WO2024059796A1 - Systèmes et procédés de filtration et de classification de segments de signature de données de signal - Google Patents

Systèmes et procédés de filtration et de classification de segments de signature de données de signal Download PDF

Info

Publication number
WO2024059796A1
WO2024059796A1 PCT/US2023/074308 US2023074308W WO2024059796A1 WO 2024059796 A1 WO2024059796 A1 WO 2024059796A1 US 2023074308 W US2023074308 W US 2023074308W WO 2024059796 A1 WO2024059796 A1 WO 2024059796A1
Authority
WO
WIPO (PCT)
Prior art keywords
sds
audio file
audio
signal data
classification
Prior art date
Application number
PCT/US2023/074308
Other languages
English (en)
Inventor
Nolan DONALDSON
Mark Fogarty
Kristan S. HOPKINS
Simon KOTCHOU
Robert F. SCORDIA
Adam STOGSDILL
Original Assignee
Covid Cough, Inc.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Covid Cough, Inc. filed Critical Covid Cough, Inc.
Publication of WO2024059796A1 publication Critical patent/WO2024059796A1/fr

Links

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • G10L25/66—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for extracting parameters related to health condition
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/90—Pitch determination of speech signals
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
    • G10L25/30—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique using neural networks

Definitions

  • the present disclosure generally relates to Signal Data Signature (SDS) classification, and more particularly, audio segmentation and feature extraction for Signal Data Signature classification.
  • SDS Signal Data Signature
  • AI/ML artificial intelligence and machine learning
  • SDS detection detection, segmentation, characterization, and classification is utilized for recognizing a source signal data signature and its accompanying parameters within a source signal data stream or recording (or other form of input).
  • the disclosed systems and methods provide a computerized framework that addresses these shortcomings, among others, by providing a novel SDS classification framework and filtering methodology.
  • the disclosed SDS framework can utilize AI/ML based technology 7 to perform audio segmentation and feature extraction pursuant to determining a SDS classification.
  • the disclosed systems and methods provide generalizable feature extraction techniques that can be applied to SDS segments in order to perform classification of the SDS and/or the SDS parameters.
  • the disclosed feature extraction and filtering enables an improved quality of SDS segment classification.
  • the present disclosure provides computerized methods for a novel framework for audio segmentation and feature extraction for signal data signal classification.
  • the present disclosure provides a non-transitory computer-readable storage medium for cartying out the above-mentioned technical steps of the framework’s functionality.
  • the non-transitory computer-readable storage medium has tangibly stored thereon, or tangibly encoded thereon, computer readable instructions that when executed by a device cause at least one processor to perform a method for a novel and improved framework for audio segmentation and feature extraction for signal data signal classification.
  • a system comprising one or more computing devices configured to provide functionality in accordance with such embodiments.
  • functionality is embodied in steps of a method performed by at least one computing device.
  • program code (or program logic) executed by a processor(s) of a computing device to implement functionality in accordance with one or more such embodiments is embodied in, by and/or on a non-transitory computer-readable medium.
  • FIG. 1 illustrates a signal data signature detection system in accordance with some embodiments of the present disclosure
  • FIG. 2 illustrates a non-limiting example SDS processing according to some embodiments of the present disclosure
  • FIG. 3A depicts a non-limiting example work flow of the disclosed systems and methods according to some embodiments of the present disclosure
  • FIG. 3B illustrates a non-limiting example embodiment of audio input and processing capabilities discussed herein according to some embodiments of the present disclosure
  • FIG. 4 depicts a block diagram of an exemplary computer-based system and platform 700 in accordance with some embodiments of the present disclosure
  • FIG. 5 depicts a block diagram of another exemplary' computer-based system and platform 800 in accordance with some embodiments of the present disclosure
  • FIG. 6 illustrates schematics of an exemplary implementation of the cloud computing/architecture(s) in accordance with some embodiments of the present disclosure.
  • FIG. 7 illustrates schematics of another exemplary' implementation of the cloud computing/architecture(s) in accordance with some embodiments of the present disclosure.
  • terms, such as “a,” “an,” or “the,” again, may be understood to convey a singular usage or to convey a plural usage, depending at least in part upon context.
  • the term “based on” may be understood as not necessarily intended to convey an exclusive set of factors and may, instead, allow for existence of additional factors not necessarily expressly described, again, depending at least in part on context.
  • a non-transitory computer readable medium stores computer data, which data can include computer program code (or computer-executable instructions) that is executable by a computer, in machine readable form.
  • a computer readable medium may comprise computer readable storage media, for tangible or fixed storage of data, or communication media for transient interpretation of code-containing signals.
  • Computer readable storage media refers to physical or tangible storage (as opposed to signals) and includes without limitation volatile and non-volatile, removable and non-removable media implemented in any method or technology for the tangible storage of information such as computer-readable instructions, data structures, program modules or other data.
  • Computer readable storage media includes, but is not limited to, RAM, ROM, EPROM, EEPROM, flash memory or other solid state memory technology, optical storage, cloud storage, magnetic storage devices, or any other physical or material medium which can be used to tangibly store the desired information or data or instructions and which can be accessed by a computer or processor.
  • server should be understood to refer to a service point which provides processing, database, and communication facilities.
  • server can refer to a single, physical processor with associated communications and data storage and database facilities, or it can refer to a networked or clustered complex of processors and associated network and storage devices, as well as operating software and one or more database systems and application software that support the services provided by the server. Cloud servers are examples.
  • a “network” should be understood to refer to a network that may couple devices so that communications may be exchanged, such as between a server and a client device or other types of devices, including between wireless devices coupled via a wireless network, for example.
  • a network may also include mass storage, such as network attached storage (NAS), a storage area network (SAN), a content delivery network (CDN) or other forms of computer or machine readable media, for example.
  • NAS network attached storage
  • SAN storage area network
  • CDN content delivery network
  • a network may include the Internet, one or more local area networks (LANs), one or more wide area networks (WANs), wire-line type connections, wireless type connections, cellular or any combination thereof.
  • wireless network should be understood to couple client devices with a network.
  • a wireless network may employ stand-alone ad-hoc networks, mesh networks, Wireless LAN (WLAN) networks, cellular networks, or the like.
  • WLAN Wireless LAN
  • a wireless network may further employ a pl ural i ty of network access technologies, including Wi-Fi, Long Term Evolution (LTE), WLAN, Wireless Router (WR) mesh, or 2nd, 3rd, 4 th or 5 th generation (2G, 3G, 4G or 5G) cellular technology, mobile edge computing (MEC), Bluetooth, 802.11b/g/n, or the like.
  • Network access technologies may enable wide area coverage for devices, such as client devices with vary ing degrees of mobility 7 , for example.
