 304, server 202 may be configured to determine an appropriate set of predefined frequency levels, where the first of these is used to indicate the value of a given bit; and others from the respective set of predetermined frequency levels are designed to reproduce the value of the given bit specified first. To this end, the server 202 may be further configured to modify the initial audio signal of the audio clip 216 to have a respective predetermined energy level at each of a respective set of predetermined frequency levels within at least one instance of the predetermined time window 406. Such an approach to reproducing the value of a given bit of the binary sequence 304 in the time-frequency representation 404 may allow the corresponding identification watermark thus generated to be more resistant to various types of noise that may be superimposed on the audio signal of the augmented audio clip 220 during its transmission, reception and conversion.

[00108] For example, the corresponding set of predefined frequency levels may include at least two frequency levels, each of which is different from each other. It should be clearly understood that this is not limited to how server 202 may be configured to determine each of the at least two frequency levels to indicate the value of a given bit of binary sequence 304. For example, in some non-limiting embodiments of the present invention, server 202 may be configured to select each of at least two frequency levels from a predetermined audio spectrum. In some non-limiting embodiments of the present invention, the predetermined audio spectrum may be an audio spectrum recognizable by the human ear, for example, from about 20 Hz to about 20,000 Hz. However, in other non-limiting embodiments of the present invention, other audio spectra, such as an infrasound spectrum spanning from about 0 Hz to about 20 Hz, or an ultrasound spectrum spanning from about 20,000 Hz to about 200,000 Hz, as well as specific audio spectra, including into itself, at least in part, some of the sound spectra mentioned above can also be represented without going beyond the scope of the present invention.

[00109] In addition, in some non-limiting embodiments of the present invention, the server 202 may be configured to select each of at least two frequency levels associated with a given bit within a predetermined audio spectrum, in an arbitrary manner - for example, based on a predetermined distribution (eg, normal distribution) of frequency levels in the time-frequency representation 404 associated with the audio clip 216. However, in other non-limiting embodiments of the present invention, each of at least two different frequency levels may be pre-selected for a given bit of the binary sequence 304, for example, before server 202 starts modifying audio clip 216. In these embodiments, each of the at least two frequency levels can also be preselected at random from a predetermined distribution of frequency levels in a plurality of audio clips, for example.

[00110] In other non-limiting embodiments of the present invention, the server 202 may be configured to select another one of the at least two frequency levels as spaced apart from the first of the at least two frequency levels with a predetermined step. For example, in some non-limiting embodiments of the present invention, the predetermined step may be 0.1 Hz, 20 Hz, 400 Hz, or 1300 Hz.

[00111] In other non-limiting embodiments of the present invention, server 202 may be configured to select each of two frequency levels associated with a given bit from a respective subband of a predetermined audio spectrum. For example, server 202 may be configured to select a first of at least two frequency levels from a lower subband of a predetermined audio spectrum; and selecting another of the at least two frequency levels from a higher sub-band of the predetermined audio spectrum, and the like. For example, in those embodiments of the present invention where the predetermined audio spectrum is the audio spectrum recognizable by the human ear, the first of at least two frequency levels may be selected from a subrange of about 20 Hz to about 100 Hz; and the other of the at least two frequency levels may be selected from a subrange of about 1000 Hz to about 20,000 Hz. In other non-limiting embodiments of the present invention, as will be apparent from the description below, the server 202 may be configured to select the other of at least two frequency levels such that the initial audio signal of the audio clip 216 has the same amplitude value (or otherwise, within its predetermined variations, eg ±5 dB) on it as on the first of at least two frequency levels.

[00112] It should be noted that other techniques for determining frequency levels for a respective set of predetermined frequency levels to indicate a given bit of binary sequence 304, such as based on a predetermined function, may also be provided without departing from the scope of the present invention.

[00113] In addition, it should be noted that in those embodiments where the given one of the at least two frequency levels is not available, or in other words, is not present in the frequency spectrum of the original audio signal, to indicate the given bit of the binary sequence 304, the server 202 may be configured to add respective predetermined portions to the initial audio signal, thereby filling a gap corresponding to a predetermined one of at least two frequency levels. However, in other non-limiting embodiments of the present invention, the server 202 may be configured to select at least two frequency levels only from those that form the frequency spectrum of the original audio signal of the audio clip 216.

[00114] In addition, it should be clearly understood that the indication of a given bit of the binary sequence 304 by a set of individual frequency levels is described in this document only for the purpose of explaining the present invention clearly; and in some non-limiting embodiments of the present invention, server 202 may be configured to indicate a given bit of binary sequence 304 by means of an appropriate set of frequency bands, with each frequency band having a predetermined bandwidth such as 5 Hz, 10 Hz, or 25 Hz , For example.

[00115] Thus, as an example, as can be understood from FIG. 4, server 202 may be configured to determine (i) a first set of frequency levels 408 to indicate in time-frequency representation 404 associated with audio clip 216, for example, the first bit of binary sequence 304 having a value of "1"; and (ii) a second set of frequency levels 410 to indicate, for example, the second bit of the binary sequence 304 having the value "0". In addition, it can be understood that each of the first frequency level set 408 and the second frequency level set 410 includes at least two different frequency levels, i.e.f ₁ , f' ₁ Andf ₂ , f' ₂ ,respectively _.

[00116] In addition, according to some non-limiting embodiments of the present invention, in order to indicate the values of each of the first bit and second bit of the binary sequence 304 in the audio clip 216, the server 202 can be configured to change the initial audio signal so that it has a corresponding previously a certain energy level at each of the first set of frequency levels 408 and the second set of frequency levels 410 within at least one instance of a predetermined time window 406. To this end, in some non-limiting embodiments of the present invention, the server 202 may be configured to modulate the amplitude of the initial audio signal at each of the first set of frequency levels 408 and the second set of frequency levels 410 to have their respective predetermined value.

[00117] For example, to indicate the value "1" of the first bit of the binary sequence 304 in the audio clip 216, the server 202 can be configured to modulate the amplitude of the initial audio signal within at least one instance of the specified time window 406 so that it has on each of the first frequency level set 408 a first predetermined amplitude value, such as 30 or 50 dB, for example. However, in other non-limiting embodiments of the present invention, the server 202 may be configured to modify the initial audio signal to have a respective amplitude value at each of the first set of frequency levels no less than a first predetermined amplitude value. In other non-limiting embodiments of the present invention, to indicate a value of '1' of the first bit of binary sequence 304, server 202 may be configured to change the initial audio signal to have a non-zero corresponding amplitude value at each of the first set of frequency levels 408 within at least one instance of a predefined time window 406.

[00118] In addition, in accordance with some non-limiting embodiments of the present invention, in order to indicate the value "0" of the second bit of the binary sequence 304, the server 202 can be configured to modulate the amplitude of the initial audio signal so that it has a second predetermined amplitude value (eg, 10 or 20 dB) at each of the second set of frequency levels 410 within at least one instance of a predefined time window 406. Similarly, in other non-limiting embodiments of the present invention, the server 202 may be configured to changing the initial audio signal to have an amplitude of each of the second set of frequency levels 410 not exceeding a second predetermined amplitude to indicate a value of "0" of the second bit.

