CN109003612B - Voice question-answer verification system and method based on artificial intelligence - Google Patents
Voice question-answer verification system and method based on artificial intelligence Download PDFInfo
- Publication number
- CN109003612B CN109003612B CN201810588018.6A CN201810588018A CN109003612B CN 109003612 B CN109003612 B CN 109003612B CN 201810588018 A CN201810588018 A CN 201810588018A CN 109003612 B CN109003612 B CN 109003612B
- Authority
- CN
- China
- Prior art keywords
- voice
- question
- signal
- data
- storage device
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/22—Interactive procedures; Man-machine interfaces
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/22—Interactive procedures; Man-machine interfaces
- G10L17/24—Interactive procedures; Man-machine interfaces the user being prompted to utter a password or a predefined phrase
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/0861—Network architectures or network communication protocols for network security for authentication of entities using biometrical features, e.g. fingerprint, retina-scan
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/10—Network architectures or network communication protocols for network security for controlling access to devices or network resources
- H04L63/108—Network architectures or network communication protocols for network security for controlling access to devices or network resources when the policy decisions are valid for a limited amount of time
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/14—Session management
- H04L67/143—Termination or inactivation of sessions, e.g. event-controlled end of session
- H04L67/145—Termination or inactivation of sessions, e.g. event-controlled end of session avoiding end of session, e.g. keep-alive, heartbeats, resumption message or wake-up for inactive or interrupted session
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Abstract
A voice question-answer verification system based on artificial intelligence carries out voiceprint verification on voice request signals through a characteristic identification module to generate confirmation signals and obtain certain identity data, then the voice question-answer module randomly selects a certain person question from a question database to carry out voice question-answer, when the result of the voice question-answer accords with a built-in answer, voice identification and semantic identification are carried out on the voice request signals to connect a corresponding cloud storage device, when the time for connecting the cloud storage device exceeds preset time, voice analysis is carried out according to received voice maintaining signals, and whether connection with the cloud storage device is maintained or not is judged, so that the technical effects of improving the safety of identity verification and strengthening the safety management of the cloud storage device are achieved.
Description
Technical Field
The invention relates to a voice question-answer verification system and a method thereof, in particular to a voice question-answer verification system and a method thereof based on artificial intelligence.
Background
With the widespread use of various types of information devices, more and more users have files or data stored in various types of information devices in a computerized manner, such as: cloud storage device. However, the general cloud storage device mainly provides security protection through setting of an account and a password, and performs identity verification of a user through verification of the account and the password to protect files or data stored in the cloud storage device. However, the protection of such files or data has the problem that the account number and the password may be stolen by others, resulting in the theft of the files or data.
In summary, it can be seen that there exists a problem in the prior art that files or data stored in the cloud storage device are stolen due to the possibility that the account and the password are stolen by others, and therefore, an improved technical means is needed to solve the problem.
Disclosure of Invention
The invention discloses a voice question-answer verification system and a voice question-answer verification method based on artificial intelligence.
First, the present invention describes a voice question-answer verification system based on artificial intelligence, which comprises: the system comprises a voiceprint database, a question database, an identity identification database, a receiving module, a feature identification module, a voice question-answering module and a processing module. The voice print database is used for storing a plurality of identity data and a plurality of preset voice print data, and the identity data corresponds to the preset voice print data in a one-to-one mode; the question database is used for storing a question template, and the question template comprises a plurality of personal questions; the identity identification database is used for storing a plurality of identity identification data, and each identity identification data comprises certain identity data, the personal question and an answer responding to each personal question; the receiving module is used for receiving the voice request signal and the voice reply signal; the characteristic identification module is used for carrying out characteristic analysis on the voice request signal to obtain voice characteristic data, comparing the voice characteristic data with the preset voiceprint data, and generating a confirmation signal and obtaining corresponding certain identity data when the voice characteristic data is consistent with one of the preset voiceprint data; the voice question-answering module is used for randomly selecting a certain person question from the question database to perform voice question-asking when the feature identification module generates a confirmation signal, comparing a voice reply signal for responding the person question with an answer of the identity data acquired by the feature identification module for responding the person question, and performing voice identification and semantic identification on a voice request signal to acquire a control instruction when the voice reply signal is consistent with the answer of the identity data acquired by the feature identification module for responding the person question, wherein the control instruction comprises a connection command and a device name; and the processing module is used for connecting the cloud storage device corresponding to the device name according to the connection command. When the time for connecting the cloud storage device exceeds the preset time, the processing module requests to input a voice maintaining signal, the receiving module receives the voice maintaining signal, the characteristic identification module carries out voiceprint identification on the voice maintaining signal, and after the voiceprint identification and verification pass, the voice question-answering module carries out voice analysis on the voice maintaining signal, so that the processing module judges whether to maintain connection with the cloud storage device according to the voice analysis result of the voice maintaining signal.
In addition, the invention discloses a voice question-answer verification method based on artificial intelligence, which comprises the following steps: receiving a voice request signal; carrying out feature analysis on the voice request signal to obtain voice feature data, and comparing the voice feature data with a plurality of preset voiceprint data; when the voice characteristic data is judged to be consistent with one of the preset voiceprint data, generating a confirmation signal and acquiring identity data; randomly selecting a person question from a question database to perform voice questioning when a confirmation signal is generated; receiving back a voice reply signal corresponding to the personal question; comparing the voice reply signal responding to the personal question with the answer of the identity data responding to the personal question in the identity recognition database; when the voice reply signal is consistent with the answer of the identity data in the identity recognition database, which is responded to the personal question, voice recognition and semantic recognition are carried out on the voice request signal to obtain a control instruction, wherein the control instruction comprises a connection command and a device name; connecting the cloud storage device corresponding to the device name according to the connection command; when the time for connecting the cloud storage device exceeds the preset time, requesting to input a voice maintaining signal; after receiving the voice maintaining signal, carrying out voiceprint recognition on the voice maintaining signal; after the voiceprint identification verification is passed, carrying out voice analysis on the voice maintaining signal; and judging whether to maintain connection with the cloud storage device according to the voice analysis result of the voice maintaining signal.