  • a wireless network may include virtually any ty pe of wireless communication mechanism by which signals may be communicated between devices, such as a client device or a computing device, between or within a network, or the like.
  • a computing (or client) device may be capable of sending or receiving signals, such as via a wired or wireless network, or may be capable of processing or storing signals, such as in memory as physical memory states, and may, therefore, operate as a server.
  • devices capable of operating as a server may include, as examples, dedicated rack-mounted servers, desktop computers, laptop computers, set top boxes, integrated devices combining various features, such as two or more features of the foregoing devices, or the like.
  • a client (or user) device may include a computing device capable of sending or receiving signals, such as via a wired or a wireless network.
  • a client device may, for example, include a desktop computer or a portable device, such as a cellular telephone, a smart phone, a display pager, a radio frequency (RF) device, an infrared (IR) device an Near Field Communication (NFC) device, a Personal Digital Assistant, a handheld computer, a tablet computer, a phablet, a laptop computer, a set top box, a wearable computer, smart watch, an integrated or distributed device combining various features, such as features of the forgoing devices, or the like.
  • RF radio frequency
  • IR infrared
  • NFC Near Field Communication
  • the anatomy of cough is commonly broken down into three distinct regions or phases.
  • the first phase is the burst, which is characterized by 7 an explosion of energy due to the physiological phenomena that comes from rapidly exhaling air.
  • the second phase is the lull/in termediate phase, which is characterized by a sharp drop-off in energy from the burst that is due to the closing of the glottis.
  • the third phase is the voiced phase of the cough, which is characterized by the manipulation of the vocal cords causing short bursts of air (e.g., glottal pulses) to emanate from the throat, creating an audible pitch.
  • FIG. 3B A non-limiting example of the three phases of a cough is depicted in FIG. 3B, where the first phase is depicted with reference to the “explosive phase,” the second phase is depicted with reference to the “intermediate phase” and the third phase is depicted with reference to the “voiced phase.”
  • SDS includes of a sample recording of a continuous acoustic signal from a forced cough vocalizations.
  • SDS classification has different commercial applications, such as, but not limited to, unobtrusive monitoring and diagnosing in health care and medical diagnostics.
  • a source SDS after a source SDS is acquired, it can be split into individual single cough segments. In some embodiments, this can be performed via any ty pe of known or to be know n audio segmentation analysis and/or digital signal processing.
  • the disclosed framework identifies different, qualifying phases (e.g., phases 1-3, respectively) within an input audio stream (e.g., a single cough) into different, qualifying segments (e.g., phases 1-3, respectively).
  • the disclosed framew ork operates to ensure that the qualify of each cough being analyzed via the disclosed systems and methods is of a particular value. That is, only “high value” coughs are to be utilized for training and/or inference via the AI/MLs (e.g., neural networks) classifying them.
  • AI/MLs e.g., neural networks
  • an audio filter processes is applied upon the cough being acquired (e.g., received as input).
  • a filter / classifier is implemented in order to measure whether audio or SDS contains all three phases of a cough.
  • the disclosed framework can operate to determine, gauge, ensure or otherwise identify whether the third phase is present (e.g., the voiced phase of the cough).
  • detection of the third phase can involve a determination as to whether the third phase includes a threshold satisfying pitch.
  • the disclosed systems and methods can implement a pitch detection algorithm (PDA).
  • PDA which can operate in the time domain and/or frequency domain, can be utilized to determine or identify the pitch or fundamental frequency of a quasiperiodic and/or oscillating signal from the cough (e.g., a digital recording of the cough and/or direct "speedv input of the cough).
  • the PDA can be any type of known or to be known PDA, such as, but not limited to, frequency-domain PDA algorithms, spectral/temporal PDA algorithms, speech detection algorithms, and the like, or some combination thereof.
  • the disclosed framework can determine whether the to send the cough for audio preparation and classification. For example, in some embodiments, if a SDS segment and associated cough sound has a certain threshold of pitch in its third phase, it is sent downstream for classification. Conversely, if a cough contains minimal to no pitch (e.g., a pitch outside a pitch threshold range (e.g., 75 - 600 Hz), it is filtered out, and not sent downstream for further preprocessing and ultimately the neural netw orks. In some embodiments, a minimum duration threshold can be applied, such that should an SDS segment be less than a predetermined amount of a cough or specific time period, it may also be filtered out (e.g., less than 5% of a cough).
  • a minimum duration threshold can be applied, such that should an SDS segment be less than a predetermined amount of a cough or specific time period, it may also be filtered out (e.g., less than 5% of a cough).
  • FIG. 1. illustrates a signal data signature detection system 100 with the following components: input 101 , hardware 102, software 109, and output 1 18.
  • the input 101 is a signal data signature recording such as a signal data signature recording captured by a sensor, a signal data signature recording captured on a mobile device, and a signal data signature recording captured on any other device, among others.
  • the input 101 may be provided by an individual, individuals or a system and recorded by a hardware device 102 such as a computer 103 wdth a memory 104, processor 105 and or network controller 106.
  • a hardw are device is able to access data sources 108 via internal storage or through the network controller 106, which connects to a network 107.
  • a user may record an input 101 including an audio recording of a vocalization, such as a cough vocalization, including forced and/or unforced cough vocalizations.
  • the input 101 may be recorded using a recording device.
  • the recording device may include one or more microphones and a software application configured to use the microphones for recording sounds.
  • the recording device may be a peripheral or connected device connected to a user computing device, and the user computing device may include a software application configured to receive or obtain a recording from the recording device.
  • the sound signal data signature may include a forced non-speech vocalization, such as, e.g., a cough.
  • a sound signature of forced non-speech vocalizations is unique to each individual.
  • the user computing device may instruct the user to force a cough vocalization as a way to authenticate a user’s identity.
  • the sound signal data signature may also be used to assess changes to the sound signature of the user’s sound signal data signature by, e.g., comparing the sound signal data signature to a baseline signature.
  • the sound signal data signature may be employed to assess any potential changes to the user’s sound signal data signature that may indicate a potential respiratory anomaly such as.
  • any agent, substance, vapor or condition that has an effect on the respiratory system such as, e.g., infections including influence, coronavirus (e.g., the common cold, COVID-19, and the like), pneumonia, bronchitis, or other diseases, conditions such as chronic obstructive pulmonary disease (COPD).
  • COPD chronic obstructive pulmonary disease
  • asthma allergies, emphysema, or other conditions, environmental factors such as humidity, air quality and pollution, foreign bodies, foreign substances, and the like, or any other respiratory effecting factor or any combination thereof.
  • a sound signal data signature analysis system 100 may be in communication with the recording device, e.g., via a network or direct connection.
  • hardware 102 and/or software 109 of the signal data signature detection system 100 may be configured to receive the input 101 and utilize a signal data signature classifier system 111 in order to identify sound signal data signatures that may represent a condition associated with the input 101.