[00119] In specific non-limiting embodiments of the present invention, the server 202 may be configured to indicate the value "0" of the second bit of the binary sequence 304 with the zero energy level of the initial audio signal of the audio clip 216 at each of the second set of frequency levels 410 within at least one instance of the predetermined time window 406. To this end, in some non-limiting embodiments of the present invention, the server 202 may be configured to exclude respective portions of the initial audio signal corresponding to each of the second set of frequency levels 410.

[00120] In some non-limiting embodiments of the present invention, in order to exclude a corresponding portion of the initial audio signal corresponding to a given one of the second set of frequency levels 410, the server 202 may be configured to apply an appropriate notch filter to the initial audio signal.

[00121] Generally speaking, a notch filter (also referred to as a "notch filter") is a signal processing filter configured to remove (or otherwise eliminate) a portion of a given signal (such as the initial audio signal of audio clip 216) at a particular predetermined frequency level, which can be represented in a respective time-frequency representation of a given signal by a respective blank space corresponding to a particular predetermined frequency level.

[00122] Thus, the server 202 may be configured to apply an appropriate notch filter to the initial audio signal of the audio clip 216 to "cut" within at least one instance of the predefined time window 406 portions of the initial audio signal corresponding to each of the second set of frequency levels 410 encoding the second bit of binary sequence 304 as shown in FIG. 4. Accordingly, the parts of the initial audio signal excluded in this way form a corresponding silent gap in it when it is reproduced.

[00123] It should be noted that the server 202 may be configured to modulate specific parameters of the respective identification watermark to be added to the initial audio signal such that the respective silent gap formed therein may be substantially unrecognizable to the human ear. For example, the server 202 may be configured to perform at least one of: modulating (e.g., reducing) the size of the predetermined time window 406, reducing the number of frequency levels to encode the value of the second bit in the time-frequency representation 404 of the initial audio signal, sampling the frequency levels for a second set of frequency levels from subbands of a predetermined audio spectrum including frequency levels poorly perceived by the human ear, and the like. In this regard, in some non-limiting embodiments of the present invention, the corresponding set of predefined frequency levels to indicate the value "0" of a given bit may have fewer predefined frequency levels than that used to indicate the value "1".

[00124] In some non-limiting embodiments of the present invention, in order to apply an appropriate notch filter, server 202 may be communicatively coupled to its analog configuration (not shown). In these embodiments, the respective notch filter may be implemented as an electronic circuit configured to filter a given one of the second set of frequency levels 410. In a specific non-limiting example, the respective notch filter may be one of the types available from TEXAS INSTRUMENTS INC ., 12500 TI Blvd., Dallas, Texas 75243 USA However, it should be clearly understood that the desktop scanner may be implemented in any other suitable hardware.

[00125] In other non-limiting embodiments of the present invention, the server 202 may be configured, by executing the respective instructions, to apply the digital implementation of the respective notch filter, whereby the server 202 is configured to apply the respective mathematical operations to the initial audio signal that are equivalent to applying analog implementation of the corresponding notch filter.

[00126] Thus, by changing the initial audio signal of the audio clip 216 at other respective sets of frequency levels to indicate therein the respective values of each other bit of the binary sequence 304, as described above with respect to the first and second bits, the server 202 can be configured to include the corresponding an identification watermark associated with a given estimator 212.

[00127] In addition, based on the time-frequency representation 404 of the initial audio signal modified to include the respective identification watermark of the given estimator 212, the server 202 may be configured to generate an augmented audio signal of the augmented audio clip 220.

[00128] In FIG. 5 is a schematic diagram of a process for generating an augmented audio time-amplitude representation 502 associated with an augmented audio clip 220 by a processor, in accordance with some non-limiting embodiments of the present invention.

[00129] In some non-limiting embodiments of the present invention, server 202 may be configured to apply an inverse Fourier transform to time-frequency representation 404 associated with audio clip 216. For example, server 202 may be configured to apply an inverse DFT to frequency temporal representation 404 in each instance of its predefined time window 406 to generate the augmented amplitude-time representation 502 associated with the augmented audio signal 220.

[00130] Thus, as described above with reference to FIG. 2, the thus generated padded audio clip 220 may further be included in a given digital task 214 for personalization to be performed by a given evaluator 212. As further mentioned above, when the padded audio clip 220 is played back, the corresponding identification watermark can be detected, for example, electronic device, thereby determining the relationship between the given estimator 212 and the augmented audio clip 220.

First way

[00131] Given the architecture and examples above, it is possible to perform a method of augmenting the audio clip to be provided to the rater, such as personalizing the audio clip 216 to be submitted to a given rater 212 as part of a given digital task 214. FIG. 6 is a flowchart of a first method 600 according to non-limiting embodiments of the present invention. The first method 600 may be performed by the server 202.

Step 602: RECEPTION BY THE PRODUCTION SERVER OF THE AUDIO REVIEW AND THE AUDIO REVIEW HAS BEEN PRE-RECORDED

[00132] The first method 600 begins at step 602, where the server 202 may be configured to receive a given audio clip for adding a corresponding identification watermark associated with a given estimator 212. For example, in some non-limiting embodiments of the present invention, the server 202 may be configured to receive a given audio clip that has been pre-recorded for a given estimator 212 to perform a respective digital task in a crowdsourcing application as described above—for example, audio clip 216 of a given digital task 214.

[00133] Thus, the first method proceeds to block 604.

STEP 604: RECEIPT BY THE PRODUCTION SERVER OF THE IDENTIFICATION OF THE EVALUER TO WHOM THE AUDIO REVIEW SHOULD BE TRANSMITTED

[00134] In addition, at step 604, according to some non-limiting embodiments of the present invention, the server 202 can be configured to receive at least one identification indicator of a given estimator 212. As described above with reference to FIG. 2 and 3, the at least one identification tag of a given evaluator 212 may include, without limitation, its name and a corresponding unique identifier, its crowdsourcing application login name, and the like.

[00135] In addition, in some non-limiting embodiments of the present invention, based on at least one identification indicator, as described above with reference to FIG. 3, the first electronic device 702 may be configured to generate a binary sequence 304 that uniquely identifies a given estimator 212 among others from a plurality of estimators 208.

[00136] Thus, the first method proceeds to block 606.

Step 606: GENERATE BY THE PRODUCTION SERVER, BASED ON THE UNIQUE BIT SEQUENCE, AN IDENTIFICATION WATERMARK ASSOCIATED WITH THE EVALUER TO BE INCLUDED IN THE AUDIO REVIEW TO GENERATE THE ADDED AUDIO REVIEW

[00137] At step 606, according to some non-limiting embodiments of the present invention, server 202 can be configured to encode binary sequence 304 in audio clip 216, thereby generating an augmented audio clip 220 personalized for a given estimator 212.

[00138] To this end, as described above with reference to FIG. 4, the server 202 may be configured to generate a time-frequency representation 404 of the initial audio signal of the audio clip 216. For example, the server 202 may be configured to apply a Fourier transform to the amplitude-time representation 402 of the initial audio signal. In some non-limiting embodiments of the present invention, the server 202 may be configured to apply the Fourier transform in a window stacking approach with a predetermined time window 406, as further mentioned above.