The system and the method described in the invention are different from the prior art in that the voice request signal is subjected to voiceprint verification through the characteristic identification module to generate a confirmation signal and obtain certain integrity data, then the voice question-answering module randomly selects a certain personal question from the question database to carry out voice question asking, compares a voice reply signal responding to the personal question with an answer responding to the personal question through the identity data, and performs voice identification and semantic identification on the voice request signal when the voice reply signal is consistent with the answer to obtain a control instruction containing a connection command and a device name, so that the processing module is connected with the cloud storage device corresponding to the device name according to the connection command. And when the time for connecting the cloud storage device exceeds the preset time, carrying out voice analysis according to the received voice maintaining signal, and further judging whether to maintain the connection with the cloud storage device.
Through the technical means, the identity of the user can be verified through voiceprint recognition and random voice question answering, and when the identity of the user passes verification, the specified cloud storage device can be connected, so that the technical effect of improving the safety of identity verification is achieved. In addition, when the time for connecting the cloud storage device exceeds the preset time, the voice maintaining signal can be requested to be input, the received voice maintaining signal is subjected to voice analysis, and whether the connection with the cloud storage device is maintained or not is further judged so as to enhance the safety management of the cloud storage device.
Drawings
FIG. 1 is a system block diagram of an embodiment of an artificial intelligence based voice question-answer verification system according to the present invention.
FIG. 2 is a diagram of an embodiment of each identification data in the identification database of FIG. 1.
FIG. 3 is a table showing the vocabulary and categories recorded in the semantic database of the artificial intelligence based voice question-answer verification system of FIG. 1.
FIG. 4A is a block diagram of an exemplary format of control commands for the artificial intelligence based voice question answering verification system of FIG. 1.
FIG. 4B is a diagram of an embodiment of control commands in the artificial intelligence based voice question answering verification system of FIG. 1.
FIG. 5 is a flowchart of an embodiment of the artificial intelligence based voice question-answer verification system of FIG. 1 executing an artificial intelligence based voice question-answer verification method.
FIG. 6 is a flowchart of an embodiment of a method for adding a valid user to the artificial intelligence based voice question-answer verification system of FIG. 1.
Fig. 7 is a flowchart illustrating an embodiment of a method for enhancing security management of a cloud storage device by the artificial intelligence based voice question-answer verification system of fig. 1.
Fig. 8 is a flowchart of an embodiment of a method for performing file access of a cloud storage device by the artificial intelligence based voice question-answer verification system of fig. 1 in a voice control manner.
[ List of reference numerals ]
30 voiceprint database
40 problem database
50 identity recognition database
60 semantic database
70 voice database
100 voice question-answer verification system based on artificial intelligence
110 receiving module
120 characteristic identification module
130 voice question-answer module
140 processing module
Detailed Description
The embodiments of the present invention will be described in detail with reference to the drawings and examples, so that how to implement the technical means for solving the technical problems and achieving the technical effects of the present invention can be fully understood and implemented.
Before explaining the artificial intelligence-based voice question-answer verification system and the method thereof, the nouns defined by the invention are explained, and the receiving module, the feature recognition module, the voice question-answer module and the processing module included in the artificial intelligence-based voice question-answer verification system can be realized in various ways, including software, hardware, firmware or any combination thereof. The techniques presented in the implementations may be stored on a machine-readable storage medium using software or firmware, such as: read Only Memory (ROM), Random Access Memory (RAM), magnetic disk storage media, optical storage media, flash memory devices, etc., and can be implemented by one or more general-purpose or special-purpose programmable microprocessors. The voice question-answer verification system based on artificial intelligence and the cloud storage device can pass through a network, such as: mobile communication networks, the internet, local area networks, wide area networks, and/or wireless networks are interconnected.
Referring to fig. 1, fig. 1 is a system block diagram of an embodiment of an artificial intelligence-based voice question-answer verification system 100 according to the present invention, where the artificial intelligence-based voice question-answer verification system 100 is used to connect to any cloud storage device, and the artificial intelligence-based voice question-answer verification system 100 may include: a voiceprint database 30, a question database 40, an identity recognition database 50, a receiving module 110, a feature recognition module 120, a voice question and answer module 130, and a processing module 140. The voiceprint database 30 is connected to the feature recognition module 120, the question database 40 is connected to the voice question and answer module 130, the identity recognition database 50 is connected to the voice question and answer module 130, the receiving module 110 is connected to the feature recognition module 120 and the voice question and answer module 130, the feature recognition module 120 is connected to the voice question and answer module 130 and the processing module 140, and the voice question and answer module 130 is connected to the processing module 140.
The voiceprint database 30 can be used to store a plurality of identity data and a plurality of preset voiceprint data, and the identity data corresponds to the preset voiceprint data in a one-to-one manner. Each identification data represents identification data of a user who can legally connect the artificial intelligence-based voice question-answer verification system 100 with the cloud storage device, and can be, but not limited to, an identification number, and can be adjusted according to actual requirements. Since the vocal organs used by the two persons are different, the vocal print maps of any two persons are different, so that the voices of different persons can be distinguished through the vocal print maps under general conditions.
The question database 40 may be used to store a question template, which contains a plurality of individual questions. The number of personal questions can be adjusted according to actual needs, and each personal question is a question that can be used to identify and distinguish different users, for example: identification number, graduation country, year of birth, month of birth, or name of the pet at home, etc.
The identity recognition database 50 may be used to store a plurality of identity recognition data, each of which includes a certain identity data, the personal question and the answer responding to each of the personal questions. For example, referring to fig. 2, fig. 2 is a schematic diagram of an embodiment of each identification data in the identification database of fig. 1, each identification data may be a data table, which includes, in addition to an identification data (e.g., an identification number), each personal question and its corresponding answer (i.e., the answer responded by the user having the identification data to each personal question), but this example is not intended to limit the present invention. In other words, the answer to each individual question in each identification data may be a pre-stored audio signal, and each pre-stored audio signal is the audio signal of each individual question that the new user would have answered when the new user who is legally using the artificial intelligence based voice question-answer verification system 100 is newly added.