  • the recording device may provide the sound signal data signature to the sound signal data signature detection system 100, e.g., via a sound signal data signature analysis interface.
  • the sound signal data signature analysis interface may include any suitable interface for data communication over, e.g., a network 107, or via local or direct data communication infrastructure.
  • the sound signal data signature analysis interface may include wired interfaces such as, e.g., a Universal Serial Bus (USB) interface, peripheral component interconnect express (PCIe), serial AT attachment (SATA), or any other wired interface, or wireless interfaces such as, e.g., BluetoothTM, Bluetooth Low Energy (BLE), NFC, RFID, Narrow Band Internet of Things (NBIOT), 3G. 4G, 5G. GSM, GPRS, WiFi, WiMax. CDMA, satellite, ZigBee, or other wireless interface, or any combination of any wired and/or wireless interfaces.
  • the recording device may communicate the sound signal data signature via the sound signal data signature analysis interface 114 using any suitable data communication protocol, such as. e.g., IPX/SPX, X.25, AX.25. AppleTalkTM, TCP/IP (e.g., HTTP), application programming interface (API), messaging protocol or any combination thereof.
  • the sound signal data signature analysis interface may include, e.g., an application programming interface.
  • “application programming interface'’ or “APT’ refers to a computing interface that defines interactions between multiple software intermediaries.
  • An “application programming interface” or “API” defines the kinds of calls or requests that can be made, how to make the calls, the data formats that should be used, the conventions to follow, among other requirements and constraints.
  • An “application programming interface” or “API” can be entirely custom, specific to a component, or designed based on an industry -standard to ensure interoperability to enable modular programming through information hiding, allowing users to use the interface independently of the implementation.
  • the sound signal data signature detection system 100 may receive the sound signal data signature of the input 101 and analyze the sound signal data signature to determine a sound signal data signature recording of the sound signal data signature isolated from noise and artifacts of in the recorded sound signal data signature, generate a signature for the sound signal data signature recording, and generate a label for the input classifying the sound signal data signature recording, e.g., via a signal data signature classifier system 111.
  • the sound signal data signature classifier system 1 11 may include hardware and software components including, e.g., the computer 103 (e.g., including a processor 105, a memory 104, a network controller 106, and the like), e.g., embodied in a user computing device, server, cloud, or a combination thereof.
  • the computer 103 e.g., including a processor 105, a memory 104, a network controller 106, and the like
  • a user computing device e.g., server, cloud, or a combination thereof.
  • the processor 105 may include local or remote processing components.
  • the processor 105 may include any type of data processing capacity, such as a hardware logic circuit, for example an application specific integrated circuit (ASIC) and a programmable logic, or such as a computing device, for example, a microcomputer or microcontroller that include a programmable microprocessor.
  • the processor 105 may include data-processing capacity provided by the microprocessor.
  • the microprocessor may include memory, processing, interface resources, controllers, and counters.
  • the microprocessor may also include one or more programs stored in memory 7 .
  • the memory 7 104 may include any suitable data storage solution, such as local hard-drive, solid-state drive, flash drive, database or other local storage, or remote storage such as a server, mainframe, database or cloud provided storage solution.
  • the data storage solution may include, e.g., a suitable memory or storage solutions for maintaining electronic data representing the activity histories for each account.
  • the data storage solution may include database technology such as, e.g., a centralized or distributed database, cloud storage platform, decentralized system, server or server system, among other storage systems.
  • the data storage solution may, additionally or alternatively, include one or more data storage devices such as, e.g., a hard drive, solid-state drive, flash drive, or other suitable storage device.
  • the data storage solution may, additionally or alternatively, include one or more temporary storage devices such as, e.g., a random-access memory, cache, buffer, or other suitable memory device, or any other data storage solution and combinations thereof.
  • the signal data signature detection system 110 can perform the splitting operations discussed below in reference to at least FIG. 3A.
  • system 110 can include an audio fdter, feature extractor and/or any other component, module, engine or technology (as illustrated and discussed in reference to FIG. 2) to perform the computational analysis regarding whether the required phases within a cough’s audio are present pursuant to classification of the cough.
  • signal detection system 110 includes a sound data signature recording system 110a, a signal data signature filter system 110b and a signal data signature preparation system 1 10c.
  • system sound data signature recording system 110 can include Hidden Markov Model (HMM) dual splitter for performing split detection of audio/acoustic signals.
  • the signal data signature filter system can include a phase filter.
  • the signal data signature preparation system 110c can be utilized to normalize and/or prepare the audio (output from systems HOa-b) for submission to a ML engine for training and/or evaluation and output.
  • system 110c can be implemented to perform decibel scaling and background noise cancellation.
  • signal data signature recording system 110a can be utilized to determine a sound signal data signature recording of the input 101 isolated from noise and artifacts.
  • signal data signature filter system 110b can be utilized to quantify and/or determine a qualify the of SDS.
  • signal data signature preparation system 110c can be utilized to condition and normalize the SDS.
  • system 110c may be optionally implemented. (Embodiments where system 110c are optionaly used and/or bypassed are depicted in FIG. 1 via the dashed lines between system 110b and system 111, and system 110c and system 111.
  • signal data signature classifier system 111 can be utilized to leverage machine learning models in a transfer learning system 112 to generate one or more labels classifying the input 101 according to trained ML model(s) 113, boundaries 114, a source model 116 and a compendium of signal data signature classifiers 121.
  • the terms “computer engine” and “engine” identify at least one software component and/or a combination of at least one software component and at least one hardware component which are designed/programmed/configured to manage/control other software and/or hardware components (such as the libraries, software development kits (SDKs), objects, and the like).
  • Examples of hardware elements may include processors, microprocessors, circuits, circuit elements (e g., transistors, resistors, capacitors, inductors, and so forth), integrated circuits, application specific integrated circuits (ASIC), programmable logic devices (PLD), digital signal processors (DSP), field programmable gate array (FPGA), logic gates, registers, semiconductor device, chips, microchips, chip sets, and so forth.
  • the one or more processors may be implemented as a Complex Instruction Set Computer (CISC) or Reduced Instruction Set Computer (RISC) processors; x86 instruction set compatible processors, multi- core, or any other microprocessor or central processing unit (CPU).
  • the one or more processors may be dual-core processor(s), dual-core mobile processor(s), and so forth.