[00139] In addition, the server 202 may be configured to determine frequency levels to indicate the corresponding bit values of the binary sequence 304 in the initial audio signal of the audio clip 216. For example, in some non-limiting embodiments of the present invention, to indicate the value of a given bit of the binary sequence 304, the server 202 may be configured to determine a corresponding set of predefined frequency levels, including at least two different frequency levels, where the first of them is used to indicate the value of a given bit; and others are designed to reproduce the value of the given bit specified first - for example, the first set of frequency levels 408 and the second set of frequency levels 410 used to indicate the first and second bits of the binary sequence 304 in the time-frequency representation 404 of the initial audio signal associated with the audio clip 216.

[00140] As further described above with reference to FIG. 4, in some non-limiting embodiments of the present invention, the server 202 may be configured to determine each of a respective set of predefined frequency levels in an arbitrary manner. In other non-limiting embodiments of the present invention, each of the respective set of predefined set of frequency levels may be arbitrarily predetermined prior to the server 202 receiving audio clip 216. In other non-limiting embodiments of the present invention, each of the respective set of predefined set of frequency levels may be predetermined based on a predetermined step as described above.

[00141] In some non-limiting embodiments of the present invention, server 202 may be configured to select each respective set of predetermined frequency levels from a predetermined audio spectrum, such as an audio spectrum recognizable by the human ear, as further described above.

[00142] Thus, the first method 600 proceeds to block 608.

Stage 608: the change in the production server of the audio signal so that it has a pre -determined level of energy at each of the two different frequency levels, to indicate the presence of a given bit by the unique sequence of bits associated with the evaluating person, in an augmented audio rock

[00143] At step 608, the server 202 may be configured to change the initial audio signal, for example, using its time-frequency representation 404, to have a respective predetermined energy level at each of the respective sets of frequency levels to indicate the value of a given bit of the binary sequence 304 in audio clip 216.

[00144] For example, as described above, to indicate the value "1" of the first bit of the binary sequence 304 in the audio clip 216, the server 202 can be configured to modulate the amplitude of the initial audio signal within at least one instance of the predefined time-frequency time window 406 presentation 404 such that it has, at each of the first set of frequency levels 408, a first predetermined amplitude value, such as 30 or 50 dB, for example. However, in other non-limiting embodiments of the present invention, the server 202 may be configured to modify the initial audio signal to have a respective amplitude value at each of the first set of frequency levels no less than a first predetermined amplitude value. In other non-limiting embodiments of the present invention, in order to indicate a value of "1" of the first bit of the binary sequence 304, the server 202 may be configured to change the initial audio signal so that it has a non-zero corresponding amplitude value at each of the first set of frequency levels 408 within at least one instance of the predefined time window 406 of the time-frequency representation 404.

[00145] In addition, in accordance with some non-limiting embodiments of the present invention, in order to indicate the value "0" of the second bit of the binary sequence 304, the server 202 can be configured to modulate the amplitude of the initial audio signal so that it has a second predetermined amplitude value (eg, 10 or 20 dB) at each of the second set of frequency levels 410 within at least one instance of a predetermined time window 406. Similarly, in other non-limiting embodiments of the present invention, the server 202 may be configured to changing the initial audio signal so that the amplitude of each of the second set of frequency levels 410 does not exceed a second predetermined amplitude value to indicate a value of "0" of the second bit.

[00146] In specific non-limiting embodiments of the present invention, the server 202 may be configured to indicate the value "0" of the second bit of the binary sequence 304 with the zero energy level of the initial audio signal of the audio clip 216 at each of the second set of frequency levels 410 within at least one instance of a predetermined time window 406 of the time-frequency representation 404. To this end, in some non-limiting embodiments of the present invention, the server 202 may be configured to exclude respective portions of the original audio signal corresponding to each of the second set of frequency levels 410.

[00147] In some non-limiting embodiments of the present invention, in order to exclude a respective portion of the initial audio signal corresponding to a given one of the second set of frequency levels 410, the server 202 may be configured to apply an appropriate notch filter to the initial audio signal, as described above.

[00148] As further described above, the server 202 may be configured to exclude a corresponding portion of the initial audio signal to indicate the value of the second bit, so that the silent gap thus formed therein is not recognizable by the human ear.

[00149] Thus, by determining for each bit of the binary sequence 204 an appropriate set of predefined frequency levels and changing the initial audio signal energy levels therein as described above, the server 202 can be configured to generate an augmented audio clip 220.

[00150] Thus, the first method 600 proceeds to block 610.

STEP 610: TRANSFER OF THE ADDED AUDIO REVIEW INCLUDING THE IDENTIFICATION WATERMARK TO AN ELECTRONIC DEVICE ASSOCIATED WITH THE JUDGER TO PERFORM ONE OR MORE DIGITAL TASKS BASED ON THE ADDED AUDIO REVIEW EVALUATION

[00151] At 610, the server 202 may be configured to include the augmented audio clip 220 in the given digital task 214 instead of the audio clip 216 to pass the given digital task to the given estimator 212 for execution.

[00152] Thus, the first method 600 ends.

[00153] Thus, specific embodiments of the method 600 allow the generation of personalized audio clips that form part of the respective digital tasks to be performed by the respective evaluators, for example, those of the plurality of evaluators 208. The respective identification watermarks in the thus personalized audio clips can be further recognized when playing audio clips, and raters who allegedly misused the audio clips, resulting in public access to them, can be identified. In addition, as mentioned above, specific measures may be taken against identified raters in order to prevent further harm to the organization owning the audio clips.

[00154] It will now be described how a personalized audio clip, such as augmented audio clip 220, can be recognized by an electronic device in accordance with some non-limiting embodiments of the present invention.

ID watermark detection

[00155] In FIG. 7 depicts another embodiment of a networked computing environment 200 suitable for determining a relationship between one of a plurality of evaluators 208 and a given in-use audio clip 720, in accordance with some non-limiting embodiments of the present invention.

[00156] As can be understood from FIG. 7, the server 202 may further be communicatively linked via the communications network 210 to a first electronic device 702, which may be associated with a user 704, for example.

[00157] According to a specific non-limiting embodiment of the present invention, the first electronic device 702 may be configured to determine a relationship between audio clips played in its vicinity 706 and each of a plurality of estimators 208, such as a predetermined estimator 212. More specifically, the first electronic the device 702 can be configured to determine whether a given in-use audio clip 720 played near 706 of the first electronic device 702 has been personalized for a given evaluator 212—for example, an augmented audio clip 220 as described above—by determining the presence of an appropriate identification a watermark associated with a given estimator 212.

[00158] As noted above, a given evaluator 212 may share augmented audio 220, for example, by at least one of (1) recording augmented audio 220 using their personal electronic devices; (2) copying the augmented audio clip 220 digital files to your personal electronic devices; and (3) sending copies of the augmented audio clip 220 thus obtained to third parties and/or organizations, for example, by posting them on open public web resources, such as social networks (not shown).