The receiving module 110 is configured to receive a voice request signal and a plurality of voice reply signals. In practical implementation, the receiving module 110 can be, but is not limited to, a microphone for receiving voice input of a user. For example, when the user wants to connect to the cloud storage device with the device name "CDrive", the voice request signal may be "connect CDrive". Each voice reply signal is the spoken word of a user responding to a certain personal question, and the detailed description is given later.
The feature identification module 120 is configured to perform feature analysis on the voice request signal to obtain voice feature data, compare the voice feature data with the predetermined voiceprint data, and generate a confirmation signal and obtain corresponding certain identity data when the voice feature data matches one of the predetermined voiceprint data. Since the voiceprint maps of any two persons are different, in the embodiment, after receiving the voice request signal from the receiving module 110, the feature identifying module 120 may perform feature analysis on the voice request signal (i.e., convert the voice request signal into a voiceprint map, and extract feature parameters of the voiceprint map), so as to obtain voice feature data (i.e., feature parameters of the voiceprint map), and directly compare the voice feature data with a plurality of preset voiceprint data (i.e., voice feature data of a plurality of users to be set as legal users in advance) stored in the voiceprint database 30, when the voice feature data matches one of the preset voiceprint data, the user is considered as legal, the feature identifying module 120 may generate a confirmation signal (i.e., complete the preliminary identification authentication of the speaker), and since the identity data in the voiceprint database 30 corresponds to the preset voiceprint data in a one-to-one manner, therefore, when the voice feature data matches one of the predetermined voiceprint data, the feature identification module 120 can find a corresponding identity data (i.e. obtain the identity data representing the speaker) from the voiceprint database 30.
The voice question-answering module 130 is configured to randomly select a certain personal question from the question database 40 for voice question asking when the feature recognition module 120 generates the confirmation signal, compare the voice reply signal corresponding to the personal question with the answer of the identity data obtained by the feature recognition module 120 in response to the personal question, and perform voice recognition and semantic recognition on the voice request signal when the voice reply signal matches the answer of the identity data obtained by the feature recognition module 120 in response to the personal question to obtain the control command, wherein the control command includes the connection command and the device name.
In detail, after the feature recognition module 120 generates the confirmation signal and obtains a certain identity data (i.e. completing the initial identity authentication of the speaker and obtaining the identity data representing the speaker), the voice question answering module 130 can randomly select any one of the personal questions from the question database 40 for voice question asking, the user (i.e. the speaker) can reply with a voice reply signal (i.e. the user replies the utterance spoken by the personal question) corresponding to the personal question, and the receiving module 110 receives the voice reply signal responding to the personal question. In this embodiment, since each identification data may be the data table shown in fig. 2, the voice question-answering module 130 may first perform voice-to-text conversion on the voice reply signal to generate a text representation (i.e., perform voice analysis), then find the corresponding identification data in the identification database 50 according to the identification data obtained by the feature recognition module 120, compare the voice analysis result (i.e., the text representation) of the voice reply signal with the answer corresponding to the personal question in the corresponding identification data, and when the voice analysis result of the voice reply signal matches the answer corresponding to the personal question in the corresponding identification data, represent that the user passes further identification verification (i.e., the speaker is determined to be a valid user); when the voice analysis result of the voice reply signal does not match the answer responded to the personal question in the corresponding identification data, it means that the user cannot pass further identification verification (i.e. the speaker is not a legal user), and cannot execute the subsequent procedure (i.e. cannot connect to the cloud storage device).
For example, since the answer in each identification data to each individual question may also be a pre-stored voice signal, the voice question-answering module 130 may first find the corresponding identification data in the identification database 50 according to the identification data obtained by the feature recognition module 120, then find the corresponding pre-stored voice signal (i.e., the answer to the individual question) according to the individual question, and then directly compare the voice reply signal with the pre-stored voice signal (i.e., compare the voice waveforms), when the voice reply signal matches the pre-stored voice signal, it represents that the user passes further identification verification (i.e., the speaker is determined to be a valid user); when the voice reply signal does not match the pre-stored voice signal, it means that the user cannot pass further identification verification (i.e. the speaker is not a legal user), and cannot execute the subsequent procedure (i.e. cannot connect to the cloud storage device).
In addition, in the embodiment, the voice question-answering module 130 only randomly selects any one person question from the question database 40 for voice question-asking to perform further identity verification, but the embodiment is not intended to limit the invention. For example, in order to improve the accuracy of the identity verification, the voice question-answering module 130 may randomly select a plurality of personal questions from the question database 40 to perform voice question-asking one by one, and may perform the voice analysis and comparison on the voice reply signal of each personal question responded by the user one by one, and when the comparison result is not consistent, it means that the user cannot pass further identity verification and cannot execute the subsequent procedure (i.e., cannot connect to the cloud storage device).
After the user passes the further identity verification, the voice question-answering module 130 may perform voice recognition on the voice request signal (i.e., the speech spoken by the user when requesting to connect to the cloud storage device) to obtain at least one voice data (i.e., find the vocabulary corresponding to the voice request signal), and then query the category corresponding to the at least one voice data from the semantic database 60 according to the at least one voice data to obtain the control command corresponding to the at least one voice data (i.e., perform semantic recognition), where the control command includes a connection command and a device name.
In this embodiment, the voice recognition may be performed by direct acoustic comparison or acoustic model comparison. The direct acoustic wave comparison method compares the voice request signal with the voice signal in the voice database 70 to obtain the most similar possible vocabulary (each vocabulary corresponds to a voice data), and the acoustic Model comparison method performs voice recognition through various acoustic models such as Hidden Markov Model (HMM), Neural Networks (Neural Networks), Dynamic Time Warping (DTW), or voice Template comparison (Template Matching). When the voice response module 130 performs voice recognition by using an acoustic model comparison method, the voice response module 130 may first extract a plurality of acoustic features (i.e., parameters such as Linear Predictive Cepstral Coefficient (LPCC), Mel Cepstral Coefficient (MFCC), MPEG7, Log Energy (Log Energy) and the like corresponding to the voice request signal) from the voice request signal, and then compare the acoustic features with one of the acoustic models to find a corresponding vocabulary (each vocabulary corresponds to a piece of voice data) that most matches the acoustic features. For example, when the voice request signal is "connect CDrive", the corresponding vocabulary obtained by the voice parsing by the voice question answering module 130 may be "connect CDrive".