  • Examples of software may include software components, programs, applications, computer programs, application programs, system programs, machine programs, operating system software, middleware, firmware, software modules, routines, subroutines, functions, methods, procedures, software interfaces, application program interfaces (API), instruction sets, computing code, computer code, code segments, computer code segments, words, values, symbols, or any combination thereof. Determining whether an embodiment is implemented using hardware elements and/or software elements may vary in accordance with any number of factors, such as desired computational rate, power levels, heat tolerances, processing cycle budget, input data rates, output data rates, memory resources, data bus speeds and other design or performance constraints.
  • the data sources 108 that are retrieved by the hardware device 102 in one of other possible embodiments includes for example but not limited to: 1) imbalanced paired training dataset of signal data signature recordings and labels and unlabeled signal data signature recording, 2) balanced paired training dataset of signal data signature recordings and labels and unlabeled signal data signature recording, 3) imbalanced paired training dataset of video recordings and labels and unlabeled video recording, 4) imbalanced paired training dataset of video recordings and labels and unlabeled signal data signature recording, 5) paired training dataset of signal data signature recordings and labels and unlabeled video recording.
  • the term “imbalance” refers to an unequal number of labeled training data compared to labeled training data. Similarity, the term “balance” refers to an equal number of labeled training data compared to labeled training data.
  • the data sources 108 and the signal data signature recording input 101 are stored in memory or a memory unit 104 and passed to a software 109 such as computer program or computer programs that executes the instruction set on a processor 105.
  • the software 109 being a computer program executes a signal data signature detection system 110 (which include signal data signature segmentation system 110a and SDS filtration system 110b, the signal data signature preparation system 110c) and a signal data signature classification system 111.
  • the signal data signature filter system 110b is used to ensure the SDS is of what quality to retain, discard and then process by the signal data signature preparation system 110c or sent directly to the signal data signature classification system 111.
  • the signal data signature classification system 111 executes a signal data signature classifier system 1 11.
  • the source models 116 define the boundaries 114 and scope to best classify the target.
  • the source models 116 are trained on subsets of the entire training set in order to attempt to deal with data variance among datasets. These source models 116 are also trained using slightly varying model architectures in an attempt to provide a little more understanding of the classification boundaries 114.
  • the oracle model 117 is trained on a new unique dataset that is predicated upon by all the source models 1 16. The predictions from the source models 116 are used as the oracle model 117 inputs which are then weighted to produce one final result that classifies that outcome of the system.
  • This outcome is a probability (between 0 and 1) that the provided observation belongs to class A which can also be considered as the 1 - p probability that it belongs to class B.
  • the system uses the combination of the source models 116 and the final oracle model 117 to produce the predictive value for the user.
  • the output 118 is a label that indicates the presence or absences of a condition given that an unlabeled signal data signature recording is provided as input 101 to the signal data signature detection system such that the output 118 can be viewed by a reader on a display screen 119 or printed on paper 120.
  • a suitable optimization function may be used to train the classifier models, including the source models 116 and the oracle model 117.
  • each source model 116 and the oracle model 117 may be separately trained using an associated optimization function.
  • each source model 116 may be used to predict a probability value for a training signal data signature and then trained based on error from the associated labeled training data using each associated optimization function.
  • the oracle model 117 may be trained using the predicted probability value from each source model 116 as input to predict a final predicted probability value, and then trained based on the error from the associated labeled training data using the associated optimization function.
  • the optimization function may employ a loss function, such as, e.g., Hinge Loss, Multi-class SVM Loss, Cross Entropy Loss, Negative Log Likelihood, or other suitable classification loss function to determine the error of the predicted label based on the known output.
  • the optimization function may include any suitable minimization algorithm for backpropagation such as a gradient method of the loss function with respect to the weights of the classifier machine learning model. Examples of suitable gradient methods include, e.g., stochastic gradient descent, batch gradient descent, mini-batch gradient descent, or other suitable gradient descent technique.
  • the signal data signature detection system 100 hardware 102 includes the computer 103 connected to the network 107.
  • the computer 103 is configured with one or more processors 105, a memory or memory 7 unit 104, and one or more network controllers 106.
  • the components of the computer 103 are configured and connected in such a way as to be operational so that an operating system and application programs may reside in a memory or memory unit 104 and may be executed by the processor or processors 105 and data may be transmitted or received via the network controller 106 according to instructions executed by the processor or processor(s) 105.
  • a data source 108 may be connected directly to the computer 103 and accessible to the processor 105, for example in the case of a signal data signature sensor, imaging sensor, or the like.
  • a data source 108 may be executed by the processor or processor(s) 105 and data may be transmitted or received via the network controller 106 according to instructions executed by the processor or processors 105.
  • a data source 108 may be connected to the signal data signature classifier system 111 remotely via the network 107, for example in the case of media data obtained from the Internet.
  • the configuration of the computer 103 may be that the one or more processors 105, memory 104, or network controllers 106 may physically reside on multiple physical components within the computer 103 or may be integrated into fewer physical components within the computer 103, without departing from the scope of the present disclosure.
  • a plurality of computers 103 may be configured to execute some or all of the steps listed herein, such that the cumulative steps executed by the plurality of computers are in accordance with the present disclosure.
  • the output 118 includes a strongly labeled signal data signature recording and identification of signal data signature type.
  • An example would be signal data signature sample from a patient which would include: 1) a label of the identified signal data signature type, 2) or flag that tells the user that a signal data signature was not detected.
  • the output 118 of signal data signature type or message that a signal data signature was not detected will be delivered to an end user via a display medium such as but not limited to a display screen 119 (e.g., tablet, mobile phone, computer screen) and/or paper 120.
  • FIG 2. illustrates an input to the signal data signature classifier system 11 1 that may include but is not limited to paired training dataset of signal data signature recordings and corresponding signal data signature labels and an unpaired signal data signature recording 101 that is first received and processed as a signal data signature wave by a hardware device such as a microphone 200.
  • the signal data signature labels may be input into the signal data signature classifier system using a physical hardware device such as a keyboard.
  • the signal data signature classifier system 111 uses a hardware 102, which includes a memory or memory unit 104, and processor 105 such that software 109, a computer program or computer programs is executed on a processor 105 and trains in realtime a set of signal data signature classifiers.
  • the output from signal data signature classifier system 111 is a label 118 that matches and diagnosis a signal data signature recording file.