[00159] To this end, in order to enable the first electronic device 702 to determine whether a given in-use audio clip 720 includes a corresponding identification watermark associated with one of the plurality of evaluators 208, the server 202 may be configured to provide the first electronic device 702 of a first data packet 712 including respective identification watermark data associated with each of the plurality of estimators 208 that the first electronic device 702 may be configured to store in its local memory (e.g., one of the solid state drive 120 and the storage device 130 with random access of his computer system 100) for further use. For example, in some non-limiting embodiments of the present invention, the corresponding identification watermark data associated with a given estimator 212 received in the first data packet 712 may include, without limitation, at least one of: (i) binary sequence 304 , representing at least one identification indicator of a given evaluator 212; (ii) indicating the respective sets of frequency levels used to indicate each of the bits of the binary sequence 304, for example, the first set of frequency levels 408 and the second set of frequency levels 410 used to indicate the first and second bits of the binary sequence 304, respectively, as described above with with reference to Fig. 4; and (iii) indicating respective predetermined energy levels to indicate each bit from the binary sequence 304 at each of the respective sets of frequency levels. How the first electronic device 702 may be configured to determine the presence of a corresponding identification watermark in a given audio clip 720 based on the data provided by the server 202 in the first data packet 712 will be described below.

[00160] In some non-limiting embodiments of the present invention, the first electronic device 702 may be implemented similarly to the corresponding estimator electronic device of the target estimator 212; and as such includes one of a personal computer, smartphone, and the like, further including some or all of the components of the computer system 100 shown in FIG. 1.

[00161] In addition, in a certain non-limiting embodiment of the present invention, an in-use predetermined in-use audio clip 720 may be played near 706 of the first electronic device 702 by a second electronic device 710 communicatively coupled to the communication network 210. For example, the second electronic device 710 may be configured to receive digital files of a given in-use audio clip 720 from the communications network 210 and play it using its speaker (not specifically labeled). Thus, how the second electronic device 710 is implemented is not limited; and in some non-limiting embodiments of the present invention, the second electronic device 710 may be implemented similarly to the first electronic device 702 and include, for example, one of a laptop computer, personal computer, smartphone, television, etc. To this end, the second electronic device 710 may also include some or all of the components of the computer system 100 shown in FIG. 1.

[00162] In specific non-limiting embodiments of the present invention, the user 704 of the first electronic device 702 may be a predetermined estimator 212. In these embodiments, the first electronic device 702 may be the private electronic device of the predetermined estimator 212, and the second electronic device 710 may be its corresponding an electronic device configured to perform incoming digital tasks, such as digital task 214, as described above with reference to FIG. 2.

[00163] However, it should be noted that in another non-limiting embodiment of the present invention, the first electronic device 702 and the second electronic device 710 cannot be associated with the same user. To this end, in some non-limiting embodiments of the present invention, the server 202 may be configured to send to the first electronic device 702 a first data packet 712 including data of respective identification watermarks associated with each of the plurality of evaluators 208 whose presence the first electronic the device 702 may be configured to sequentially determine in each in-use audio clip played in its vicinity 706, for example, in a given in-use audio clip 720, as will be described below.

[00164] Thus, by playing a given audio clip 720, the second electronic device 710 can be configured to generate, in the vicinity of 706 the first electronic device 702, an in-use audio signal 708. In this regard, to determine whether a given audio clip 720 has been personalized for a given evaluator 212 , in some non-limiting embodiments of the present invention, the first electronic device 702 may be configured to: (1) capture an in-use audio signal 708, such as through a built-in microphone (not shown); (2) to analyze, based on the data from the first data packet 712, the audio signal 708 in use to determine the presence of a corresponding identification watermark associated with a given estimator 212; and (3) in response to determining the presence of the respective identification watermark, determine the relationship between the given audio clip 720 and the given estimator 212.

[00165] In accordance with some non-limiting embodiments of the present invention, in order to analyze the audio signal 708 in use, first of all, the first electronic device 702 can be configured to generate its time-frequency representation. On FIG. 8 is a schematic diagram of a process for generating a time-frequency representation 804 of an in-use audio signal 708 by a first electronic device 702 in accordance with some non-limiting embodiments of the present invention.

[00166] In some non-limiting embodiments of the present invention, the first electronic device 702 may be configured to generate an in-use time-frequency representation 804 in a manner similar to how the server 202 is configured to generate a time-frequency representation 404 of the initial audio signal associated with audio clip 216 as described above with reference to FIG. 4. More specifically, the first electronic device 702 may be configured to (1) generate an in-use amplitude-time representation 802 of an in-use audio signal 708; and (2) applying a Fourier transform to the in-use time-amplitude representation 802, thereby generating a in-use time-frequency representation 804 of the in-use audio signal 708.

[00167] In some non-limiting embodiments of the present invention, the first electronic device 702 may be configured to apply to the in-use amplitude-time representation 802 the same Fourier transform configuration that the server 202 applied to the amplitude-time representation 402 to generate the time-frequency representation 404 of the initial audio signal associated with the audio clip 216. For example, in those embodiments where the server 202 has applied the Fourier transform to the amplitude-time representation 402 in the window stacking approach, as described above with reference to FIG. 4, the first electronic device 702 can also be configured to apply a Fourier transform to the time-amplitude representation 802 in use using a windowing approach. Furthermore, in these embodiments, the first electronic device 702 may be configured to apply a Fourier transform in a window stacking approach using the same size of the predefined time window 406 that is used by the server 202. However, a different size of the predefined time window 406 or even a different a Fourier transform configuration for use in generating the time-frequency representation 804 in use can also be provided without departing from the scope of the present invention.

[00168] In addition, using the in-use time-frequency representation 804, the first electronic device 702 can be configured to determine the presence of a respective identification watermark associated with a given estimator 212 in a given in-use audio clip 720. To this end, in some non-limiting embodiments of the present invention, the first electronic device 702 may be configured to determine the energy levels of the audio signal 708 in use at its frequency levels, which were used, for example, to indicate the bits of the binary sequence 304 associated with a given estimator 212, in addition audio clip 220.

[00169] In Fig. 9 is a schematic diagram of the step of determining by a first electronic device 702 the presence of a respective identification watermark associated with a given estimator 212 in a given audio clip 720 in use, in accordance with some non-limiting embodiments of the present invention.

[00170] More specifically, to determine the presence of a given bit of the binary sequence 304 in a given in-use audio signal 720, the first electronic device 702 may be configured to determine the respective energy levels of the in-use audio signal 708 at each of at least two of its frequency levels, used to indicate the value of a given bit in a respective identification watermark associated with a given estimator 212. In other words, the first electronic device 702 may be configured to determine whether the corresponding energy levels of the in-use audio signal 708 on each of at least two its theme frequency levels, which are used by server 202 to indicate the value of a given bit of binary sequence 304 when personalizing audio clips for a given estimator 212, such as augmented audio clip 220 as described above.

[00171] In some non-limiting embodiments of the present invention, the first electronic device 702 may be configured to determine whether a given bit value has been indicated in a given in-use audio clip 720 by comparing the energy levels of the in-use audio signal 708 on a given one of at least two frequency levels and an adjacent frequency level.

, с первым из первого набора частотных уровней 408, f ₁ . Кроме того, первое электронное устройство 702 может быть выполнено с возможностью определения первого разностного значения 907 (например, его абсолютного значения) между первичным уровнем 902 энергии и первым вторичным уровнем 903 энергии, связанным с первым одним из первого набора частотных уровней.[00172] Thus, the first electronic device 702 may be configured to determine the first primary energy level 902 of the in-use audio signal 708 at the first of the first set of frequency levels 408 , f ₁ , used to carry the value of the first bit of the binary sequence 304 in the augmented audio clip 220. In addition, the first electronic device 702 may be configured to determine the first secondary energy level 903 of the in-use audio signal 708 at the first adjacent frequency level 904,

, with the first of the first set of frequency levels 408, f ₁ . In addition, the first electronic device 702 may be configured to determine the first difference value 907 (eg, its absolute value) between the primary energy level 902 and the first secondary energy level 903 associated with the first one of the first set of frequency levels.