The semantic recognition may be that the voice question and answer module 130 queries a category corresponding to the at least one voice data from the semantic database 60 according to the at least one voice data to obtain a control command corresponding to the at least one voice data, where the control command may include a connection command and a device name of the cloud storage device. Specifically, the phonetic question answering module 130 can query the semantic database 60 for a category corresponding to each vocabulary according to the corresponding vocabulary, wherein the category can be a behavior, a device or a file. More specifically, the semantic database 60 may record the relationship between words and corresponding categories (as shown in fig. 3, fig. 3 is an example comparison table of words and categories recorded by the semantic database in the artificial intelligence-based voice question-answering verification system of fig. 1), and each voice datum corresponds to one category (i.e., each word corresponds to one category). Since a complete control command may include an action class (i.e. the operation the speaker wants to perform) and a device class (i.e. the device the speaker wants to operate), therefore, the voice question-answering module 130 needs to query the semantic database 60 to determine whether the vocabulary obtained by parsing the voice request signal at least corresponds to a behavior category or a device category, and further to determine whether a complete control command has been collected, wherein the control command may have a specific format, which may include a connection command and a device name (as shown in FIG. 4A, FIG. 4A is an embodiment format of the control command in the artificial intelligence based voice question-answering verification system of FIG. 1), in practical applications, the device names and the connection commands may be ordered according to actual requirements, where the device names are used to represent the cloud storage devices to be operated, and the connection commands are used to represent operations to be performed by the speakers. For example, when the corresponding vocabulary obtained by the voice question-answering module 130 is "connection, CDrive", the voice question-answering module 130 may obtain the category corresponding to "connection" as "behavior" and the category corresponding to "CDrive" as "device" according to the semantic database 60, so the content of the control command may be as shown in fig. 4B, where fig. 4B is an embodiment of the control command in the artificial intelligence-based voice question-answering verification system of fig. 1, and fig. 4B shows that the speaker wants to "connect" to the cloud storage device, whose device name is "CDrive".
It should be noted that the vocabulary obtained by the voice question and answer module 130 may not be able to query the semantic database 60 for the corresponding category (i.e. the vocabulary cannot identify its category), but the comparison table of the vocabulary and the category recorded by the semantic database 60 can be updated at any time according to the requirement, wherein the vocabulary in the comparison table needs to include the device name of each cloud storage device and the category corresponding to the device name is "device". In addition, when the voice question-answering module 130 determines that the category corresponding to the vocabulary lacks a behavior category or a device category, or determines that the vocabulary corresponds to a plurality of behavior categories or a plurality of device categories, it is determined that the complete control command cannot be collected and the control command cannot be obtained.
The processing module 140 can be used to connect the cloud storage device corresponding to the device name according to the connection command. More specifically, when the processing module 140 receives the control instruction, it may execute an application program, so that the application program logs in the cloud storage device corresponding to the device name according to the connection command. For example, when the control instruction includes a device name "CDrive" and the connection command is "connect", the processing module 140 may execute the application program to "connect" the cloud storage device with the device name "CDrive".
In addition, in order to enhance the security management of the cloud storage device, when the time period of connecting the cloud storage device exceeds a predetermined time, the processing module 140 may request the user to input a voice maintaining signal in a voice manner or a manner displayed on the display device, so that the user responds to the voice maintaining signal in the voice input manner, wherein the voice maintaining signal may be, but is not limited to, a maintaining statement preset by the artificial intelligence based voice question-answer verification system 100 when the user recites, for example: the connection is maintained. When the receiving module 110 receives the voice maintaining signal, the feature recognition module 120 performs voiceprint recognition on the voice maintaining signal (i.e., determines whether the voice maintaining signal is a valid user, and the detailed description is described in the above paragraphs, which is not described herein), and after the voiceprint recognition verification is passed, the voice question and answer module 130 performs voice analysis on the voice maintaining signal (i.e., performs voice-to-text conversion), so that the processing module 140 determines whether to maintain connection with the cloud storage device according to the result of the voice analysis of the voice maintaining signal. Further, when the voice analysis result of the voice maintenance signal is different from the maintenance statement preset by the artificial intelligence based voice question-answer verification system 100, the processing module 140 determines that the cloud storage device is offline (i.e. not connected to the cloud storage device); when the voice analysis result of the voice maintenance signal is the same as the maintenance statement preset by the artificial intelligence based voice question-answer verification system 100, the processing module 140 determines to maintain the connection with the cloud storage device. The predetermined time may be, but is not limited to, ten minutes, and may be adjusted according to actual requirements. The embodiment can avoid the situation that files in the cloud storage device are stolen by others when a legal user leaves the seat.
In the present embodiment, the artificial intelligence based voice question-answer verification system 100 can add new legal users, as detailed below. The new user (i.e., the legitimate user to be added) may input the registration request signal by voice, and after the receiving module 110 receives the registration request signal, the processing module 140 may request the new user to input the voice registration signal by voice or by displaying the voice registration signal on the display device, so that the new user responds to the voice registration signal by voice input, wherein the voice registration signal may be a registration statement preset by the artificial intelligence based voice question-answer verification system 100 for the new user to read.