  • a user is able to the signal data signature type output 118 on a display screen 119 or printed paper 120.
  • the signal data signature classifiers may be configured to additionally utilize one or more exemplary AI/ML techniques for data segmentation and classification tasks, e.g., such as one or more of the techniques including, but not limited to, decision trees, boosting, support-vector machines, neural networks, nearest neighbor algorithms, Naive Bayes, bagging, random forests, and the like.
  • the signal data signature classifiers may include an exemplary neutral network technique such as, without limitation, feedforward neural network, radial basis function network, recurrent neural network, convolutional network (e.g., U-net) or other suitable network.
  • an exemplary implementation of Neural Network may be executed as follows: a. define Neural Network architecture/model, b. transfer the input data to the exemplary' neural network model, c. train the exemplary model incrementally, d. determine the accuracy for a specific number of timesteps, e. apply the exemplary trained model to process the newly -received input data, f. optionally and in parallel, continue to train the exemplary trained model with a predetermined periodicity'.
  • the exemplary trained neural network model may specify a neural network by at least a neural network topology, a series of activation functions, and connection weights.
  • the topology of a neural network may include a configuration of nodes of the neural network and connections between such nodes.
  • the exemplary trained neural network model may also be specified to include other parameters, including but not limited to, bias values/functions and/or aggregation functions.
  • an activation function of a node may be a step function, sine function, continuous or piecewise linear function, sigmoid function, hyperbolic tangent function, or other type of mathematical function that represents a threshold at which the node is activated.
  • the exemplary aggregation function may be a mathematical function that combines (e.g., sum, product, and the like) input signals to the node.
  • an output of the exemplary aggregation function may be used as input to the exemplary activation function.
  • the bias may be a constant value or function that may be used by the aggregation function and/or the activation function to make the node more or less likely to be activated.
  • FIG. 2 depicts a partial view of the signal data signature detection system 110 including (110a, 110b and 110c) as elements of 202, with an input signal data signature recording 101 captured using a physical hardware device, microphone 200; such that the signal data signature signal is captured as a .wav file 201, or any other type of computer readable signal data signature signal formatted file, and is then pre-processed 202.
  • Signal Data Signature Pre- Processing 202 imposes a few, basic standards upon the sample via one or more cleansing, filtering and/or normalizing processes. Such cleansing, filtering and/or normalizing ensures high-quality audio files.
  • any other suitable filters may be employed for signal quality optimization, such as one or more filters for, e.g., dynamic range modification (e.g., via dynamic range compression or expansion), optimization of signal to noise ratio, removal, suppression or otherwise mitigation of ancillary noise(s), implementation of bandlimiting to isolate frequency content within a range of interest (e.g., via resampling or the use of equalization filters), among other signal optimizations or any combination thereof.
  • dynamic range modification e.g., via dynamic range compression or expansion
  • optimization of signal to noise ratio e.g., via removal, suppression or otherwise mitigation of ancillary noise(s)
  • implementation of bandlimiting to isolate frequency content within a range of interest e.g., via resampling or the use of equalization filters
  • background noise may be filtered from a sample including one or more recordings of a vocalization, and then the vocalization with the recording(s) can be identified, e.g., using a Pretrained Audio Neural Network (PANN) or other detection/recognition tools or any combination thereof.
  • PANN Pretrained Audio Neural Network
  • audio samples that do not contain a vocalization may be prevented from being processed by the system to avoid unnecessary resource utilization.
  • the SDSs above the threshold for match are then passed to a classifier 121, such as a deep learning or other supervised learning classifier model such as, e.g., a neural network-based classifier (e.g., a convolutional neural network (CNN), recurrent neural network (RNN), or other deep learning neural network (DNN) or any combination thereof), of the signal data signature classifier system 111.
  • a neural network-based classifier e.g., a convolutional neural network (CNN), recurrent neural network (RNN), or other deep learning neural network (DNN) or any combination thereof.
  • CNN convolutional neural network
  • RNN recurrent neural network
  • DNN deep learning neural network
  • Process 300 which provides functionality executed by the SDS detection system 110 for segment splitting, segment filtering and segment preparation, as discussed herein. According to some embodiments, as discussed herein, Process 300 involves operations by system 110 for the detection of the three phases of the input cough (as illustrated in FIG. 3B), thereby enabling audio of the cough to be passed to the classification system 111.
  • Process 300 begins with Step 302 where input audio is received.
  • the audio can be any t pe of recording or file (e.g., .wav file, for example) that includes audio information.
  • the audio can be received in real-time via a microphone (e.g., direct input), or can be an audio file that is retrieved from a stored location.
  • Step 304 the input audio file is analyzed and the SDS of the audio file is determined.
  • the determination of the SDS is performed via implementation of the HMM filter 110a, whereby the audio can be split into individual audio files (e.g., split the single cough into individual coughs).
  • Step 304 can involve parsing the audio file, determining, extracting, retrieving, or otherwise identifying the parameters associated with an SDS therefrom.
  • the analysis and identification of the SDS can be performed by any known or to be known audio (or media) file analysis technique, algorithm, classifier or mechanism, including, but not limited to, HMM, artificial neural network analysis (ANN), convolutional neural networks (CNN), computer vision, Bayesian network analysis, data mining, feature vector analysis, logical model and/or tree analysis, data mining, and the like.
  • the determination of the SDS can involve the creation of a SDS file or data structure (e.g., data and/or metadata) that can be analyzed as Process 300 progresses, as discussed below. Therefore, in some embodiments, the below processing related to the SDS should be understood to correspond to a file comprising data and/or metadata of the audio file.
  • the SDS file can be stored in a database in accordance with the audio file (e g., in a look-up table (LUT)).
  • Step 306 the determine SDS is split into unique signature segments.
  • the unique signature segments can correspond to the first, second and third phase (the explosive phase, intermediate phase and voiced phase, respectively). Accordingly, in some embodiments, for example, each SDS segment can comprise a single cough.
  • Step 306 can involve the determination as to whether all three phases of a cough exist.
  • the determined SDS can be analyzed (wherein, in some embodiments, such analysis can be performed in a similar manner as in Step 304), whereby a single cough (or SDS segments) of the audio file are identified.
  • the anatomy of a cough can be segmented into three phases: a first phase (e.g., rapidly exhaled air); a second phase (e.g., sharp drop-off in energy' from the burst that is due to the closing of the glottis); and a third phase (e.g., the voiced phase of the cough).
  • a first phase e.g., rapidly exhaled air
  • a second phase e.g., sharp drop-off in energy' from the burst that is due to the closing of the glottis
  • a third phase e.g., the voiced phase of the cough.
  • Step 308 involves the determination of the three phases of the cough.
  • Step 308 may be optional, as a determination as to whether all three phases are present may not be necessary' for purposes of executing the steps of Process 300.