[00173] It should be noted that it is not limited to how the first electronic device 702 is configured to determine the first adjacent frequency layer 904; and in some non-limiting embodiments of the present invention, the first electronic device 702 may be configured to determine the first adjacent frequency level 904 based on a predetermined frequency step from the first one of the first set of frequency levels 408, which may be, for example, 0.1 Hz, 1 Hz, 10 Hz, etc.

[00174] In addition, according to some non-limiting embodiments of the present invention, the first electronic device 702 may be configured to determine the first combined difference value by combining the respective difference values associated with each of the first set of frequency levels 408. Thus, on based on the first combined difference value, as will be described below, the first electronic device 702 may be configured to determine the corresponding value of the first bit of the in-use binary sequence 908. Accordingly, if at least a portion of the in-use binary sequence 908 corresponds to the binary sequence 304, representing at least one identification indicator of a given evaluator 212, in some non-limiting embodiments of the present invention, the first electronic device 702 can be configured to determine the presence of a corresponding identification watermark in a given audio clip 720 in use; or in other words, that a given in-use audio clip 720 has been personalized for a given rater 212.

. Соответственно, на втором смежном частотном уровне 906 первое электронное устройство 702 может быть выполнено с возможностью определения второго вторичного уровня 905 энергии и, дополнительно, второго разностного значения 909 между ними и первого первичного уровня 902 энергии, который первое электронное устройство 702 может использоваться для определения первого объединенного разностного значения.[00175] It should be noted that in some non-limiting embodiments of the present invention, to determine the combined difference value, instead of using the respective adjacent frequency levels that are higher than each of the first set of frequency levels 408, for example, the first adjacent frequency level 904, the first electronic device 702 may be configured to use corresponding lower adjacent frequency levels. For example, the first electronic device 702 may be configured to determine, based on a predetermined frequency step, a second adjacent frequency layer 906,

. Accordingly, at the second adjacent frequency level 906, the first electronic device 702 may be configured to determine the second secondary energy level 905 and, additionally, the second difference 909 between them and the first primary energy level 902, which the first electronic device 702 may be used to determine the first combined difference value.

[00176] In addition, in some non-limiting embodiments of the present invention, to determine the first combined delta value associated with the first bit of the binary sequence 908 in use, the first electronic device 702 may be configured to select one of the respective delta values associated with the lower adjacent frequency level and the higher adjacent frequency level of each of the first set of frequency levels 408. For example, in some non-limiting embodiments of the present invention, the first electronic device 702 may be configured to select the minimum one of the respective difference values associated with the lower adjacent frequency layer and the higher adjacent frequency layer. For example, if the first electronic device 702 has determined that the absolute value of the first difference value 907 is lower than the absolute value of the second difference value 909, the first electronic device 702 may be configured to select the first difference value 907 to generate a first combined difference value associated with the first bit of the binary sequence 908 in use.

[00177] However, it should be noted that in other non-limiting embodiments of the present invention, the first electronic device 702 may be configured to select a maximum one of the respective delta values associated with each of the first set of frequency levels 408 to generate—such as a second delta the value 909 in the example above.

[00178] In addition, according to some non-limiting embodiments of the present invention, in order to generate a first combined difference value associated with the first bit, the first electronic device 702 may be configured to sum the absolute values of the respective difference values associated with each of the first set frequency levels 408 defined as described above. However, in other non-limiting embodiments of the present invention, the first electronic device 702 may be configured to algebraically sum the respective delta values, that is, taking into account the respective signs of each of the respective delta values.

[00179] In addition, the first electronic device 702 may be configured to determine the corresponding value of the first bit of the binary sequence 908 in use by comparing the first combined difference value with a predetermined threshold value. For example, in response to the first combined difference value being greater than a predetermined threshold value, the first electronic device 702 may be configured to determine the corresponding value of the first bit of the binary sequence 908 in use as positive, ie having a value of "1". Accordingly, in response to the fact that the first combined difference value is equal to or below a predetermined threshold value, the first electronic device 702 may be configured to determine the corresponding value of the first bit as negative, which has a value of '0'.

[00180] However, in specific non-limiting embodiments of the present invention, the first electronic device 702 may be configured to take a different approach to determining the first combined difference value. For example, the first electronic device 702 may be configured to determine a first combined sum of those respective differences associated with the frequency levels of the first set of frequency levels 408 at which the audio signal 708 in use has the respective primary energy levels (such as the first primary level 902 energy) indicating that the corresponding value of the first bit of the binary sequence 908 in use is "1". In addition, the first electronic device 702 may be configured to determine a second combined sum of those respective difference values associated with the frequency levels of the first set of frequency levels 408 at which the in-use audio signal 708 has respective energy levels indicating that the respective value of the first bit in use of the binary sequence 908 is equal to "0".

[00181] In addition, according to some non-limiting embodiments of the present invention, the first electronic device 702 may be configured to determine the first combined difference value associated with the first bit as the difference between the first combined sum and the second combined sum. In these embodiments, the first electronic device 702 may be configured to determine the corresponding value of the first bit by determining whether the first combined difference value satisfies a predetermined condition. For example, the first electronic device 702 may be configured to determine the corresponding value of the first bit as "1" if the first combined difference value is positive, ie, greater than "0". On the contrary, if the first combined difference value determined based on the first combined sum and the second combined sum as described above is equal to or less than '0', that is, not positive, the first electronic device 702 can thus be configured to determine the corresponding the value of the first bit of the binary sequence 908 in use as "0".

[00182] In further non-limiting embodiments of the present invention, in order to determine the respective value of the first bit of the in-use binary sequence 908, the first electronic device 702 may be configured to determine an appropriate confidence level for each primary energy level of the in-use audio signal 708 on each of the first set of frequency levels 408. The given confidence level indicates whether the respective primary energy levels of the in-use audio signal 708 on the respective set of frequency levels carry the respective value of the given bit of the binary sequence 304 or not. In other words, the given frequency level indicates the probability value of the respective energy levels of the audio signal 708 in use, which have been modified to indicate, on the respective set of frequency levels, the respective value of the given bit of the binary sequence 304.