When the receiving module 110 receives the voice registration signal, the feature recognition module 120 performs feature analysis on the voice registration signal (i.e., converts the voice registration signal into a voiceprint, and then extracts feature parameters of the voiceprint), so as to obtain voice feature data (i.e., feature parameters of the voiceprint), so as to store and newly add preset voiceprint data in the voiceprint database 30, and then the voice question-answering module 130 performs voice question-asking one by one according to all the personal questions provided by the question database 40, and receives voice answer signals responding to each personal question one by one through the receiving module 110, so as to store and newly add new identification data in the question database 40 and store new identity data corresponding to the new preset voiceprint data in the voiceprint database 30. In the embodiment, the voice question-answering module 130 can perform voice analysis (i.e., perform voice-to-text) on each voice answer signal to obtain corresponding words, which are stored as answers to corresponding personal questions in the question database 40 and as identity data (i.e., identity certificate numbers) in the voiceprint database 30. In other words, in other embodiments, the voice answer signals except the identification data (i.e. identification number) corresponding to the voiceprint database 30 may be directly stored as answers responding to each individual question in the new identification data without performing voice analysis, and then compared in a sound wave manner when the comparison is to be performed.
In this embodiment, the voice question-answer verification system 100 based on artificial intelligence can also access the files in the cloud storage device through a voice control method, after the cloud storage device is connected, the user can input a voice access signal by the receiving module 110, and the voice access signal can include a file name (i.e., a name of any file stored in the connected cloud storage device), so that after the receiving module 110 receives the voice access signal, the voice question-answer module 130 can perform voice recognition and semantic recognition on the voice access signal, so that the processing module 140 correspondingly accesses the file corresponding to the file name in the connected cloud storage device according to the results of the voice recognition and the semantic recognition. For example, when the voice access signal is "read description", the corresponding vocabulary obtained by the voice parsing by the voice question-answering module 130 may be "read description", and then the category corresponding to "read" is "behavior" and the category corresponding to "description" is "file" according to the semantic database 60, so that the result of semantic recognition is that the user wants to "read" the file with the file name of "description", and therefore, the processing module 140 "reads" the file with the file name of "description" in the cloud storage device connected to the cloud storage device according to the result of voice recognition and semantic recognition.
In addition, in this embodiment, the processing module 140 may also record the number of times the file in the connected cloud storage device is accessed by the artificial intelligence based voice question-answering verification system 100 and the time of accessing the file each time in a storage module (not shown), if the processing module 140 determines that the number of times the file in the cloud storage device is accessed by the artificial intelligence based voice question-answering verification system 100 in a short time is too large, it may determine that the usage status is abnormal, and directly disconnect the file from the cloud storage device, or request the user to input a voice determination signal, so that the user inputs the voice determination signal by a voice input method, the feature identification module 120 may perform voiceprint identification on the voice determination signal (i.e. determine whether the voice determination signal is a legal user, which is described in the above paragraphs and is not described here again), so that the processing module 140 determines whether to maintain the connection with the cloud storage device according to the result of the voiceprint identification, and further enhance the security management of the cloud storage device. The processing module 140 determines how many times the files of the cloud storage device are accessed within a long time as the usage status is abnormal, and may be adjusted according to actual requirements, for example, the processing module 140 may determine that five times the files of the cloud storage device are accessed within ten minutes as the usage status is abnormal.
In this embodiment, each identification data may further store a record of the identification data contained therein connected to or disconnected from the cloud storage device and an access record of any file in the cloud storage device, where the records may include a time stamp (i.e., a time of connecting to or disconnecting from the cloud storage device and a time of accessing any file in the cloud storage device). Since the record of the user connected or disconnected to the cloud storage device or the record of accessing a certain file in the cloud storage device is the operation record of the user and is unknown to other users, when the voice question and answer module 130 randomly asks a question from the question database 40 for identification, in addition to randomly selecting a certain person question, the voice question and answer module 130 can ask the user the time of the previous connection or disconnection to the cloud storage device or the time of the previous access to a certain file in the cloud storage device for identification, when the voice question and answer module 130 asks the user the time of the previous connection or disconnection to the cloud storage device or the time of the previous access to a certain file in the cloud storage device, the voice question and answer module 130 compares the voice reply signal responding to the question with the access record of any file in the connection or disconnection to the cloud storage device or the access to the cloud storage device in the identification data corresponding to the user, when the comparison result is consistent, the user passes further identity verification (namely the speaker is confirmed to be a legal user); when the comparison result is not consistent, the user cannot pass further identification verification (i.e. the speaker is not a legal user), and cannot execute the subsequent program (i.e. cannot connect to the cloud storage device).
Next, referring to fig. 5, fig. 5 is a flowchart illustrating an embodiment of the artificial intelligence based voice question-answer verification system of fig. 1 executing an artificial intelligence based voice question-answer verification method, which includes the steps of: receiving a voice request signal (step 210); performing feature analysis on the voice request signal to obtain voice feature data, and comparing the voice feature data with a plurality of preset voiceprint data (step 220); when the voice feature data is determined to be consistent with one of the preset voiceprint data, generating a confirmation signal and acquiring identity data (step 230); randomly selecting a person question from the question database for voice questioning when the confirmation signal is generated (step 240); receiving back a voice reply signal for the personal question (step 250); comparing the voice reply signal corresponding to the personal question with the answer of the identity data corresponding to the personal question in the identity recognition database (step 260); when the voice reply signal matches the answer of the identity data in the identity recognition database to the personal question, performing voice recognition and semantic recognition on the voice request signal to obtain a control command, wherein the control command comprises a connection command and a device name (step 270); connecting the cloud storage device corresponding to the device name according to the connection command (step 280); when the time for connecting the cloud storage device exceeds a preset time, requesting to input a voice maintaining signal (step 290); after receiving the voice maintaining signal, performing voiceprint recognition on the voice maintaining signal (step 292); after the voiceprint recognition verification is passed, performing voice analysis on the voice maintaining signal (step 294); and determining whether to maintain connection with the cloud storage device according to a voice analysis result of the voice maintaining signal (step 296).
The voice print database can be used for storing a plurality of identity data and a plurality of preset voice print data, and the identity data corresponds to the preset voice print data in a one-to-one mode; the question database can be used for storing a question template, and the question template comprises a plurality of personal questions; the identity identification database can be used for storing a plurality of identity identification data, each identity identification data comprises certain identity data, the personal question and an answer responded to each personal question, and in addition, each identity identification data also stores the record of the identity data connection or off-line cloud storage device contained in the identity identification data and the access record of any file in the access cloud storage device.