  • a PDA is applied to the third phase/segment of the audio file.
  • the PDA can operate in the time domain and/or frequency domain, can be utilized to determine or identify the pitch or fundamental frequency of a quasiperiodic and/or oscillating signal from the cough.
  • the input to the PDA can be the SDS portion related to the third phase, a spectrogram of the audio file (or third phase portion), or any other type of digital representation of the pitch data related to the audio file and/or third phase.
  • Step 312 the output of the PDA on the SDS segment is stored and evaluated applied to the third phase/segment of the audio file.
  • Step 314 based on the applied PDA to the third phase/segment of the audio file (or SDS), a determination is made regarding whether a threshold satisfying amount of pitch is present within the third phase.
  • the pitch threshold corresponds to a determined pitch value that is at least audible enough for classification. That is, for example, it can be classified by classification system 111.
  • Process 300 proceeds from Step 314 to Step 318 where the SDS of the input audio of the cough (and/or the input audio) is discarded, with no further processing.
  • Process 300 can reapply Step 312 in order to “double-check” that there was no error in the PDA processing.
  • Process 300 proceeds from Step 314 to Step 316 where the audio file is transmitted to the classification system 111 for classification of the cough.
  • the SDS can be provided to preparation system 110c for normalization and reduction of background noise pnor to transmission to classification system 111.
  • FIG. 4 depicted is a block diagram of an exemplary computer-based system and platform 400 in accordance with one or more embodiments of the present disclosure.
  • the illustrative computing devices and the illustrative computing components of the exemplary 7 computer-based system and platform 400 may be configured to manage a large number of members and concurrent transactions, as detailed herein.
  • the exemplary computer-based system and platform 400 may be based on a scalable computer and network architecture that incorporates varies strategies for assessing the data, caching, searching, and/or database connection pooling.
  • An example of the scalable architecture is an architecture that is capable of operating multiple servers.
  • members 402-404 e.g., clients of the exemplary computer-based system and platform 400 may include virtually any computing device capable of receiving and sending a message over a network (e.g., cloud network), such as network 405, to and from another computing device, such as servers 406 and 407, each other, and the like.
  • the member devices 402-404 may be personal computers, multiprocessor systems, microprocessor-based or programmable consumer electronics, network PCs, and the like.
  • one or more member devices within member devices 402-404 may include computing devices that ty pically connect using a wireless communications medium such as cell phones, smart phones, pagers, walkie talkies, radio frequency (RF) devices, infrared (IR) devices, CBs, integrated devices combining one or more of the preceding devices, or virtually any mobile computing device, and the like.
  • a wireless communications medium such as cell phones, smart phones, pagers, walkie talkies, radio frequency (RF) devices, infrared (IR) devices, CBs, integrated devices combining one or more of the preceding devices, or virtually any mobile computing device, and the like.
  • one or more member devices within member devices 402-404 may be devices that are capable of connecting using a wired or wireless communication medium such as a PDA, POCKET PC, wearable computer, a laptop, tablet, desktop computer, a netbook, a video game device, a pager, a smart phone, an ultra-mobile personal computer (UMPC), and/or any other device that is equipped to communicate over a wired and/or wireless communication medium (e.g., NFC, RFID, NBIOT, 3G, 4G, 5G, GSM, GPRS, WiFi, WiMax, CDMA, satellite, ZigBee, and the like).
  • a wired or wireless communication medium such as a PDA, POCKET PC, wearable computer, a laptop, tablet, desktop computer, a netbook, a video game device, a pager, a smart phone, an ultra-mobile personal computer (UMPC), and/or any other device that is equipped to communicate over a wired and/or wireless communication medium (e.g., NFC, RFID
  • one or more member devices within member devices 402-404 may include may run one or more applications, such as Internet browsers, mobile applications, voice calls, video games, videoconferencing, and email, among others. In some embodiments, one or more member devices within member devices 402-404 may be configured to receive and to send web pages, and the like.
  • an exemplary specifically programmed browser application of the present disclosure may be configured to receive and display graphics, text, multimedia, and the like, employing virtually any web based language, including, but not limited to Standard Generalized Markup Language (SMGL), such as HyperText Markup Language (HTML), a wireless application protocol (WAP), a Handheld Device Markup Language (HDML), such as Wireless Markup Language (WML), WMLScript, XML, JavaScript, and the like.
  • SMGL Standard Generalized Markup Language
  • HTML HyperText Markup Language
  • WAP wireless application protocol
  • HDML Handheld Device Markup Language
  • WMLScript Wireless Markup Language
  • a member device within member devices 402-404 may be specifically programmed by either Java. .Net, QT, C, C++ and/or other suitable programming language.
  • one or more member devices within member devices 402-404 may be specifically programmed include or execute an application to perform a variety of possible tasks, such as, without limitation, messaging functionality, browsing, searching, playing, streaming or displaying various forms of content, including locally stored or uploaded messages, images and/or video, and/or games.
  • the exemplary network 405 may provide network access, data transport and/or other services to any computing device coupled to it.
  • the exemplary network 405 may include and implement at least one specialized network architecture that may be based at least in part on one or more standards set by, for example, without limitation.
  • GSM Global System for Mobile communication
  • IETF Internet Engineering Task Force
  • WiMAX Worldwide Interoperability for Microwave Access
  • the exemplary 7 network 405 may implement one or more of a GSM architecture, a General Packet Radio Service (GPRS) architecture, a Universal Mobile Telecommunications System (UMTS) architecture, and an evolution of UMTS referred to as Long Term Evolution (LTE).
  • GSM Global System for Mobile communication
  • IETF Internet Engineering Task Force
  • WiMAX Worldwide Interoperability for Microwave Access
  • the exemplary 7 network 405 may implement one or more of a GSM architecture, a General Packet Radio Service (GPRS) architecture, a Universal Mobile Telecommunications System (UMTS) architecture, and an evolution of
  • the exemplary network 405 may include and implement, as an alternative or in conjunction with one or more of the above, a WiMAX architecture defined by the WiMAX forum.
  • the exemplary network 405 may also include, for instance, at least one of a LAN, a WAN, the Internet, a virtual LAN (VLAN), an enterprise LAN, a layer 3 virtual private network (VPN), an enterprise IP network, or any combination thereof.
  • VLAN virtual LAN
  • VPN layer 3 virtual private network
  • enterprise IP network or any combination thereof.
  • At least one computer network communication over the exemplary network 405 may be transmitted based at least in part on one of more communication modes such as but not limited to: NFC, RFID, Narrow Band Internet of Things (NBIOT), ZigBee, 3G. 4G, 5G, GSM, GPRS, WiFi, WiMax, CDMA, satellite and any combination thereof.
  • the exemplary network 405 may also include mass storage, such as NAS, SAN, CDN or other forms of computer or machine readable media.
  • the exemplary server 406 or the exemplary server 407 may be a web server (or a series of servers) running a network operating system, examples of which may include but are not limited to Microsoft Windows Server, Novell NetWare, or Linux.
  • the exemplary server 406 or the exemplary server 407 may be used for and/or provide cloud and/or network computing.