[00183] For example, in some non-limiting embodiments of the present invention, the first electronic device 702 may be configured to determine an appropriate level of confidence for a given primary energy level of the in-use audio signal 708 in accordance with the following equation:

(1)

(1)

- это заданный первичный уровень энергии, определенный на соответственном одном из соответственного набора частотных уровней, связанных с заданным битом находящейся в использовании двоичной последовательности 908, например, первый первичный уровень 902 энергии, связанный с первым битом находящейся в использовании двоичной последовательности 908;Where

is a given primary energy level defined at a respective one of a respective set of frequency levels associated with a given bit of the in-use binary sequence 908, eg, the first primary energy level 902 associated with the first bit of the in-use binary sequence 908;

- это первый соответственный вторичный уровень энергии, определенный на более высоком смежном частотном уровне по отношению к соответственному одному из соответственного набора частотных уровней, например, первый вторичный уровень 903 энергии; и

is the first corresponding secondary energy level defined at a higher adjacent frequency level with respect to the corresponding one of the corresponding set of frequency levels, for example, the first secondary energy level 903; And

- это второй соответственный вторичный уровень энергии, определенный на более низком смежном частотном уровне по отношению к соответственному одному из соответственного набора частотных уровней, например, второй вторичный уровень 905 энергии.

is the second respective secondary energy level defined at a lower adjacent frequency level with respect to the respective one of the respective set of frequency levels, for example, the second secondary energy level 905.

[00184] Thus, the first electronic device 702 may be configured to determine the appropriate levels of confidence for each primary energy level of the in-use audio signal 708 at each of the first set of frequency levels 408. In addition, the first electronic device 702 may be configured to combining the respective confidence levels to determine a first combined confidence level associated with the first bit of the binary sequence 908 in use. For example, in some non-limiting embodiments of the present invention, the first electronic device 702 may be configured to determine a first combined confidence level similar to the first the value of the combined difference, as described above. More specifically, the first electronic device 702 may be configured to determine a first combined confidence level by summing the respective confidence levels associated with the frequency levels of the first set of frequency levels 408 at which the in-use audio signal 708 has respective primary energy levels indicating that the respective the value of the first bit of the binary sequence 908 in use is "1"; and subtracting those respective confidence levels associated with the respective primary energy levels of the in-use audio signal, indicating that the respective value of the first bit of the in-use binary sequence 908 is "0".

[00185] In addition, the first electronic device 702 may be configured to determine the corresponding value of the first bit of the binary sequence 908 in use as "1" if the first combined confidence level has a positive value; otherwise defining the corresponding value as "0".

[00186] Thus, by analyzing other energy levels of the in-use audio signal 708 at its frequency levels corresponding to other respective sets of frequency levels used to indicate the values of other bits of the binary sequence 304 in the augmented audio signal 220, using the time-frequency representation in use 804, the first electronic device 702 may be configured to determine the corresponding values of other bits of the binary sequence 908 in use. In addition, the first electronic device 702 may be configured to determine whether the binary sequence 908 in use corresponds to the binary sequence 304 associated with the given estimator 212.

[00187] For example, in some non-limiting embodiments of the present invention, the first electronic device 702 may be configured to determine that an in-use binary sequence 908 corresponds to a binary sequence 304 if a predetermined threshold number of bits (e.g., ten, in as an example) of the former has the same meanings as the corresponding bits of the latter. It is not limited how the predetermined threshold number of bits is identified in the binary sequence 908 in use; and in some non-limiting embodiments of the present invention, each of the predetermined threshold number of bits may have a corresponding predetermined ordinal position in the binary sequence 908 in use—eg, first, fourth, seventh, and the like. In other non-limiting embodiments of the present invention, the predetermined threshold number of bits may be a predetermined threshold number of consecutive bits, such as the first consecutive bits, within the binary sequence 908 in use.

[00188] Thus, returning to FIG. 7, in some non-limiting embodiments of the present invention, in response to determining that binary sequence 908 in use corresponds to binary sequence 304, first electronic device 702 may be configured to determine the presence of a corresponding identification watermark associated with a given estimator. 212 in a given in-use audio clip 720 playing near 706 thereof, which may mean that this in-use audio clip 720 has been personalized for a given evaluator 212 in a manner similar to augmented audio clip 220 as described above.

[00189] It should be clearly understood that the present invention is not limited to performing the above approach to detecting the corresponding identification watermark in a given audio clip 720 in use on the first electronic device 702; and in some non-limiting embodiments of the present invention, the server 202 may be configured to search the communication network 210 for audio clips that can be considered as confidential information; and apply to such audio clips , mutatis mutandis, the aforementioned approach to determine the presence of identification watermarks associated with one or more of the plurality of evaluators 208. For example, in some non-limiting embodiments of the present invention, the server 202 may be configured to search in public web resources, such as social networks, forums, and others, providing their users with the opportunity to publicly exchange media content, suspicious audio clips and further analyze such audio clips, as described above. In these embodiments, the server 202 may be configured to identify suspicious audio clips based on, without limitation, at least one of: (1) its duration, such as equal to or less than a predetermined duration, such as 20 seconds; (2) its title - for example, if the title includes specific predefined keywords such as "wake up word"; and (3) the degree to which it belongs to one or more of the plurality of raters 208—for example, if the given audio clip was posted to a social network through a personal user account associated with one or more of the plurality of raters 208, for example.

[00190] In addition, after determining the presence of a respective identification watermark in a given in-use audio clip 720, the first electronic device 702 may be configured to generate a second data packet 714 including a warning notification of recognizing a personalized audio clip in its vicinity 706, i.e. this audio clip in use 720; and transmitting the second data packet 714 to the server 202, which may have generated the present audio clip 720 in use. Therefore, in some non-limiting embodiments of the present invention, after receiving the second data packet 714 from the first electronic device 702, the server 202 may be configured to take specific preventive action against the predetermined rater 212 to prevent further distribution of personalized audio clips associated with the predetermined rater 212.

[00191] For example, in some non-limiting embodiments of the present invention, server 202 may be further configured to restrict a given rater 212's access to its respective account using a crowdsourcing application running on server 202. Server 202 may be configured to restrict access to a given evaluator 212 for a predetermined period, such as several hours, days, or weeks, or, for example, while a public access trigger instance of a given in-use audio clip 720 is being examined. In addition, in other non-limiting embodiments of the present invention, for repeated cases of making records included in digital tasks submitted to a given evaluator 212 public, the server 202 may be configured to lock the corresponding user account of the given evaluator 212 indefinitely.

Second way

[00192] Given the architecture and examples above, it is possible to perform a method for determining a relationship between a given audio clip and a scoring person, such as between a given in-use audio clip 720 and a given estimator 212. FIG. 10 is a flow diagram of a second method 1000 according to non-limiting embodiments of the present invention. The second method 1000 may be performed by the first electronic device 702.

STEP 1002: ELECTRONIC DEVICE CAPTURE A IN-USE AUDIO SIGNAL GENERATED NEAR THE ELECTRONIC DEVICE IN RESPONSIBILITY TO PLAYBACK THE PREDEMINED AUDIO REVIEW

[00193] The second method 1000 begins at step 1002, wherein the first electronic device 702 is configured to receive an in-use signal 708 of a predetermined in-use audio clip 720 being played near 706 of the first electronic device 702. For example, as described above with reference to FIG. . 7, a given in-use audio clip 720 may be played by a second electronic device 710 currently positioned such that the in-use audio signal 708 reaches proximity 706 of the first electronic device 702.

[00194] For example, in some non-limiting embodiments of the present invention, the second electronic device 710 may be the corresponding electronic device of the specified evaluator 212, designed to perform digital tasks received from the server 202. To this end, the first electronic device 702 may, for example, be private electronic device of a given estimator 212. Thus, in these embodiments, prior to determining the presence of a corresponding identification watermark associated with a given estimator, the first electronic device 702 may be configured to receive from the server 202 a first data packet 712 including data only the respective identification watermark associated with the given estimator 212 as described above.