Through the steps, the identity of the user can be verified through voiceprint recognition and random voice question answering, and when the identity of the user passes verification, the specified cloud storage device can be connected, so that the technical effect of improving the safety of identity verification is achieved. In addition, when the time for connecting the cloud storage device exceeds the preset time, the voice maintaining signal can be requested to be input, the received voice maintaining signal is subjected to voice analysis, and whether the connection with the cloud storage device is maintained or not is further judged so as to enhance the safety management of the cloud storage device.
Referring to fig. 6, fig. 6 is a flowchart illustrating an embodiment of a method for adding a valid user to the artificial intelligence based voice question-answer verification system of fig. 1, including the steps of: requesting to input a voice registration signal when receiving a registration request signal (step 310); after receiving the voice registration signal, performing feature analysis on the voice registration signal to store and newly add preset voiceprint data in a voiceprint database (step 320); and performing voice question one by one according to all the personal questions provided by the question database and receiving a voice answer signal responding to each personal question one by one, so as to store and add new identification data in the question database and store new identification data corresponding to the new preset voiceprint data in the voiceprint database (step 330). The detailed description is already described in the above paragraphs, and will not be repeated herein.
In addition, referring to fig. 7, fig. 7 is a flowchart illustrating an embodiment of a method for enhancing security management of a cloud storage device by the artificial intelligence-based voice question-answer verification system of fig. 1, including the steps of: when the voice analysis result of the voice maintaining signal is different from the preset maintaining statement, judging that the connection with the cloud storage device is not maintained (step 410); and when the voice analysis result of the voice maintaining signal is the same as the preset maintaining statement, determining to maintain the connection with the cloud storage device (step 420). In addition, in this embodiment, when the processing module determines that the number of times of accessing the file of the cloud storage device by the artificial intelligence-based voice question-answering verification system in a short time is too many, it may be determined that the usage status is abnormal, and the file is directly disconnected from the cloud storage device, or the user is requested to input a voice determination signal, so that the user inputs the voice determination signal by a voice input method, and the feature recognition module may perform voiceprint recognition on the voice determination signal (i.e., determine whether the voice determination signal is a valid user, which is described in the above paragraphs, and is not described herein again), so that the processing module determines whether the voice determination signal is connected to the cloud storage device according to the result of the voiceprint recognition, and further enhances the security management of the cloud storage device. The detailed description is already described in the above paragraphs, and will not be repeated herein.
Referring to fig. 8, fig. 8 is a flowchart illustrating an embodiment of a method for performing file access of a cloud storage device in a voice control manner by the artificial intelligence based voice question-answer verification system of fig. 1, including the steps of: after connecting the cloud storage device, receiving a voice access signal, wherein the voice access signal includes a file name (step 510); and performing voice recognition and semantic recognition on the voice access signal, and correspondingly accessing the file corresponding to the file name in the connected cloud storage device according to the voice recognition and semantic recognition results of the voice access signal (step 520). The detailed description is already described in the above paragraphs, and will not be repeated herein.
In summary, it can be seen that the difference between the present invention and the prior art is that the voice request signal is voice-print verified by the feature recognition module to generate the confirmation signal and obtain some identity data, then the voice question-answering module randomly selects a certain person question from the question database to carry out voice question-answering, and comparing the voice reply signal responding to the personal question with the answer responded by the identity data aiming at the personal question, when the voice analysis result is matched with the answer, performing voice recognition and semantic recognition on the voice request signal to obtain a control command including a connection command and a device name, the processing module is connected with the cloud storage device corresponding to the device name according to the connection command, and the technical means can solve the problems in the prior art, so that the technical effect of improving the safety of identity verification is achieved. In addition, when the time for connecting the cloud storage device exceeds the preset time, voice analysis is carried out according to the received voice maintaining signal, and whether the connection with the cloud storage device is maintained or not is further judged, so that the safety management of the cloud storage device is enhanced.
Although the present invention has been described with reference to the foregoing embodiments, it should be understood that various changes and modifications can be made therein by those skilled in the art without departing from the spirit and scope of the invention.
Claims (10)
1. An artificial intelligence based voice question-answer verification system, comprising:
the voice print database is used for storing a plurality of identity data and a plurality of preset voice print data, and the identity data corresponds to the preset voice print data in a one-to-one mode;
a question database for storing a question template, the question template comprising a plurality of individual questions;
an identity identification database for storing a plurality of identity identification data, each of which comprises a certain identity data, the personal question and an answer responding to each of the personal questions;
the receiving module is used for receiving the voice request signal and the voice reply signal;
the characteristic identification module is used for carrying out characteristic analysis on the voice request signal to obtain voice characteristic data, comparing the voice characteristic data with the preset voiceprint data, and generating a confirmation signal and obtaining a certain corresponding identity identification data when the voice characteristic data is consistent with one of the preset voiceprint data;
a voice question-answering module for randomly selecting a certain personal question from the question database to perform voice question-asking when the feature recognition module generates the confirmation signal, comparing the voice reply signal corresponding to the personal question with the answer of the identity recognition data obtained by the feature recognition module and responded by the personal question, and performing voice recognition and semantic recognition on the voice request signal to obtain a control instruction when the voice reply signal matches the answer of the identity recognition data obtained by the feature recognition module and responded by the personal question, wherein the control instruction comprises a connection command and a device name; and
the processing module is used for connecting the cloud storage device corresponding to the device name according to the connection command;
when the time for connecting the cloud storage device exceeds the preset time, the processing module requests to input a voice maintaining signal, the receiving module receives the voice maintaining signal, the feature recognition module performs voiceprint recognition on the voice maintaining signal, and after the voiceprint recognition and verification pass, the voice question and answer module performs voice analysis on the voice maintaining signal, so that the processing module judges whether to maintain the connection with the cloud storage device according to the voice analysis result of the voice maintaining signal.