  • the exemplary server 406 or the exemplary server 407 may have connections to external systems like email, SMS messaging, text messaging, ad content providers, and the like. Any of the features of the exemplary server 406 may be also implemented in the exemplary server 407 and vice versa.
  • one or more of the exemplary servers 406 and 407 may be specifically programmed to perform, in non-limiting example, as authentication servers, search servers, email servers, social networking services servers, SMS servers, IM servers, MMS servers, exchange servers, photo-sharing sendees servers, advertisement providing servers, financial/banking-related services servers, travel services servers, or any similarly suitable service-base servers for users of the member computing devices 401-404.
  • the exemplary 7 server 406, and/or the exemplary' server 407 may include a specifically programmed software module that may be configured to send, process, and receive information using a scripting language, a remote procedure call, an email, a tweet, Short Message Service (SMS), Multimedia Message Service (MMS), instant messaging (IM), internet relays chat (IRC), mIRC, Jabber, an application programming interface, Simple Object Access Protocol (SOAP) methods, Common Object Request Broker Architecture (CORBA), HTTP (Hypertext Transfer Protocol), REST (Representational State Transfer), or any combination thereof.
  • SMS Short Message Service
  • MMS Multimedia Message Service
  • IM instant messaging
  • IRC internet relays chat
  • mIRC Jabber
  • SOAP Simple Object Access Protocol
  • CORBA Common Object Request Broker Architecture
  • HTTP Hypertext Transfer Protocol
  • REST Real-Representational State Transfer
  • FIG. 5 depicts a block diagram of another exemplary computer-based system and platform 500 in accordance with one or more embodiments of the present disclosure.
  • the member computing devices 502a, 502b thru 502n shown each at least includes a computer- readable medium, such as a random-access memory (RAM) 508 coupled to a processor 510 or FLASH memory.
  • the processor 510 may execute computer-executable program instructions stored in memory 508.
  • the processor 510 may include a microprocessor, an ASIC, and/or a state machine.
  • the processor 510 may include, or may be in communication with, media, for example computer- readable media, which stores instructions that, when executed by the processor 510, may cause the processor 510 to perform one or more steps described herein.
  • examples of computer-readable media may include, but are not limited to, an electronic, optical, magnetic, or other storage or transmission device capable of providing a processor, such as the processor 510 of client 502a, with computer-readable instructions.
  • suitable media may include, but are not limited to, a floppy disk, CD-ROM, DVD, magnetic disk, memory chip, ROM, RAM, an ASIC, a configured processor, all optical media, all magnetic tape or other magnetic media, or any other medium from which a computer processor can read instructions.
  • various other forms of computer- readable media may transmit or carry instructions to a computer, including a router, private or public network, or other transmission device or channel, both wired and wireless.
  • the instructions may comprise code from any computer-programming language, including, for example, C, C++, Visual Basic. Java, Python, Perl, JavaScript, and the like.
  • member computing devices 502a through 502n may also comprise a number of external or internal devices such as a mouse, a CD-ROM, DVD, a phy sical or virtual keyboard, a display, or other input or output devices.
  • examples of member computing devices 502a through 502n e.g., clients
  • member computing devices 502a through 502n may be specifically programmed with one or more application programs in accordance with one or more principles/methodologies detailed herein.
  • member computing devices 502a through 502n may operate on any operating system capable of supporting a browser or browser-enabled application, such as MicrosoftTM, WindowsTM, and/or Linux.
  • member computing devices 502a through 502n shown may include, for example, personal computers executing a browser application program such as Microsoft Corporation's Internet ExplorerTM, Apple Computer, Inc.’s SafariTM. Mozilla Firefox, and/or Opera.
  • users, 512a through 502n may communicate over the exemplary network 506 with each other and/or with other systems and/or devices coupled to the network 506.
  • exemplary server devices 504 and 513 may be also coupled to the network 506.
  • one or more member computing devices 502a through 502n may be mobile clients.
  • At least one database of exemplary databases 507 and 515 may be any type of database, including a database managed by a database management system (DBMS).
  • DBMS database management system
  • an exemplary DBMS-managed database may be specifically programmed as an engine that controls organization, storage, management, and/or retrieval of data in the respective database.
  • the exemplary DBMS-managed database may be specifically programmed to provide the ability to query, backup and replicate, enforce rules, provide security, compute, perform change and access logging, and/or automate optimization.
  • the exemplary DBMS-managed database may be chosen from Oracle database, IBM DB2, Adaptive Server Enterprise, FileMaker, Microsoft Access, Microsoft SQL Server, MySQL, PostgreSQL, and a NoSQL implementation.
  • the exemplar ⁇ ' DBMS-managed database may be specifically programmed to define each respective schema of each database in the exemplary DBMS, according to a particular database model of the present disclosure which may include a hierarchical model, network model, relational model, object model, or some other suitable organization that may result in one or more applicable data structures that may include fields, records, files, and/or objects.
  • the exemplary’ DBMS-managed database may be specifically programmed to include metadata about the data that is stored.
  • FIG. 6 and FIG. 7 illustrate schematics of exemplary implementations of the cloud computing/architecture(s) in which the exemplary novel computer-based systems/platforms, the exemplary novel computer-based devices, and/or the exemplary novel computer-based components of the present disclosure may be specifically configured to operate.
  • the exemplary novel computer-based systems/platforms, the exemplary novel computer-based devices, and/or the exemplary novel computer-based components of the present disclosure may be specifically configured to operate in a cloud computing/ architecture 525 such as, but not limiting to: infrastructure a service (laaS) 710, platform as a service (PaaS) 708, and/or software as a sendee (SaaS) 706 using a web browser, mobile app, thin client, terminal emulator or other endpoint 704, as depicted in FIG. 7.
  • a cloud computing/ architecture 525 such as, but not limiting to: infrastructure a service (laaS) 710, platform as a service (PaaS) 708, and/or software as a sendee (SaaS) 706 using a web browser, mobile app, thin client, terminal emulator or other endpoint 704, as depicted in FIG. 7.
  • a module is a software, hardware, or firmware (or combinations thereof) system, process or functionality, or component thereof, that performs or facilitates the processes, features, and/or functions described herein (with or without human interaction or augmentation).
  • a module can include sub-modules.
  • Softw are components of a module may be stored on a computer readable medium for execution by a processor. Modules may be integral to one or more servers, or be loaded and executed by one or more servers. One or more modules may be grouped into an engine or an application.
  • the term “user”, “‘subscriber’ “consumer” or “customer” should be understood to refer to a user of an application or applications as described herein and/or a consumer of data supplied by a data provider.
  • the term “user” or “subscriber” can refer to a person who receives data provided by the data or service provider over the Internet in a browser session, or can refer to an automated software application which receives the data and stores or processes the data.
  • the methods and systems of the present disclosure may be implemented in many manners and as such are not to be limited by the foregoing exemplary embodiments and examples.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Signal Processing (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Epidemiology (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