[00195] However, in other non-limiting embodiments of the present invention, where the first electronic device 702 and the second electronic device 710 are not associated with a given estimator 212, the first data packet 712 may include all corresponding identification watermark data associated with each of a plurality of estimators 208, the presence of which the first electronic device 702 can be sequentially determined to have, as will be described below with respect to the identification watermark associated with a given estimator 212.

[00196] Thus, the second method 1000 proceeds to block 1004.

Stage 1004: the determination by the electronic device for the presence of an identification watermark associated with an assessing person in the use of the audio signal, while the identification watermark is generated on the basis of the identification pointer of the evaluating person, and the identification pointer is represented by a unique sequence of bits; THE RESPECTIVE VALUE OF A TARGET BIT FROM A UNIQUE SEQUENCE OF BITS IN A DESIGNATED AUDIO REVIEW HAS BEEN INDICATED BY VARIATION OF THE RESPECTIVE ENERGY LEVELS OF THE ORIGINAL AUDIO SIGNAL ASSOCIATED WITH THEM BY AT LEAST TWO DIFFERENT FREQUENCY LEVELS

[00197] At step 1004, having captured the audio signal 708 in use, the first electronic device 702 can be configured to analyze it to determine the presence of a corresponding identification watermark of at least one of the plurality of estimators 208, such as a given estimator 212.

[00198] To this end, first of all, in some non-limiting embodiments of the present technology, the first electronic device 702 may be configured to generate an in-use time-frequency representation 804 of an in-use audio signal 708, for example, by applying a Fourier transform, as described above. In addition, the first electronic device 702 may be configured to determine, using the time-frequency representation 804 in use, the respective energy levels in each set of predefined frequency levels used in the first encoding method 600 of the binary sequence 304 associated with a given estimator. 212 in audio clip 216. Also, as described above with reference to FIG. 8 and 9, based on the energy levels of the in-use audio signal 708 thus determined, the first electronic device 702 can be configured to generate an in-use binary sequence 908 and further determine if the in-use binary sequence corresponds to the binary sequence 304 associated with assigned appraiser 212.

[00199] More specifically, the first electronic device 702 may be configured to determine the respective value of the first bit of the binary sequence 908 in use by determining the first primary energy value 902 and the second primary energy level 910 respectively associated with each of the first set of frequency levels 408 used to indicate the first bit of the binary sequence 304 in the augmented audio clip 220. In other words, the first electronic device 702 may be configured to determine whether an in-use audio signal 708 has been changed to have corresponding predetermined energy levels at each of the first set of frequency levels 408 to indicate therein the value of the first bit of the binary sequence 304 associated with the given estimator 212.

[00200] In addition, as described above with reference to FIG. 9, the first electronic device 702 may be configured to determine respective secondary energy levels of the in-use audio signal 708 at frequency levels adjacent to each of the first set of frequency levels 408, such as the first secondary energy level 903 and the second secondary energy level 905, respectively. associated with the first adjacent frequency level 904 and the second adjacent frequency level 906 of the first of the first set of frequency levels 408.

[00201] In addition, in order to determine the respective value of the first bit of the in-use binary sequence 908, the first electronic device 702 may be configured to determine the respective difference values for each primary energy level of the in-use audio signal 708 at each of the first set of frequency levels 408 - such as the first difference 907 and the second difference 909 associated with the first primary energy level 902 as described above. In addition, the first electronic device 702 may be configured to determine the first combined difference value associated with the first bit of the binary sequence 908 in use. Finally, if the first combined difference value meets a predetermined condition (for example, if the first combined difference value is positive , as an example), the first electronic device 702 may be configured to determine the corresponding value of the first bit as "1", otherwise determine that the first bit has a value of "0".

[00202] In other non-limiting embodiments of the present invention, as further described above with reference to FIG. 9, in order to determine the respective value of the first bit of the in-use binary sequence 908, the first electronic device 702 may be configured to determine a first combined confidence level associated with the respective primary energy levels of the in-use audio signal 708 at each of the first set of frequency levels 408. C to this end, the first electronic device 702 may be configured to determine respective confidence levels for each of the first primary energy level 902 and the second energy level 910 in accordance with equation (1) as described above.

[00203] Thus, by iteratively applying step 1004 to the in-use audio signal 708 based on the data from the first data packet 712, the first electronic device 702 can be configured to determine other bits of the in-use binary sequence 908.

[00204] Thus, the second method 1000 proceeds to block 1006.

Stage 1006: In response to the compliance of the bits that is in the use of the bits sequence associated with the evaluating person, the determination of the presence of the identification water sign in the use of the audio signal, thereby determining that the specified audiolum was personalized for the evaluating person to transmit him for the execution of one or MORE DIGITAL TASKS BASED ON THE ASSESSMENT OF A TARGET AUDIO REVIEW

[00205] At 1006, in accordance with some non-limiting embodiments of the present invention, the first electronic device 702 may be configured to determine whether an in-use binary sequence 908 matches a binary sequence 304 associated with a given estimator 212. Accordingly, by determining the correspondence between the in-use binary sequence 908 and the binary sequence 304, the first electronic device 702 can be configured to determine the presence of a corresponding identification watermark associated with a given estimator 212 in a given in-use audio clip 720.

[00206] For example, as described above, the first electronic device 702 may be configured to determine that an in-use binary sequence 908 corresponds to a binary sequence 304 if a predetermined threshold number of bits (such as ten, for example) of the first has the same values as the corresponding bits of the latter.

[00207] In addition, after determining the presence of a corresponding identification watermark in a given audio clip 720 in use, the first electronic device 702 may be configured to generate a second data packet 714 including a personalized audio recognizing alert notification in its vicinity 706, then there is a predetermined audio clip 720 in use; and transmitting the second data packet 714 to the server 202. In this regard, in some non-limiting embodiments of the present invention, after receiving the second data packet 714 from the first electronic device 702, the server 202 may be configured to take specific preventive actions against a given evaluator 212 to prevent further distribution of personalized audio clips associated with the given estimator 212, as described above.

[00208] Thus, some non-limiting embodiments of the second method 1000 allow the detection of pre-generated identification watermarks in an audio clip played near electronic devices, which may further allow tracking sources of confidential information leakage and prevent damage to associated ownership rights.

[00209] It should be noted that in some non-limiting embodiments of the present invention, the second method 1000 may be performed by the server 202, configured to search for suspicious audio clips in the communication network 210, as described above.

[00210] Thus, the second method 1000 ends.

[00211] It should be clearly understood that not all of the technical effects mentioned herein need to be implemented in every embodiment of the present invention.

[00212] Changes and improvements in the above embodiments of the present invention may become apparent to those skilled in the art. The preceding description is intended to be exemplary and not limiting. Therefore, it is intended that the scope of the present invention be defined only by the scope of the appended claims.