2. The system of claim 1, wherein the processing module requests to input a voice registration signal after the receiving module receives the registration request signal, and the receiving module receives the voice registration signal, such that the feature recognition module performs feature analysis on the voice registration signal to add new preset voiceprint data in the voiceprint database, and then the voice question-answering module performs voice question-asking one by one according to all the personal questions provided by the question database, and receives a voice answer signal responding to each of the personal questions one by one through the receiving module, so as to add new identification data in the question database and store new identification data corresponding to the new preset voiceprint data in the voiceprint database.
3. The system according to claim 1, wherein each of the identification data further stores a record of the identification data contained therein connected to or offline from the cloud storage device and an access record of any file stored in the cloud storage device.
4. The system according to claim 1, wherein when the voice analysis result of the voice maintaining signal is different from a preset maintaining statement, the processing module determines not to maintain connection with the cloud storage device; when the voice analysis result of the voice maintaining signal is the same as the preset maintaining statement, the processing module judges that the connection with the cloud storage device is maintained.
5. The system according to claim 1, wherein the receiving module receives a voice access signal after connecting to the cloud storage device, the voice access signal including a file name, and the voice question-answering module performs voice recognition and semantic recognition on the voice access signal, so that the processing module accesses the file corresponding to the file name in the connected cloud storage device according to the result of the voice recognition and the semantic recognition.
6. A voice question-answer verification method based on artificial intelligence comprises the following steps:
receiving a voice request signal;
carrying out feature analysis on the voice request signal to obtain voice feature data, and comparing the voice feature data with a plurality of preset voiceprint data;
when the voice characteristic data is judged to be consistent with one of the preset voiceprint data, generating a confirmation signal and acquiring identity data;
randomly selecting a personal question from a question database for voice questioning when the confirmation signal is generated;
receiving back a voice reply signal corresponding to the personal question;
comparing the voice reply signal corresponding to the personal question with the answer responded by the identification data in the identification database corresponding to the personal question;
when the voice reply signal is matched with the answer of the identification data in the identification database, which is responded to the personal question, the voice request signal is subjected to voice identification and semantic identification to obtain a control instruction, wherein the control instruction comprises a connection command and a device name;
connecting the cloud storage device corresponding to the device name according to the connection command;
when the time for connecting the cloud storage device exceeds a preset time, requesting to input a voice maintaining signal;
after receiving the voice maintaining signal, carrying out voiceprint recognition on the voice maintaining signal;
after the voiceprint identification verification is passed, carrying out voice analysis on the voice maintaining signal; and
and judging whether to maintain connection with the cloud storage device or not according to the voice analysis result of the voice maintaining signal.
7. The artificial intelligence based voice question-answer verification method according to claim 6, characterized in that the artificial intelligence based voice question-answer verification method further comprises:
requesting to input a voice registration signal after receiving a registration request signal;
after receiving the voice registration signal, performing feature analysis on the voice registration signal to add new preset voiceprint data in the voiceprint database; and
according to all the personal questions provided by the question database, voice asking is carried out one by one, and voice answer signals responding to each personal question are received one by one, so that new identification data is added to the question database, and new identification data corresponding to the new preset voiceprint data is stored in the voiceprint database.
8. The artificial intelligence-based voice question-answer verification method according to claim 6, wherein each of the identity recognition data further stores records of the identity data contained therein connected or disconnected to the cloud storage device and access records of any file stored in the cloud storage device.
9. The artificial intelligence based voice question-answer verification method according to claim 6, characterized in that the artificial intelligence based voice question-answer verification method further comprises:
when the voice analysis result of the voice maintaining signal is different from a preset maintaining statement, judging that the voice maintaining signal is not connected with the cloud storage device; and
and when the voice analysis result of the voice maintaining signal is the same as the preset maintaining statement, judging that the voice maintaining signal is connected with the cloud storage device.
10. The artificial intelligence based voice question-answer verification method according to claim 6, characterized in that the artificial intelligence based voice question-answer verification method further comprises:
after the cloud storage device is connected, receiving a voice access signal, wherein the voice access signal comprises a file name; and
and performing voice identification and semantic identification on the voice access signal, and correspondingly accessing the file corresponding to the file name in the cloud storage device according to the voice identification and semantic identification results of the voice access signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810588018.6A CN109003612B (en) | 2018-06-08 | 2018-06-08 | Voice question-answer verification system and method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810588018.6A CN109003612B (en) | 2018-06-08 | 2018-06-08 | Voice question-answer verification system and method based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109003612A CN109003612A (en) | 2018-12-14 |
| CN109003612B true CN109003612B (en) | 2021-01-29 |
Family
ID=64601051