L'invention concerne des systèmes et des procédés pour un cadre informatisé qui traite ces inconvénients, entre autres, en fournissant un nouveau cadre de classification de signature de données de signal (SDS). Selon certains modes de réalisation de la présente divulgation, le cadre SDS décrit utilise une technologie basée sur l'intelligence artificielle et/ou l'apprentissage automatique (IA/ML) pour effectuer une segmentation audio et une extraction de caractéristiques pour déterminer une classification SDS. Les systèmes et les procédés de l'invention fournissent des techniques d'extraction de caractéristiques généralisables qui peuvent être appliquées à des segments SDS afin d'effectuer une classification du SDS et/ou des paramètres SDS. Le cadre fonctionne pour discerner si les phases/segments appropriés d'un fichier audio d'entrée sont présents, ce par quoi une classification peut se produire sur la base de celle-ci.
PCT/US2023/074308 2022-09-15 2023-09-15 Systèmes et procédés de filtration et de classification de segments de signature de données de signal WO2024059796A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US202263375821P 2022-09-15 2022-09-15
US63/375,821 2022-09-15

Publications (1)

Publication Number Publication Date
WO2024059796A1 true WO2024059796A1 (fr) 2024-03-21

Family

ID=90275825

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2023/074308 WO2024059796A1 (fr) 2022-09-15 2023-09-15 Systèmes et procédés de filtration et de classification de segments de signature de données de signal

Country Status (1)

Country Link
WO (1) WO2024059796A1 (fr)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070276278A1 (en) * 2003-04-10 2007-11-29 Michael Coyle Systems and methods for monitoring cough
WO2022091062A1 (fr) * 2020-11-02 2022-05-05 Dzhekiev Igor Détection automatique de sons respiratoires associés à une maladie

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070276278A1 (en) * 2003-04-10 2007-11-29 Michael Coyle Systems and methods for monitoring cough
WO2022091062A1 (fr) * 2020-11-02 2022-05-05 Dzhekiev Igor Détection automatique de sons respiratoires associés à une maladie

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
ALICE ASHBY: "Cough-based COVID-19 detection with audio quality clustering and confidence measure based learning", CONFORMAL AND PROBABILISTIC PREDICTION WITH APPLICATIONS, 24 August 2022 (2022-08-24), pages 1 - 21, XP093153335 *
ALICE EVELYN ASHBY: "A novel cough audio pre-processing and segmentation algorithm for COVID-19 detection", BACHELOR OF SCIENCE THESIS, 2 June 2022 (2022-06-02), pages 1 - 79, XP093153331 *
AYDIN TEYHOUEE; NATHANIEL D. OSGOOD: "Cough Detection Using Hidden Markov Models", ARXIV.ORG, 28 April 2019 (2019-04-28), 201 Olin Library Cornell University Ithaca, NY 14853 , XP081268172 *
XIYU ZHANG: "Novel COVID-19 Screening Using Cough Recordings of A Mobile Patient Monitoring System", 2021 43RD ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE & BIOLOGY SOCIETY (EMBC), 1 November 2021 (2021-11-01), pages 2353 - 2357, XP093153342, DOI: 10.1109/EMBC46164.2021.9630722 *

Similar Documents

Publication Publication Date Title
Mouawad et al. Robust detection of COVID-19 in cough sounds: using recurrence dynamics and variable Markov model
US11538472B2 (en) Processing speech signals in voice-based profiling
Ali et al. Voice recognition system using machine learning techniques
US20210020191A1 (en) Methods and systems for voice profiling as a service
Barata et al. Automatic recognition, segmentation, and sex assignment of nocturnal asthmatic coughs and cough epochs in smartphone audio recordings: observational field study
Melek Diagnosis of COVID-19 and non-COVID-19 patients by classifying only a single cough sound
US11996117B2 (en) Multi-stage adaptive system for content moderation
Nemati et al. Private audio-based cough sensing for in-home pulmonary assessment using mobile devices
WO2022091062A1 (fr) Détection automatique de sons respiratoires associés à une maladie
JP2023538287A (ja) 呼吸器症候群を検出するためのアンサンブル機械学習モデル
KR102314572B1 (ko) 인공지능 기반의 언어 능력 평가 방법 및 시스템
Fontes et al. Classification system of pathological voices using correntropy
Sadiq et al. Deep learning based multimedia data mining for autism spectrum disorder (ASD) diagnosis
Boulares et al. Transfer learning benchmark for cardiovascular disease recognition
Deb et al. Detection of common cold from speech signals using deep neural network
Turan et al. Monitoring Infant's Emotional Cry in Domestic Environments Using the Capsule Network Architecture.
Usman et al. Heart rate detection and classification from speech spectral features using machine learning
Shuvo et al. NRC-Net: Automated noise robust cardio net for detecting valvular cardiac diseases using optimum transformation method with heart sound signals
WO2022147566A1 (fr) Procédé et système d'apprentissage automatique utilisant un plan d'apprentissage automatique dérivé us22011178
Sanjeev et al. Deep learning-based mixed data approach for COVID-19 detection
CN112466284B (zh) 一种口罩语音鉴别方法
CN109634554B (zh) 用于输出信息的方法和装置
WO2024059796A1 (fr) Systèmes et procédés de filtration et de classification de segments de signature de données de signal
US20220300856A1 (en) Signal data signature classifiers trained with signal data signature libraries and a machine learning derived strategic blueprint
Raina et al. Intelligent and Interactive Healthcare System (I 2 HS) Using Machine Learning

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23866531

Country of ref document: EP

Kind code of ref document: A1