Claims (62)

1. A computer-implemented method for adding an audio clip to be provided to an evaluating person for performing one or more digital tasks, wherein the add-on is intended to modify the audio clip to include data suitable for determining the identification information of the evaluating person to determine the relationship between the audio clip and the evaluating person, and the method is executed by the production server and contains the steps in which: receiving, by means of the production server, an audio clip which audio clip has been previously recorded; receiving by the production server an identification indicator of the evaluator to whom the audio clip is to be transmitted, the identification indicator being represented by a unique sequence of bits; generating by the production server, based on the unique bit sequence, an identification watermark associated with the scoring person to be included in the audio clip to generate the augmented audio clip, the generation including the steps of: determining by the production server for a given bit from a unique sequence of bits at least two different frequency levels from a predetermined audio spectrum to carry the value of the given bit in the audio signal associated with the augmented audio clip, wherein the first of at least two different frequency levels is intended to indicate the value of a given bit; others of at least two different frequency levels are designed to duplicate the values indicated by the first of the at least two frequencies; And the value of the set bit is indicated by a predetermined energy level of the audio signal; modifying, by means of the production server, the audio signal to have a predetermined energy level at each of at least two different frequency levels to indicate the presence of a predetermined bit from a unique bit sequence associated with the scoring person in the augmented audio clip; And transmitting the augmented audio clip including the identification watermark to an electronic device associated with the scoring person to perform one or more digital tasks based on the evaluation of the augmented audio clip. 2. The method of claim. 1, in which the value of the given bit is a binary value, and "0" is represented by the zero energy level of the audio signal associated with the augmented audio clip, at each of at least two different frequency levels; and said change comprises excluding a corresponding portion of the audio signal at each of at least two different frequency levels. 3. The method of claim 2, wherein said exclusion of the respective portion from the audio signal generates a silent gap when the augmented audio signal is reproduced, the silent gap being substantially unrecognizable to the human ear. 4. The method of claim 2, wherein said elimination comprises applying an appropriate notch filter to the audio signal. 5. The method of claim 1, wherein the predetermined audio spectrum comprises an audio spectrum recognizable by the human ear. 6. The method of claim 1, wherein each of the at least two different frequency levels is selected within a respective range of a predetermined audio spectrum. 7. The method of claim 1, wherein each of the at least two different frequency levels has been randomly selected. 8. The method of claim 1, wherein each of the at least two different frequency levels has been randomly preselected. 9. The method of claim. 1, in which each of the at least two different frequency levels was selected with a predetermined step. 10. The method of claim 1, wherein modifying the audio signal comprises first converting the audio signal to its time-frequency representation. 11. The method of claim 10, wherein said transform comprises applying a Fourier transform to the audio signal. 12. A computer-implemented method for determining the relationship between an evaluating person and a given audio clip, the method being performed by an electronic device and comprising the steps of: capturing, by means of the electronic device, an in-use audio signal generated in the vicinity of the electronic device in response to playing a predetermined audio clip; determine by means of an electronic device the presence of an identification watermark associated with the evaluating person in the audio signal in use, wherein the identification watermark has been generated based on the identification index of the scoring person, the identification index being represented by a unique bit sequence; the respective value of a given bit from a unique sequence of bits was indicated in a given audio clip by varying the respective energy levels of the original audio signal associated therewith at two different frequency levels; determine the respective value of the given bit, which definition includes the steps in which: determining by means of an electronic device a respective primary energy level of the audio signal in use at each of at least two different frequency levels; determining by means of an electronic device a respective secondary energy level of the audio signal in use at a respective adjacent frequency level for each of the at least two different frequency levels; determining by means of an electronic device, for each of at least two different frequency levels, a respective difference between a respective primary energy level and a respective secondary energy level of the audio signal in use; electronically combining respective differences associated with at least two different frequency levels to determine a combined difference associated with a given bit; determining, based on the combined difference value, a corresponding value of a given bit for inclusion in an in-use bit sequence associated with an in-use audio signal; And in response to matching the bit sequence in use with the unique bit sequence associated with the evaluator, the presence of an identification watermark of the audio signal in use is determined, thereby determining that the given audio clip has been personalized for the evaluator to be transferred to him to perform one or more digital tasks based on the rating of the given audio clip. 13. The method of claim. 12, in which the corresponding value of the given bit is a binary value and the said union of the respective difference values comprises the steps of: determining the first combined value as the sum of the respective difference values associated with the values of at least two different frequency levels, at which the respective primary energy levels indicate that the respective value of the given bit is "1"; determining the second combined value as the sum of the respective difference values associated with the values of at least two different frequency levels, at which the respective primary energy levels indicate that the respective value of the given bit is "0"; determining the combined difference value as the difference between the first combined value and the second combined value; and wherein said determination of the respective value of a given bit based on the combined difference value comprises the steps of: determining the corresponding value as "1" if the combined difference value is a positive value; And determining the corresponding value as "0" if the combined difference value is a non-positive value. 14. The method of claim 12, further comprising, for a given frequency level of at least two different frequency levels, where the given frequency level is associated with a respective primary energy level of the audio signal in use at the given frequency level: determining a first respective secondary energy level at a first respective adjacent frequency level higher than the predetermined frequency level; determining a second corresponding secondary energy level at a second adjacent frequency level lower than the predetermined frequency level; determining a first respective difference value between a respective primary energy level and a first respective secondary energy level; determining a second respective difference between the respective primary energy level and the second respective secondary energy level, and wherein: said determination of the respective difference value comprises the step of determining the minimum of the first respective difference value and the second respective difference value. 15. The method of claim 12, wherein the electronic device is an electronic device associated with the evaluator. 16. The method of claim 12, wherein the method is performed by a server configured to receive a predetermined audio clip, and wherein an in-use audio signal is generated by the server by processing the predetermined audio clip. 17. The method of claim 16, wherein the server is configured to obtain a given audio clip by searching for at least one network resource for it. 18. The method of claim 12, wherein said determining the presence of the identification watermark in the audio signal in use comprises first converting the audio signal in use into its time-frequency representation. 19. The method of claim 12, wherein said determining the predetermined audio clip as personalized to the scoring person further includes generating, by means of an electronic device, a predetermined notification for transmission to an entity associated with the production of the predetermined audio clip. 20. A system for augmenting an audio clip provided to an evaluator to perform one or more digital tasks, wherein the add-on is for modifying the audio clip to include data suitable for identifying the evaluator's identification information to determine the relationship between the audio clip and the evaluator, the system including: a production server, including: CPU; a durable computer-readable medium containing instructions; moreover, the processor, when executing instructions, is adapted: receive an audio clip, while the audio clip was pre-recorded; receive an identification indicator of the scoring person to whom the audio clip is to be transmitted, wherein the identification indicator is represented by a unique sequence of bits; generate, based on the unique bit sequence, an identification watermark associated with the scoring person to be included in the audio clip to generate the augmented audio clip, by: determining for a given bit from a unique sequence of bits of at least two different frequency levels from a predetermined audio spectrum to carry the value of a given bit in an audio signal associated with an augmented audio clip, the first of at least two different frequency levels is for indicating the value of a given bit; others of at least two different frequency levels are designed to duplicate the values indicated by the first of at least two frequencies; And the value of the set bit is indicated by a predetermined energy level of the audio signal; modify the audio signal to have a predetermined energy level at each of at least two different frequency levels to indicate the presence of a predetermined bit from the unique bit sequence associated with the rater in the augmented audio clip; And transmit the augmented audio clip including the identification watermark to an electronic device associated with the evaluator to perform one or more digital tasks based on the evaluation of the augmented audio clip.

Images