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810588018.6A Active CN109003612B (en) | 2018-06-08 | 2018-06-08 | Voice question-answer verification system and method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109003612B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220139402A1 (en) * | 2019-02-18 | 2022-05-05 | Nec Corporation | Voice authentication apparatus, voice authentication method, and a recording medium |
| CN113284494B (en) * | 2021-05-25 | 2023-12-01 | 北京基智科技有限公司 | Voice assistant recognition method, device, equipment and computer readable storage medium |
| CN115952482B (en) * | 2023-03-13 | 2023-05-30 | 山东博奥克生物科技有限公司 | Medical equipment data management system and method |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10271204A (en) * | 1997-03-21 | 1998-10-09 | Hitachi Vlsi Eng Corp | Automatic answering device and telephone set provided with automatic answering function |
| JP2000330589A (en) * | 1999-05-19 | 2000-11-30 | Nec Corp | System for identifying person himself and its method |
| JP2001274907A (en) * | 2000-03-24 | 2001-10-05 | Nec Shizuoka Ltd | Caller recognition system and method |
| CN101441869A (en) * | 2007-11-21 | 2009-05-27 | 联想(北京)有限公司 | Method and terminal for speech recognition of terminal user identification |
| CN101494662A (en) * | 2008-01-24 | 2009-07-29 | 通用汽车公司 | Method and system for enhancing telematics services |
| CN101685635A (en) * | 2008-09-23 | 2010-03-31 | 吕共欣 | Identity authentication system and method |
| CN102402985A (en) * | 2010-09-14 | 2012-04-04 | 盛乐信息技术（上海）有限公司 | Voiceprint authentication system for improving voiceprint identification safety and method for realizing the same |
| CN102737634A (en) * | 2012-05-29 | 2012-10-17 | 百度在线网络技术（北京）有限公司 | Authentication method and device based on voice |
| CN103078828A (en) * | 2011-10-25 | 2013-05-01 | 上海博路信息技术有限公司 | Cloud-model voice authentication system |
| CN103119644A (en) * | 2010-07-23 | 2013-05-22 | 奥尔德巴伦机器人公司 | Humanoid robot equipped with a natural dialogue interface, method for controlling the robot and corresponding program |
| CN104217149A (en) * | 2013-05-31 | 2014-12-17 | 国际商业机器公司 | Biometric authentication method and equipment based on voice |
| CN104715371A (en) * | 2013-12-16 | 2015-06-17 | 黄金富知识产权咨询(深圳)有限公司 | Safe payment method adopting voiceprint to identify identity and corresponding system |
| CN105138882A (en) * | 2015-07-30 | 2015-12-09 | 广东欧珀移动通信有限公司 | Terminal unlocking method and apparatus |
| CN107689095A (en) * | 2017-08-25 | 2018-02-13 | 遵义博文软件开发有限公司 | Vocal print code question and answer gate inhibition |
-
2018
- 2018-06-08 CN CN201810588018.6A patent/CN109003612B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10271204A (en) * | 1997-03-21 | 1998-10-09 | Hitachi Vlsi Eng Corp | Automatic answering device and telephone set provided with automatic answering function |
| JP2000330589A (en) * | 1999-05-19 | 2000-11-30 | Nec Corp | System for identifying person himself and its method |
| JP2001274907A (en) * | 2000-03-24 | 2001-10-05 | Nec Shizuoka Ltd | Caller recognition system and method |
| CN101441869A (en) * | 2007-11-21 | 2009-05-27 | 联想(北京)有限公司 | Method and terminal for speech recognition of terminal user identification |
| CN101494662A (en) * | 2008-01-24 | 2009-07-29 | 通用汽车公司 | Method and system for enhancing telematics services |
| CN101685635A (en) * | 2008-09-23 | 2010-03-31 | 吕共欣 | Identity authentication system and method |
| CN103119644A (en) * | 2010-07-23 | 2013-05-22 | 奥尔德巴伦机器人公司 | Humanoid robot equipped with a natural dialogue interface, method for controlling the robot and corresponding program |
| CN102402985A (en) * | 2010-09-14 | 2012-04-04 | 盛乐信息技术（上海）有限公司 | Voiceprint authentication system for improving voiceprint identification safety and method for realizing the same |
| CN103078828A (en) * | 2011-10-25 | 2013-05-01 | 上海博路信息技术有限公司 | Cloud-model voice authentication system |
| CN102737634A (en) * | 2012-05-29 | 2012-10-17 | 百度在线网络技术（北京）有限公司 | Authentication method and device based on voice |
| CN104217149A (en) * | 2013-05-31 | 2014-12-17 | 国际商业机器公司 | Biometric authentication method and equipment based on voice |
| CN104715371A (en) * | 2013-12-16 | 2015-06-17 | 黄金富知识产权咨询(深圳)有限公司 | Safe payment method adopting voiceprint to identify identity and corresponding system |
| CN105138882A (en) * | 2015-07-30 | 2015-12-09 | 广东欧珀移动通信有限公司 | Terminal unlocking method and apparatus |
| CN107689095A (en) * | 2017-08-25 | 2018-02-13 | 遵义博文软件开发有限公司 | Vocal print code question and answer gate inhibition |
Non-Patent Citations (2)
| Title |
|---|
| Searching Multimedia Content with a Spontaneous Conversational Speech Track;Martha Larson等;《proceedings of the 17th International Conference on Multimedia 2009》;20091024;全文 * |
| 基于MFCC相似度和谱熵的端点检测算法;邓瑞等;《现代电子技术》;20131101;第36卷(第21期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109003612A (en) | 2018-12-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2016216737B2 (en) | Voice Authentication and Speech Recognition System | |
| US20160372116A1 (en) | Voice authentication and speech recognition system and method | |
| CA2088080C (en) | Automatic speech recognizer | |
| US7447632B2 (en) | Voice authentication system | |
| KR101963993B1 (en) | Identification system and method with self-learning function based on dynamic password voice | |
| US8630391B2 (en) | Voice authentication system and method using a removable voice ID card | |
| WO2016092807A1 (en) | Speaker identification device and method for registering features of registered speech for identifying speaker | |
| US6477500B2 (en) | Text independent speaker recognition with simultaneous speech recognition for transparent command ambiguity resolution and continuous access control | |
| CA2189011C (en) | Method for reducing database requirements for speech recognition systems | |
| CN109003612B (en) | Voice question-answer verification system and method based on artificial intelligence | |
| CN104462912B (en) | Improved biometric password security | |
| JPH1173195A (en) | Method for authenticating speaker's proposed identification | |
| US6629069B1 (en) | Speech recognizer using database linking | |
| KR100442308B1 (en) | Method and system for enrolling addresses in a speech recognition database | |
| KR20140076056A (en) | Voice based CAPTCHA method and voice based CAPTCHA apparatus | |
| JPH10173644A (en) | Identity authentication method | |
| JPH1173196A (en) | Method for authenticating speaker's proposed identification | |
| WO2022236386A1 (en) | Access control system | |
| US7289957B1 (en) | Verifying a speaker using random combinations of speaker's previously-supplied syllable units | |
| CN112565242B (en) | Remote authorization method, system, equipment and storage medium based on voiceprint recognition | |
| CN111261172B (en) | Voiceprint recognition method and device | |
| JP4245948B2 (en) | Voice authentication apparatus, voice authentication method, and voice authentication program | |
| CN110931020B (en) | Voice detection method and device | |
| TW202001659A (en) | Voice question-answer verification system based on artificial intelligence and method thereof | |
| WO2006027844A1 (en) | Speaker collator |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |