WO2021189903A1 - 基于音频的用户状态识别方法、装置、电子设备及存储介质 - Google Patents
基于音频的用户状态识别方法、装置、电子设备及存储介质 Download PDFInfo
- Publication number
- WO2021189903A1 WO2021189903A1 PCT/CN2020/131983 CN2020131983W WO2021189903A1 WO 2021189903 A1 WO2021189903 A1 WO 2021189903A1 CN 2020131983 W CN2020131983 W CN 2020131983W WO 2021189903 A1 WO2021189903 A1 WO 2021189903A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- audio
- target
- spectrogram
- voice signal
- training
- 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.)
- Ceased
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
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
-
- 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
- G10L15/00—Speech recognition
- G10L15/20—Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech
-
- 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
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
- G10L25/18—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being spectral information of each sub-band
-
- 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
Definitions
- This application relates to the field of artificial intelligence, and in particular to an audio-based user state recognition method, device, electronic equipment, and storage medium.
- An audio-based user state recognition method provided in this application includes:
- the user state recognition model is used to recognize the to-be-recognized spectrogram to obtain a user state recognition result.
- the present application also provides an audio-based user state recognition device, which includes:
- the model generation module is used to obtain an audio training set, perform feature conversion on each audio in the audio training set to obtain a target spectrogram atlas; based on the attention mechanism and small sample learning, use the target spectrogram atlas to
- the pre-built deep learning network model is trained to obtain the user state recognition model;
- the state recognition module is used to perform feature conversion on the audio of the user to be recognized when the audio of the user to be recognized is received to obtain the spectrogram to be recognized; use the user state recognition model to perform the feature conversion on the spectrogram to be recognized Recognize and get the result of user status recognition.
- This application also provides an electronic device, which includes:
- Memory storing at least one instruction
- the processor executes the instructions stored in the memory to implement the following steps:
- the user state recognition model is used to recognize the to-be-recognized spectrogram to obtain a user state recognition result.
- the present application also provides a computer-readable storage medium in which at least one instruction is stored, and when the at least one instruction is executed by a processor in an electronic device, the following steps are implemented:
- the user state recognition model is used to recognize the to-be-recognized spectrogram to obtain a user state recognition result.
- FIG. 1 is a schematic flowchart of an audio-based user state recognition method provided by an embodiment of this application
- FIG. 2 is a schematic diagram of a detailed process of obtaining a target spectrogram set in an audio-based user state recognition method provided by an embodiment of the application;
- FIG. 3 is a schematic diagram of modules of an audio-based user state recognition device provided by an embodiment of the application.
- FIG. 4 is a schematic diagram of the internal structure of an electronic device that implements an audio-based user state recognition method provided by an embodiment of the application;
- This application provides an audio-based user status recognition method.
- FIG. 1 it is a schematic flowchart of an audio-based user state recognition method provided by an embodiment of this application.
- the method can be executed by a device, and the device can be implemented by software and/or hardware.
- the audio-based user state recognition method includes:
- the audio training set is a collection of audios containing initial tags.
- the initial tags are the user's disease conditions, such as acute bronchitis, chronic pharyngitis, pertussis, fever; further, Since the user's cough audio has corresponding sound features under different disease conditions, preferably, the audio training set is a collection of cough audio corresponding to different disease conditions, wherein the sound feature is the frequency domain of the cough audio
- the characteristics can be represented by a spectrogram.
- the embodiment of the present application performs feature transformation on the audio training set to obtain the target spectrogram atlas, including:
- each audio in the audio training set is resampled to obtain the corresponding digital voice signal.
- the present application uses a digital-to-analog converter to resample each audio in the audio training set.
- a pre-emphasis operation is performed on each audio in the audio training set
- the performing the pre-emphasis operation on each audio in the audio training set includes: re-sampling each audio in the audio training set to obtain the corresponding digital voice signal;
- the digital voice signal is pre-emphasized to obtain a standard digital voice signal, and all the standard digital voice signals are summarized to obtain a voice signal set.
- x(t) is the digital voice signal
- t is the time
- y(t) is the standard digital voice signal
- ⁇ is the preset adjustment value of the pre-emphasis operation, preferably, the value of ⁇
- the range is [0.9,1.0].
- the standard voice signal in the voice signal set can only reflect the change of audio in the time domain, and cannot reflect the audio characteristics of the standard voice signal.
- the audio is more intuitive and clear, and feature conversion is performed on each standard digital voice signal in the voice signal set.
- performing feature conversion on each standard digital voice signal in the voice signal set includes: using a preset sound processing algorithm to map each standard digital voice signal in the voice signal set on a frequency Domain, the corresponding target spectrogram is obtained, and all the target spectrograms are summarized to obtain the target spectrogram set.
- the sound processing algorithm described in this application is the Mel filter algorithm.
- the above steps only perform feature conversion on each audio of the audio training set, and will not affect the initial label corresponding to each audio of the audio training set, so the target spectrogram is set Each target spectrogram has a corresponding initial label.
- the target spectrogram atlas is used to pre-build
- the deep learning network model is trained to obtain an audio-based user state recognition model.
- the training of the pre-built deep learning network model by using the target spectrogram atlas includes:
- Step A The target spectrogram set is divided into a training set and a test set;
- the target spectrogram set is divided into a training set and a test set, and the robustness of the model is enhanced by continuously testing the training model by using the test set, and dividing the target spectrogram set into a training set And a test set, including: classifying each target spectrogram in the target spectrogram atlas according to the corresponding initial label to obtain the corresponding classification target spectrogram atlas; randomly taking out from the classification target spectrogram atlas A preset number of target spectrograms are used as the test subset, and the complement of the training subset in the classified spectrogram set is used as the training subset; all the training sets of the training subset are summarized, and all the training sets are summarized.
- the test subset obtains
- Step B Use the training set to train the deep learning network to obtain an initial recognition model, test the initial recognition model according to the test set to obtain a loss value, and return to step when the loss value is greater than a preset threshold A.
- the loss value is less than or equal to a preset threshold, the initial recognition model is used as the user state recognition model.
- the deep learning network in the embodiment of the present application is a convolutional neural network.
- the size of the images in the target spectrogram atlas may be different, which in turn leads to the target extracted by the deep learning network model during the training process.
- the target spectrograms in the spectrogram set have different feature dimensions and cannot be uniformly trained.
- the embodiment of the present application uses the training set to compare the pre-deep learning network , It is necessary to add an attention mechanism processing layer before the fully connected layer of the deep learning network model to perform image feature alignment, where the attention mechanism processing layer performs a feature alignment network according to different image feature dimensions, for example: target sound spectrum
- the image feature a of the feature extraction performed on the deep learning network model in Figure A is a D*T1 dimensional matrix
- the image feature b of the target spectrogram B that is feature extraction performed on the deep learning network model is a D*T2 dimensional matrix
- the attention mechanism processing layer converts the preset weight matrix of image feature a multiplied by T1*1 into a D-dimensional matrix, and converts the preset weight matrix of image feature b multiplied by T2*1 into a D-dimensional matrix to realize the image Feature a and image feature b are aligned.
- the embodiment of the present application needs to perform the initial recognition model to verify the recognition ability of the model to facilitate the training and adjustment of the model.
- the recognition category of the initial recognition model in the embodiment of the present application is the same as the category of the initial tags in the target spectrogram atlas.
- the recognition categories in the initial recognition model also have the same two types: chronic pharyngitis and fever.
- testing the initial recognition model according to the test set to obtain a loss value includes: extracting a feature vector corresponding to each of the initial tags in the initial recognition model to obtain a target feature Vector; use the initial recognition model to perform feature extraction on each target spectrogram in the test subset to obtain a test feature vector; calculate the target feature vector and the test feature vector corresponding to each of the initial tags Calculate the average value of all the loss distance values to obtain the loss value.
- the embodiment of the present application adopts an Euclidean distance calculation method to calculate the distance between the target feature vector corresponding to each of the initial tags and the test feature vector.
- the different recognition types of the initial model correspond to different fully connected layer nodes, and the fully connected layer nodes have corresponding sequences.
- the embodiment of the present application obtains the full range corresponding to each recognition type of the initial recognition model.
- the output values of the connection layer nodes are combined in the order of the corresponding fully connected layer nodes to obtain the corresponding target feature vector; further, in the embodiment of the present application, each target spectrogram in the test subset is input to the office
- the initial recognition model according to the initial label corresponding to each target spectrogram in the test subset, the output value of the fully connected layer node corresponding to the recognition category in the initial recognition model is obtained, and the output value of the fully connected layer node is obtained according to the corresponding fully connected layer node. Combine sequentially to obtain the test feature vector.
- the audio training set may be stored in a blockchain node.
- the audio of the user to be identified is of the same category as the audio in the audio training set.
- the audio of the user to be identified is the user's cough audio. Audio training set
- the method for performing feature conversion on the audio of the user to be identified in the embodiment of the present application is the same as the above-mentioned method for performing feature conversion on each audio of the audio training set.
- the user status recognition result is the user's health status, such as acute bronchitis, chronic pharyngitis, pertussis, and fever.
- feature conversion is performed on each audio in the audio training set to obtain the target spectrogram atlas, so that the features in the audio in the audio training set are clearer and more intuitive, and the accuracy of subsequent model training is increased; Attention mechanism and small sample learning, using the target spectrogram atlas to train a pre-built deep learning network model to obtain a user state recognition model, which enhances the robustness and training accuracy of the model under the small sample training set; Perform feature conversion on the audio of the user to be identified to obtain the spectrogram to be identified, so that the audio features of the user to be identified are more clear and intuitive, and the recognition accuracy of the subsequent model is improved; The to-be-recognized spectrogram is recognized, and the user state recognition result is obtained. A small amount of more easily available audio data is used to train the model, which reduces the data resource consumption of the model training. Only the user's audio can be used to recognize the user state. Enhance the practicality of the model.
- FIG. 3 it is a functional block diagram of the audio-based user state recognition device of the present application.
- the audio-based user state recognition apparatus 100 described in this application can be installed in an electronic device.
- the audio-based user state recognition device may include a model generation module 101 and a state recognition module 102.
- the module described in the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can complete fixed functions, and are stored in the memory of the electronic device.
- each module/unit is as follows:
- the model generation module 101 is used to obtain an audio training set, perform feature conversion on each audio in the audio training set to obtain a target spectrogram set; based on the attention mechanism and small sample learning, use the target spectrogram Set to train the pre-built deep learning network model to obtain the user state recognition model.
- the audio training set is a collection of audios containing initial tags.
- the initial tags are the user's disease conditions, such as acute bronchitis, chronic pharyngitis, pertussis, fever; further, Since the user's cough audio has corresponding sound features under different disease conditions, preferably, the audio training set is a collection of cough audio corresponding to different disease conditions, wherein the sound feature is the frequency domain of the cough audio
- the characteristics can be represented by a spectrogram.
- the model generation module 101 in this embodiment of the present application uses the following means to perform feature transformation on the audio training set to obtain the Target sound spectrum atlas, including:
- each audio in the audio training set is resampled to obtain the corresponding digital voice signal.
- the present application uses a digital-to-analog converter to resample each audio in the audio training set.
- a pre-emphasis operation is performed on each audio in the audio training set
- the pre-emphasis operation on each audio in the audio training set includes: re-sampling each audio in the audio training set to obtain the corresponding digital voice signal;
- the digital voice signal is pre-emphasized to obtain a standard digital voice signal, and all the standard digital voice signals are summarized to obtain a voice signal set.
- model generation module 101 uses the following formula to perform the pre-emphasis operation:
- x(t) is the digital voice signal
- t is the time
- y(t) is the standard digital voice signal
- ⁇ is the preset adjustment value of the pre-emphasis operation, preferably, the value of ⁇
- the range is [0.9,1.0].
- the standard voice signal in the voice signal set can only reflect the change of audio in the time domain, and cannot reflect the audio characteristics of the standard voice signal.
- the audio is more intuitive and clear, and feature conversion is performed on each standard digital voice signal in the voice signal set.
- the model generation module 101 in the embodiment of the present application uses the following means to perform feature conversion on each standard digital voice signal in the voice signal set, including: using a preset voice processing algorithm to concentrate the voice signal Each standard digital speech signal is mapped in the frequency domain to obtain a corresponding target spectrogram, and all the target spectrograms are summarized to obtain the target spectrogram set.
- the sound processing algorithm described in this application is the Mel filter algorithm.
- the above steps only perform feature conversion on each audio of the audio training set, and will not affect the initial label corresponding to each audio of the audio training set, so the target spectrogram is set Each target spectrogram has a corresponding initial label.
- the target spectrogram atlas is used to pre-build
- the deep learning network model is trained to obtain an audio-based user state recognition model.
- the model generation module 101 uses the following methods to train the pre-built deep learning network model, including:
- Step A The target spectrogram set is divided into a training set and a test set;
- the target spectrogram set is divided into a training set and a test set, and the robustness of the model is enhanced by continuously testing the training model by using the test set, and dividing the target spectrogram set into a training set
- the test set including: classifying each target spectrogram in the target spectrogram atlas according to the corresponding initial label to obtain the corresponding classification target spectrogram atlas; randomly taking out from the classification target spectrogram atlas
- a preset number of target spectrograms are used as the test subset, and the complement of the training subset in the classified spectrogram set is used as the training subset; all the training sets of the training subset are summarized, and all the training sets are summarized.
- the test subset obtains a
- Step B Use the training set to train the deep learning network to obtain an initial recognition model, test the initial recognition model according to the test set to obtain a loss value, and return to step when the loss value is greater than a preset threshold A.
- the loss value is less than or equal to a preset threshold, the initial recognition model is used as the user state recognition model.
- the deep learning network in the embodiment of the present application is a convolutional neural network.
- the size of the images in the target spectrogram atlas may be different, which in turn leads to the target extracted by the deep learning network model during the training process.
- the target spectrograms in the spectrogram set have different feature dimensions and cannot be uniformly trained.
- the embodiment of the present application uses the training set to compare the pre-deep learning network , It is necessary to add an attention mechanism processing layer before the fully connected layer of the deep learning network model to perform image feature alignment, where the attention mechanism processing layer performs a feature alignment network according to different image feature dimensions, for example: target sound spectrum
- the image feature a of the feature extraction performed on the deep learning network model in Figure A is a D*T1 dimensional matrix
- the image feature b of the target spectrogram B that is feature extraction performed on the deep learning network model is a D*T2 dimensional matrix
- the attention mechanism processing layer converts the preset weight matrix of image feature a multiplied by T1*1 into a D-dimensional matrix, and converts the preset weight matrix of image feature b multiplied by T2*1 into a D-dimensional matrix to realize the image Feature a and image feature b are aligned.
- the embodiment of the present application needs to perform the initial recognition model to verify the recognition ability of the model to facilitate the training and adjustment of the model.
- the recognition category of the initial recognition model in the embodiment of the present application is the same as the category of the initial tags in the target spectrogram atlas.
- the recognition categories in the initial recognition model also have the same two types: chronic pharyngitis and fever.
- the model generation module 101 in the embodiment of the present application obtains the loss value by the following means, including: extracting the feature vector corresponding to each of the initial tags in the initial recognition model to obtain the target feature vector;
- the recognition model performs feature extraction on each target spectrogram in the test subset to obtain a test feature vector; calculates the distance between the target feature vector corresponding to each initial tag and the test feature vector to obtain the loss distance Value; Calculate the average of all the loss distance values to obtain the loss value.
- the embodiment of the present application adopts an Euclidean distance calculation method to calculate the distance between the target feature vector corresponding to each of the initial tags and the test feature vector.
- the model generation module 101 described in this embodiment of the application obtains each of the initial recognition models.
- the output values of the fully connected layer nodes corresponding to the recognition category are combined according to the order of the corresponding fully connected layer nodes to obtain the corresponding target feature vector; further, the model generation module 101 described in the embodiment of the present application combines the Each target spectrogram in the test subset is input to the initial recognition model, and the fully connected layer node corresponding to the recognition category in the initial recognition model is obtained according to the initial label corresponding to each target spectrogram in the test subset The output values of are combined according to the order of the corresponding fully connected layer nodes to obtain the test feature vector.
- the audio training set may be stored in a blockchain node.
- the state recognition module 102 is configured to, when receiving the audio of the user to be recognized, perform feature conversion on the audio of the user to be recognized to obtain the spectrogram to be recognized; The spectrum is identified, and the user status identification result is obtained.
- the audio of the user to be identified is of the same category as the audio in the audio training set.
- the audio of the user to be identified is the user's cough audio. Audio training set
- the method for performing feature conversion on the audio of the user to be identified in the embodiment of the present application is the same as the above-mentioned method for performing feature conversion on each audio of the audio training set.
- the user status recognition result is the user's disease condition, such as acute bronchitis, chronic pharyngitis, whooping cough, and fever.
- FIG. 44 it is a schematic structural diagram of an electronic device that implements an audio-based user state recognition method according to the present application.
- the electronic device 1 may include a processor 10, a memory 11, and a bus, and may also include a computer program stored in the memory 11 and running on the processor 10, such as an audio-based user state recognition program.
- the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, magnetic disk, CD etc.
- the memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, for example, a mobile hard disk of the electronic device 1.
- the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), and a secure digital (Secure Digital) equipped on the electronic device 1.
- the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device.
- the memory 11 can be used not only to store application software and various data installed in the electronic device 1, such as the code of an audio-based user status recognition program, etc., but also to temporarily store data that has been output or will be output.
- the processor 10 may be composed of integrated circuits in some embodiments, for example, may be composed of a single packaged integrated circuit, or may be composed of multiple integrated circuits with the same function or different functions, including one or more Combinations of central processing unit (CPU), microprocessor, digital processing chip, graphics processor, and various control chips, etc.
- the processor 10 is the control core of the electronic device (Control Unit), using various interfaces and lines to connect the various components of the entire electronic device, by running or executing programs or modules stored in the memory 11 (for example, audio-based user status recognition programs, etc.), and calling
- the data in the memory 11 is used to perform various functions of the electronic device 1 and process data.
- the bus may be a peripheral component interconnect (PCI) bus or an extended industry standard structure (extended industry standard structure). industry standard architecture, EISA for short) bus, etc.
- PCI peripheral component interconnect
- extended industry standard structure extended industry standard structure
- EISA industry standard architecture
- the bus can be divided into address bus, data bus, control bus and so on.
- the bus is configured to implement connection and communication between the memory 11 and at least one processor 10 and the like.
- FIG. 4 only shows an electronic device with components. Those skilled in the art can understand that the structure shown in FIG. 4 does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure. Components, or a combination of certain components, or different component arrangements.
- the electronic device 1 may also include a power source (such as a battery) for supplying power to various components.
- the power source may be logically connected to the at least one processor 10 through a power management device, thereby controlling power
- the device implements functions such as charge management, discharge management, and power consumption management.
- the power supply may also include any components such as one or more DC or AC power supplies, recharging devices, power failure detection circuits, power converters or inverters, and power status indicators.
- the electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.
- the electronic device 1 may also include a network interface.
- the network interface may include a wired interface and/or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is usually used in the electronic device 1 Establish a communication connection with other electronic devices.
- the electronic device 1 may also include a user interface.
- the user interface may be a display (Display) and an input unit (such as a keyboard (Keyboard)).
- the user interface may also be a standard wired interface or a wireless interface.
- the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc.
- the display can also be appropriately called a display screen or a display unit, which is used to display the information processed in the electronic device 1 and to display a visualized user interface.
- the audio-based user state recognition program 12 stored in the memory 11 in the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can realize:
- the user state recognition model is used to recognize the to-be-recognized spectrogram to obtain a user state recognition result.
- the integrated module/unit of the electronic device 1 can be stored in a computer-readable storage medium. It can be volatile or non-volatile.
- the computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory) .
- the computer-readable storage medium stores a computer program, where the computer program is executed by a processor to implement the following steps:
- the user state recognition model is used to recognize the to-be-recognized spectrogram to obtain a user state recognition result.
- the computer usable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function, etc.; the storage data area may store a block chain node Use the created data, etc.
- modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
- the functional modules in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
- the above-mentioned integrated unit may be implemented in the form of hardware, or may be implemented in the form of hardware plus software functional modules.
- the blockchain referred to in this application is a new application mode of computer technology such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm.
- Blockchain essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information for verification. The validity of the information (anti-counterfeiting) and the generation of the next block.
- the blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- Acoustics & Sound (AREA)
- Human Computer Interaction (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Epidemiology (AREA)
- Public Health (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
一种基于音频的用户状态识别方法和装置、电子设备以及计算机可读存储介质,方法包括:获取音频训练集,对所述音频训练集中的每个音频进行特征转换,得到目标声谱图集(S1);基于注意力机制与小样本学习,利用所述目标声谱图集对预构建的深度学习网络模型进行训练,得到用户状态识别模型(S2);当接收到待识别用户的音频时,对所述待识别用户的音频进行特征转换,得到待识别声谱图(S3);利用所述用户状态识别模型对所述待识别声谱图进行识别,得到用户状态识别结果(S4)。此外还涉及一种区块链技术,所述音频训练集可以存储在区块链中。利用上述方法降低了数据资源消耗,增强了模型的实用性。
Description
本申请要求于2020年10月9日提交中国专利局、申请号为CN202011074898.9、名称为“基于音频的用户状态识别方法、装置及存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
本申请涉及人工智能领域,尤其涉及一种基于音频的用户状态识别方法、装置、电子设备及存储介质。
随着智慧生活的理念逐渐普及,用户状态成为了智慧生活的核心关注点,因此用户状态的识别成为了一件非常重要的事情,如识别用户当前的健康状态,尤其在传染病大肆流行的时候,时刻了解每个人的健康状态很重要。一般情况下,需要用户到医院找医生进行身体检查才能了解其健康情况,医院本身就充满了各种病菌,去医院检查存在着被感染的风险。
发明人意识到,目前,通常利用大量的用户的医学图像(如胸部X光)来训练机器学习模型实现用户状态识别来确定用户的健康状态,但是大量的用户的医学图像耗费了大量的数据资源,且用户的医学图像获取门槛较高导致实用性不强无法更好地推广普及。
本申请提供的一种基于音频的用户状态识别方法,包括:
获取音频训练集,对所述音频训练集中的每个音频进行特征转换,得到目标声谱图集;
基于注意力机制与小样本学习,利用所述目标声谱图集对预构建的深度学习网络模型进行训练,得到用户状态识别模型;
当接收到待识别用户的音频时,对所述待识别用户的音频进行特征转换,得到待识别声谱图;
利用所述用户状态识别模型对所述待识别声谱图进行识别,得到用户状态识别结果。
本申请还提供一种基于音频的用户状态识别装置,所述装置包括:
模型生成模块,用于获取音频训练集,对所述音频训练集中的每个音频进行特征转换,得到目标声谱图集;基于注意力机制与小样本学习,利用所述目标声谱图集对预构建的深度学习网络模型进行训练,得到用户状态识别模型;
状态识别模块,用于当接收到待识别用户的音频时,对所述待识别用户的音频进行特征转换,得到待识别声谱图;利用所述用户状态识别模型对所述待识别声谱图进行识别,得到用户状态识别结果。
本申请还提供一种电子设备,所述电子设备包括:
存储器,存储至少一个指令;及
处理器,执行所述存储器中存储的指令以实现如下步骤:
获取音频训练集,对所述音频训练集中的每个音频进行特征转换,得到目标声谱图集;
基于注意力机制与小样本学习,利用所述目标声谱图集对预构建的深度学习网络模型进行训练,得到用户状态识别模型;
当接收到待识别用户的音频时,对所述待识别用户的音频进行特征转换,得到待识别声谱图;
利用所述用户状态识别模型对所述待识别声谱图进行识别,得到用户状态识别结果。
本申请还提供一种计算机可读存储介质,所述计算机可读存储介质中存储有至少一个指令,所述至少一个指令被电子设备中的处理器执行时实现如下步骤:
获取音频训练集,对所述音频训练集中的每个音频进行特征转换,得到目标声谱图集;
基于注意力机制与小样本学习,利用所述目标声谱图集对预构建的深度学习网络模型进行训练,得到用户状态识别模型;
当接收到待识别用户的音频时,对所述待识别用户的音频进行特征转换,得到待识别声谱图;
利用所述用户状态识别模型对所述待识别声谱图进行识别,得到用户状态识别结果。
图1为本申请一实施例提供的基于音频的用户状态识别方法的流程示意图;
图2为本申请一实施例提供的基于音频的用户状态识别方法中得到目标声谱图集的详细流程示意图;
图3为本申请一实施例提供的基于音频的用户状态识别装置的模块示意图;
图4为本申请一实施例提供的实现基于音频的用户状态识别方法的电子设备的内部结构示意图;
本申请目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。
应当理解,此处所描述的具体实施例仅仅用以解释本申请,并不用于限定本申请。
本申请提供一种基于音频的用户状态识别方法。参照图1所示,为本申请一实施例提供的基于音频的用户状态识别方法的流程示意图。该方法可以由一个装置执行,该装置可以由软件和/或硬件实现。
在本实施例中,基于音频的用户状态识别方法包括:
S1、获取音频训练集,对所述音频训练集中的每个音频进行特征转换,得到目标声谱图集;
本申请实施例中,所述音频训练集为包含初始标签的音频的集合,较佳地,所述初始标签为用户的疾病情况,例如:急性支气管炎、慢性咽炎、百日咳、发烧;进一步地,由于不同疾病情况下用户的咳嗽音频具有对应的声音特征,因此,较佳地,所述音频训练集为不同的疾病情况对应的咳嗽音频的集合,其中,所述声音特征为咳嗽音频的频域特征可用声谱图表示。
进一步地,为了后续模型更好的所述音频训练集中的每个音频的特征更加直观清晰,本申请实施例对所述音频训练集进行特征变换,得到所述目标声谱图集,包括:
S11、对所述音频训练集中的每个音频进行重采样,得到对应的数字语音信号;
本申请实施例中,为了便于对所述音频训练集中的每个音频进行数据处理,对所述音频训练集中的每个音频进行重采样,得到对应的数字语音信号,较佳的地,本申请实施例利用数模转换器对所述音频训练集中的每个音频进行重采样。
S12、对所述数字语音信号进行预加重,得到标准数字语音信号;
S13、汇总所有的所述标准数字语音信号,得到语音信号集;
本申请实施例中,为了对所述音频训练集获取过程中导致的音频信息丢失进行补偿,对所述音频训练集中的每个音频进行预加重操作,
详细地,本申请实施例中,所述对所述音频训练集中的每个音频进行预加重操作,包括:将所述音频训练集中的每个音频进行重采样,得到对应的数字语音信号;将所述数字语音信号进行预加重,得到标准数字语音信号,汇总所有的所述标准数字语音信号,得到语音信号集。
详细地,本申请实施例利用如下公式进行所述预加重操作:
y(t)=x(t)-μx(t-1)
其中,x(t)为所述数字语音信号,t为时间,y(t)为所述标准数字语音信号,μ为所述预加重操作的预设调节值,较佳地,μ的取值范围为[0.9,1.0]。
S14、对所述语音信号集中包含的每个标准数字语音信号进行特征转换,得到目标声谱图集。
本申请实施例中,所述语音信号集中的标准语音信号只能体现音频在时域上的变化,不能体现所述标准语音信号的音频特征,为了体现所述标准语音信号的音频特征,使音频特征更加直观和清晰,对所述语音信号集中的每个标准数字语音信号进行特征转换。
详细地,本申请实施例中对所述语音信号集中的每个标准数字语音信号进行特征转换,包括:利用预设声音处理算法,将所述语音信号集中的每个标准数字语音信号映射在频域,得到对应的目标声谱图,汇总所有的所述目标声谱图的得到所述目标声谱图集。
较佳地,本申请中所述声音处理算法为梅尔滤波算法。
本申请实施例中,上述步骤只是对所述音频训练集的每个音频进行特征转换,不会影响所述音频训练集的每个音频对应的所述初始标签,所以所述目标声谱图集中每个目标声谱图都有对应的初始标签。
S2、基于注意力机制与小样本学习,利用所述目标声谱图集对预构建的深度学习网络模型进行训练,得到用户状态识别模型;
本申请实施例中,由于所述音频训练集中的样本数量过少,为了保证后续模型的训练精度及鲁棒性,基于注意力机制与小样本学习,利用所述目标声谱图集对预构建的深度学习网络模型进行训练,得到基于音频的用户状态识别模型。
详细地,本申请实施例中,所述利用所述目标声谱图集对预构建的深度学习网络模型进行训练,包括:
步骤A:将所述目标声谱图集划分为训练集及测试集;
本申请实施例中,由于所述目标声谱图集中的样本数据较少且不易获取,直接将所述目标声谱图集作为训练集会导致后续模型的鲁棒性较差,因此,本申请实施例将所述目标声谱图集划分为训练集及测试集,通过利用测试集不断的对训练模型进行测试调整增强模型的鲁棒性,所述将所述目标声谱图集划分为训练集及测试集,包括:将所述目标声谱图集中的每个目标声谱图按照对应的初始标签进行分类,得到对应的分类目标声谱图集;从所述分类目标声谱图集中随机取出预设数量的目标声谱图作为测试子集,将所述分类声谱图集中所述训练子集的补集作为训练子集;汇总所有的所述训练子集的训练集,汇总所有的所述测试子集得到测试集,较佳地,本申请实施例中所述预设数量为1。
步骤B:利用所述训练集对所述深度学习网络进行训练得到初始识别模型,根据所述测试集对所述初始识别模型进行测试得到损失值,当所述损失值大于预设阈值时返回步骤A,当所述损失值小于或等于预设阈值时,将所述初始识别模型作为用户状态识别模型。
较佳地,本申请实施例中所述深度学习网络为卷积神经网络。
本申请实施例中,由于所述音频训练集中的音频时间可能不一致,导致所述目标声谱图集中的图像大小存在差异,进而导致所述深度学习网络模型在训练的过程中提取的所述目标声谱图集中的目标声谱图的特征维度不同,无法进行统一训练,因此,为了更好地利用所述音频训练集中的数据,本申请实施例利用所述训练集对所述深度学习网络前,需要在所述深度学习网络模型的全连接层前增加注意力机制处理层进行图像特征对齐,其中,所述注意力机制处理层根据图像特征维度不同进行特征对齐的网络,例如:目标声谱图A的在所述深度学习网络模型进行特征提取的图像特征a为D*T1维矩阵,目标声谱图B的在所述深度学习网络模型进行特征提取的图像特征b为D*T2维矩阵,所述注意力机制处理层将图像特征a乘上T1*1的预设权重矩阵转化为D维矩阵,将图像特征b乘上T2*1的预设权重矩阵转化为D维矩阵,实现图像特征a及图像特征b的特征对齐。
进一步地,由于所述训练集的中的样本数量较少,所以本申请实施例需要对所述初始识别模型进行以验证该模型的识别能力方便对模型进行训练调整。
详细地,本申请实施例中所述初始识别模型的识别类别和所述目标声谱图集中的初始标签的类别相同,例如:所述目标声谱图集中共有两种初始标签为慢性咽炎、发烧,那么所述初始识别模型中的识别类别也有相同的两种为慢性咽炎、发烧。进一步地,本申请实施例中所述根据所述测试集对所述初始识别模型进行测试得到损失值,包括:提取所述初始识别模型中每种所述初始标签对应的特征向量,得到目标特征向量;利用所述初始识别模型对所述测试子集中的每个目标声谱图进行特征提取,得到测试特征向量;计算每种所述初始标签对应的所述目标特征向量与所述测试特征向量的距离,得到损失距离值;计算所有所述损失距离值的平均值,得到所述损失值。较佳地,本申请实施例采用欧氏距离计算方法计算每种所述初始标签对应的所述目标特征向量与所述测试特征向量的距离。
进一步地,本领域技术人员可知所述初始模型的不同识别类别连接对应不同的全连接层节点,全连接层节点有对应的顺序,本申请实施例获取初始识别模型的每种识别类别对应的全连接层节点的输出值并按照对应的全连接层节点的顺序进行组合,得到对应的所述目标特征向量;进一步地,本申请实施例将所述测试子集中的每个目标声谱图输入所述初始识别模型,根据所述测试子集中的每个目标声谱图对应的初始标签,获取所述初始识别模型中对应识别类别的全连接层节点的输出值并按照对应的全连接层节点的顺序进行组合,得到所述测试特征向量。
本申请的另一实施例中,为了保证数据的隐私性,所述音频训练集可以存储在区块链节点中。
S3、当接收到待识别用户的音频时,对所述待识别用户的音频进行特征转换,得到待识别声谱图;
本申请实施例中,所述待识别用户的音频与所述音频训练集中的音频的类别相同,较佳地,本申请实施例中,所述待识别用户的音频为用户的咳嗽音频。音频训练集
进一步地,本申请实施例中对所述待识别用户的音频进行特征转换的方法与上述对所述音频训练集的每个音频进行特征转换的方法相同。
S4、利用所述用户状态识别模型对所述待识别声谱图进行识别,得到用户状态识别结果。
本申请实施例中,所述用户状态识别结果为用户的健康状态,例如:急性支气管炎、慢性咽炎、百日咳、发烧。
本申请实施例中,对所述音频训练集中的每个音频进行特征转换,得到目标声谱图集,使所述音频训练集中音频中的特征更加清晰直观,增加了后续模型训练的精度;基于注意力机制与小样本学习,利用所述目标声谱图集对预构建的深度学习网络模型进行训练,得到用户状态识别模型,增强了小样本训练集下的模型的鲁棒性及训练精度;对所述待识别用户的音频进行特征转换,得到待识别声谱图,使所述待识别用户的音频特征更加清晰直观,提高了后续模型的识别精度;利用所述用户状态识别模型对所述待识别声谱图进行识别,得到用户状态识别结果,利用少量的更易得的音频数据进行模型的训练,降低了模型的训练的数据资源消耗,只需要用户的音频就可以对用户状态进行识别,增强了模型的实用性。
如图3所示,是本申请基于音频的用户状态识别装置的功能模块图。
本申请所述基于音频的用户状态识别装置100可以安装于电子设备中。根据实现的功能,所述基于音频的用户状态识别装置可以包括模型生成模块101、状态识别模块102。本发所述模块也可以称之为单元,是指一种能够被电子设备处理器所执行,并且能够完成固定功能的一系列计算机程序段,其存储在电子设备的存储器中。
在本实施例中,关于各模块/单元的功能如下:
所述模型生成模块101用于获取音频训练集,对所述音频训练集中的每个音频进行特征转换,得到目标声谱图集;基于注意力机制与小样本学习,利用所述目标声谱图集对预构建的深度学习网络模型进行训练,得到用户状态识别模型。
本申请实施例中,所述音频训练集为包含初始标签的音频的集合,较佳地,所述初始标签为用户的疾病情况,例如:急性支气管炎、慢性咽炎、百日咳、发烧;进一步地,由于不同疾病情况下用户的咳嗽音频具有对应的声音特征,因此,较佳地,所述音频训练集为不同的疾病情况对应的咳嗽音频的集合,其中,所述声音特征为咳嗽音频的频域特征可用声谱图表示。
进一步地,为了后续模型更好的所述音频训练集中的每个音频的特征更加直观清晰,本申请实施例所述模型生成模块101利用如下手段对所述音频训练集进行特征变换,得到所述目标声谱图集,包括:
对所述音频训练集中的每个音频进行重采样,得到对应的数字语音信号;
本申请实施例中,为了便于对所述音频训练集中的每个音频进行数据处理,对所述音频训练集中的每个音频进行重采样,得到对应的数字语音信号,较佳的地,本申请实施例利用数模转换器对所述音频训练集中的每个音频进行重采样。
对所述数字语音信号进行预加重,得到标准数字语音信号;
汇总所有的所述标准数字语音信号,得到语音信号集;
本申请实施例中,为了对所述音频训练集获取过程中导致的音频信息丢失进行补偿,对所述音频训练集中的每个音频进行预加重操作,
详细地,本申请实施例中,所述对所述音频训练集中的每个音频进行预加重操作,包括:对所述音频训练集中的每个音频进行重采样,得到对应的数字语音信号;将所述数字语音信号进行预加重,得到标准数字语音信号,汇总所有的所述标准数字语音信号,得到语音信号集。
详细地,本申请实施例所述模型生成模块101利用如下公式进行所述预加重操作:
y(t)=x(t)-μx(t-1)
其中,x(t)为所述数字语音信号,t为时间,y(t)为所述标准数字语音信号,μ为所述预加重操作的预设调节值,较佳地,μ的取值范围为[0.9,1.0]。
对所述语音信号集中包含的每个标准数字语音信号进行特征转换,得到目标声谱图集。
本申请实施例中,所述语音信号集中的标准语音信号只能体现音频在时域上的变化,不能体现所述标准语音信号的音频特征,为了体现所述标准语音信号的音频特征,使音频特征更加直观和清晰,对所述语音信号集中的每个标准数字语音信号进行特征转换。
详细地,本申请实施例中所述模型生成模块101利用如下手段对所述语音信号集中的每个标准数字语音信号进行特征转换,包括:利用预设声音处理算法,将所述语音信号集中的每个标准数字语音信号映射在频域,得到对应的目标声谱图,汇总所有的所述目标声谱图的得到所述目标声谱图集。
较佳地,本申请中所述声音处理算法为梅尔滤波算法。
本申请实施例中,上述步骤只是对所述音频训练集的每个音频进行特征转换,不会影响所述音频训练集的每个音频对应的所述初始标签,所以所述目标声谱图集中每个目标声谱图都有对应的初始标签。
本申请实施例中,由于所述音频训练集中的样本数量过少,为了保证后续模型的训练精度及鲁棒性,基于注意力机制与小样本学习,利用所述目标声谱图集对预构建的深度学习网络模型进行训练,得到基于音频的用户状态识别模型。
详细地,本申请实施例中,所述模型生成模块101利用如下手段对预构建的深度学习网络模型进行训练,包括:
步骤A:将所述目标声谱图集划分为训练集及测试集;
本申请实施例中,由于所述目标声谱图集中的样本数据较少且不易获取,直接将所述目标声谱图集作为训练集会导致后续模型的鲁棒性较差,因此,本申请实施例将所述目标声谱图集划分为训练集及测试集,通过利用测试集不断的对训练模型进行测试调整增强模型的鲁棒性,所述将所述目标声谱图集划分为训练集及测试集,包括:将所述目标声谱图集中的每个目标声谱图按照对应的初始标签进行分类,得到对应的分类目标声谱图集;从所述分类目标声谱图集中随机取出预设数量的目标声谱图作为测试子集,将所述分类声谱图集中所述训练子集的补集作为训练子集;汇总所有的所述训练子集的训练集,汇总所有的所述测试子集得到测试集,较佳地,本申请实施例中所述预设数量为1。
步骤B:利用所述训练集对所述深度学习网络进行训练得到初始识别模型,根据所述测试集对所述初始识别模型进行测试得到损失值,当所述损失值大于预设阈值时返回步骤A,当所述损失值小于或等于预设阈值时,将所述初始识别模型作为用户状态识别模型。
较佳地,本申请实施例中所述深度学习网络为卷积神经网络。
本申请实施例中,由于所述音频训练集中的音频时间可能不一致,导致所述目标声谱图集中的图像大小存在差异,进而导致所述深度学习网络模型在训练的过程中提取的所述目标声谱图集中的目标声谱图的特征维度不同,无法进行统一训练,因此,为了更好地利用所述音频训练集中的数据,本申请实施例利用所述训练集对所述深度学习网络前,需要在所述深度学习网络模型的全连接层前增加注意力机制处理层进行图像特征对齐,其中,所述注意力机制处理层根据图像特征维度不同进行特征对齐的网络,例如:目标声谱图A的在所述深度学习网络模型进行特征提取的图像特征a为D*T1维矩阵,目标声谱图B的在所述深度学习网络模型进行特征提取的图像特征b为D*T2维矩阵,所述注意力机制处理层将图像特征a乘上T1*1的预设权重矩阵转化为D维矩阵,将图像特征b乘上T2*1的预设权重矩阵转化为D维矩阵,实现图像特征a及图像特征b的特征对齐。
进一步地,由于所述训练集的中的样本数量较少,所以本申请实施例需要对所述初始识别模型进行以验证该模型的识别能力方便对模型进行训练调整。
详细地,本申请实施例中所述初始识别模型的识别类别和所述目标声谱图集中的初始标签的类别相同,例如:所述所述目标声谱图集中共有两种初始标签为慢性咽炎、发烧,那么所述初始识别模型中的识别类别也有相同的两种为慢性咽炎、发烧。进一步地,本申请实施例中所述模型生成模块101利用如下手段得到损失值,包括:提取所述初始识别模型中每种所述初始标签对应的特征向量,得到目标特征向量;利用所述初始识别模型对所述测试子集中的每个目标声谱图进行特征提取,得到测试特征向量;计算每种所述初始标签对应的所述目标特征向量与所述测试特征向量的距离,得到损失距离值;计算所有所述损失距离值的平均值,得到所述损失值。较佳地,本申请实施例采用欧氏距离计算方法计算每种所述初始标签对应的所述目标特征向量与所述测试特征向量的距离。
进一步地,本领域技术人员可知所述初始模型的不同识别类别连接对应不同的全连接层节点,全连接层节点有对应的顺序,本申请实施例所述模型生成模块101获取初始识别模型的每种识别类别对应的全连接层节点的输出值并按照对应的全连接层节点的顺序进行组合,得到对应的所述目标特征向量;进一步地,本申请实施例所述模型生成模块101将所述测试子集中的每个目标声谱图输入所述初始识别模型,根据所述测试子集中的每个目标声谱图对应的初始标签,获取所述初始识别模型中对应识别类别的全连接层节点的输出值并按照对应的全连接层节点的顺序进行组合,得到所述测试特征向量。
本申请的另一实施例中,为了保证数据的隐私性,所述音频训练集可以存储在区块链节点中。
所述状态识别模块102用于当接收到待识别用户的音频时,对所述待识别用户的音频进行特征转换,得到待识别声谱图;利用所述用户状态识别模型对所述待识别声谱图进行识别,得到用户状态识别结果。
本申请实施例中,所述待识别用户的音频与所述音频训练集中的音频的类别相同,较佳地,本申请实施例中,所述待识别用户的音频为用户的咳嗽音频。音频训练集
进一步地,本申请实施例中对所述待识别用户的音频进行特征转换的方法与上述对所述音频训练集的每个音频进行特征转换的方法相同。
本申请实施例中,所述用户状态识别结果为用户的疾病情况,例如:急性支气管炎、慢性咽炎、百日咳、发烧。
如图44所示,是本申请实现基于音频的用户状态识别方法的电子设备的结构示意图。
所述电子设备1可以包括处理器10、存储器11和总线,还可以包括存储在所述存储器11中并可在所述处理器10上运行的计算机程序,如基于音频的用户状态识别程序。
其中,所述存储器11至少包括一种类型的可读存储介质,所述可读存储介质包括闪存、移动硬盘、多媒体卡、卡型存储器(例如:SD或DX存储器等)、磁性存储器、磁盘、光盘等。所述存储器11在一些实施例中可以是电子设备1的内部存储单元,例如该电子设备1的移动硬盘。所述存储器11在另一些实施例中也可以是电子设备1的外部存储设备,例如电子设备1上配备的插接式移动硬盘、智能存储卡(Smart Media Card, SMC)、安全数字(Secure
Digital, SD)卡、闪存卡(Flash
Card)等。进一步地,所述存储器11还可以既包括电子设备1的内部存储单元也包括外部存储设备。所述存储器11不仅可以用于存储安装于电子设备1的应用软件及各类数据,例如基于音频的用户状态识别程序的代码等,还可以用于暂时地存储已经输出或者将要输出的数据。
所述处理器10在一些实施例中可以由集成电路组成,例如可以由单个封装的集成电路所组成,也可以是由多个相同功能或不同功能封装的集成电路所组成,包括一个或者多个中央处理器(Central Processing unit,CPU)、微处理器、数字处理芯片、图形处理器及各种控制芯片的组合等。所述处理器10是所述电子设备的控制核心(Control
Unit),利用各种接口和线路连接整个电子设备的各个部件,通过运行或执行存储在所述存储器11内的程序或者模块(例如基于音频的用户状态识别程序等),以及调用存储在所述存储器11内的数据,以执行电子设备1的各种功能和处理数据。
所述总线可以是外设部件互连标准(peripheral component interconnect,简称PCI)总线或扩展工业标准结构(extended
industry standard architecture,简称EISA)总线等。该总线可以分为地址总线、数据总线、控制总线等。所述总线被设置为实现所述存储器11以及至少一个处理器10等之间的连接通信。
图4仅示出了具有部件的电子设备,本领域技术人员可以理解的是,图4示出的结构并不构成对所述电子设备1的限定,可以包括比图示更少或者更多的部件,或者组合某些部件,或者不同的部件布置。
例如,尽管未示出,所述电子设备1还可以包括给各个部件供电的电源(比如电池),优选地,电源可以通过电源管理装置与所述至少一个处理器10逻辑相连,从而通过电源管理装置实现充电管理、放电管理、以及功耗管理等功能。电源还可以包括一个或一个以上的直流或交流电源、再充电装置、电源故障检测电路、电源转换器或者逆变器、电源状态指示器等任意组件。所述电子设备1还可以包括多种传感器、蓝牙模块、Wi-Fi模块等,在此不再赘述。
进一步地,所述电子设备1还可以包括网络接口,可选地,所述网络接口可以包括有线接口和/或无线接口(如WI-FI接口、蓝牙接口等),通常用于在该电子设备1与其他电子设备之间建立通信连接。
可选地,该电子设备1还可以包括用户接口,用户接口可以是显示器(Display)、输入单元(比如键盘(Keyboard)),可选地,用户接口还可以是标准的有线接口、无线接口。可选地,在一些实施例中,显示器可以是LED显示器、液晶显示器、触控式液晶显示器以及OLED(Organic
Light-Emitting Diode,有机发光二极管)触摸器等。其中,显示器也可以适当的称为显示屏或显示单元,用于显示在电子设备1中处理的信息以及用于显示可视化的用户界面。
应该了解,所述实施例仅为说明之用,在专利申请范围上并不受此结构的限制。
所述电子设备1中的所述存储器11存储的基于音频的用户状态识别程序12是多个指令的组合,在所述处理器10中运行时,可以实现:
获取音频训练集,对所述音频训练集中的每个音频进行特征转换,得到目标声谱图集;
基于注意力机制与小样本学习,利用所述目标声谱图集对预构建的深度学习网络模型进行训练,得到用户状态识别模型;
当接收到待识别用户的音频时,对所述待识别用户的音频进行特征转换,得到待识别声谱图;
利用所述用户状态识别模型对所述待识别声谱图进行识别,得到用户状态识别结果。
具体地,所述处理器10对上述指令的具体实现方法可参考图1对应实施例中相关步骤的描述,在此不赘述。
进一步地,所述电子设备1集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中,所述计算机可读存储介质可以是易失性,也可以是非易失性。所述计算机可读介质可以包括:能够携带所述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(ROM,Read-Only Memory)。
所述计算机可读存储介质中存储有计算机程序,其中,所述计算机程序被处理器执行时实现如下步骤:
获取音频训练集,对所述音频训练集中的每个音频进行特征转换,得到目标声谱图集;
基于注意力机制与小样本学习,利用所述目标声谱图集对预构建的深度学习网络模型进行训练,得到用户状态识别模型;
当接收到待识别用户的音频时,对所述待识别用户的音频进行特征转换,得到待识别声谱图;
利用所述用户状态识别模型对所述待识别声谱图进行识别,得到用户状态识别结果。
进一步地,所述计算机可用存储介质可主要包括存储程序区和存储数据区,其中,存储程序区可存储操作系统、至少一个功能所需的应用程序等;存储数据区可存储根据区块链节点的使用所创建的数据等。
在本申请所提供的几个实施例中,应该理解到,所揭露的设备,装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述模块的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式。
所述作为分离部件说明的模块可以是或者也可以不是物理上分开的,作为模块显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
另外,在本申请各个实施例中的各功能模块可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用硬件加软件功能模块的形式实现。
对于本领域技术人员而言,显然本申请不限于上述示范性实施例的细节,而且在不背离本申请的精神或基本特征的情况下,能够以其他的具体形式实现本申请。
因此,无论从哪一点来看,均应将实施例看作是示范性的,而且是非限制性的,本申请的范围由所附权利要求而不是上述说明限定,因此旨在将落在权利要求的等同要件的含义和范围内的所有变化涵括在本申请内。不应将权利要求中的任何附关联图标记视为限制所涉及的权利要求。
本申请所指区块链是分布式数据存储、点对点传输、共识机制、加密算法等计算机技术的新型应用模式。区块链(Blockchain),本质上是一个去中心化的数据库,是一串使用密码学方法相关联产生的数据块,每一个数据块中包含了一批次网络交易的信息,用于验证其信息的有效性(防伪)和生成下一个区块。区块链可以包括区块链底层平台、平台产品服务层以及应用服务层等。
此外,显然“包括”一词不排除其他单元或步骤,单数不排除复数。系统权利要求中陈述的多个单元或装置也可以由一个单元或装置通过软件或者硬件来实现。第二等词语用来表示名称,而并不表示任何特定的顺序。
最后应说明的是,以上实施例仅用以说明本申请的技术方案而非限制,尽管参照较佳实施例对本申请进行了详细说明,本领域的普通技术人员应当理解,可以对本申请的技术方案进行修改或等同替换,而不脱离本申请技术方案的精神和范围。
Claims (20)
- 一种基于音频的用户状态识别方法,其中,所述方法包括:获取音频训练集,对所述音频训练集中的每个音频进行特征转换,得到目标声谱图集;基于注意力机制与小样本学习,利用所述目标声谱图集对预构建的深度学习网络模型进行训练,得到用户状态识别模型;当接收到待识别用户的音频时,对所述待识别用户的音频进行特征转换,得到待识别声谱图;利用所述用户状态识别模型对所述待识别声谱图进行识别,得到用户状态识别结果。
- 如权利要求1所述的基于音频的用户状态识别方法,其中,所述对所述音频训练集中的每个音频进行特征转换,得到目标声谱图集,包括:将所述音频训练集中的每个音频进行重采样,得到对应的数字语音信号;对所述数字语音信号进行预加重,得到标准数字语音信号;汇总所有的所述标准数字语音信号,得到语音信号集;对所述语音信号集中包含的每个标准数字语音信号进行特征转换,得到目标声谱图集。
- 如权利要求2所述的基于音频的用户状态识别方法,其中,所述对所述语音信号集中包含的每个标准数字语音信号进行特征转换,得到目标声谱图集,包括:利用预设声音处理算法,将所述语音信号集中的每个标准数字语音信号映射在频域,得到对应的目标声谱图;汇总所有的所述目标声谱图得到所述目标声谱图集。
- 如权利要求1所述的基于音频的用户状态识别方法,其中,所述利用所述目标声谱图集对预构建的深度学习网络模型进行训练,得到用户状态识别模型,包括:将所述目标声谱图集随机划分为训练集及测试集;利用所述训练集对所述深度学习网络模型进行训练得到初始识别模型;根据所述测试集对所述初始识别模型进行测试得到损失值;当所述损失值大于预设阈值时返回所述将所述目标声谱图集随机划分为训练集及测试集步骤;当所述损失值小于或等于预设阈值时,将所述初始识别模型作为用户状态识别模型。
- 如权利要求4所述的基于音频的用户状态识别方法,其中,所述将所述目标声谱图集随机划分为训练集及测试集,包括:将所述目标声谱图集中的每个目标声谱图按照对应的初始标签进行分类,得到对应的分类目标声谱图集;从所述分类目标声谱图集中随机取出预设数量的目标声谱图作为测试子集,将所述分类声谱图集中所述测试子集的补集作为训练子集;汇总所有的所述训练子集得到训练集;汇总所有的所述测试子集得到测试集。
- 如权利要求5所述的基于音频的用户状态识别方法,其中,所述根据所述测试集对所述初始识别模型进行测试得到损失值,包括:提取所述初始识别模型中每种所述初始标签对应的特征向量,得到目标特征向量;利用所述初始识别模型对所述测试集中的每个目标声谱图进行特征提取,得到对应的测试特征向量;计算每种所述初始标签对应的所述目标特征向量与所述测试特征向量的距离,得到损失距离值;计算所有所述损失距离值的平均值,得到所述损失值。
- 如权利要求1至6中任何一项所述的基于音频的用户状态识别方法,其中,所述音频训练集为不同的疾病情况对应的咳嗽音频的集合。
- 一种基于音频的用户状态识别装置,其中,所述装置包括:模型生成模块,用于获取音频训练集,对所述音频训练集中的每个音频进行特征转换,得到目标声谱图集;基于注意力机制与小样本学习,利用所述目标声谱图集对预构建的深度学习网络模型进行训练,得到用户状态识别模型;状态识别模块,用于当接收到待识别用户的音频时,对所述待识别用户的音频进行特征转换,得到待识别声谱图;利用所述用户状态识别模型对所述待识别声谱图进行识别,得到用户状态识别结果。
- 一种电子设备,其中,所述电子设备包括:至少一个处理器;以及,与所述至少一个处理器通信连接的存储器;其中,所述存储器存储有可被所述至少一个处理器执行的指令,所述指令被所述至少一个处理器执行,以使所述至少一个处理器能够执行如下步骤:获取音频训练集,对所述音频训练集中的每个音频进行特征转换,得到目标声谱图集;基于注意力机制与小样本学习,利用所述目标声谱图集对预构建的深度学习网络模型进行训练,得到用户状态识别模型;当接收到待识别用户的音频时,对所述待识别用户的音频进行特征转换,得到待识别声谱图;利用所述用户状态识别模型对所述待识别声谱图进行识别,得到用户状态识别结果。
- 如权利要求9所述的电子设备,其中,所述对所述音频训练集中的每个音频进行特征转换,得到目标声谱图集,包括:将所述音频训练集中的每个音频进行重采样,得到对应的数字语音信号;对所述数字语音信号进行预加重,得到标准数字语音信号;汇总所有的所述标准数字语音信号,得到语音信号集;对所述语音信号集中包含的每个标准数字语音信号进行特征转换,得到目标声谱图集。
- 如权利要求10所述的电子设备,其中,所述对所述语音信号集中包含的每个标准数字语音信号进行特征转换,得到目标声谱图集,包括:利用预设声音处理算法,将所述语音信号集中的每个标准数字语音信号映射在频域,得到对应的目标声谱图;汇总所有的所述目标声谱图得到所述目标声谱图集。
- 如权利要求9所述的电子设备,其中,所述利用所述目标声谱图集对预构建的深度学习网络模型进行训练,得到用户状态识别模型,包括:将所述目标声谱图集随机划分为训练集及测试集;利用所述训练集对所述深度学习网络模型进行训练得到初始识别模型;根据所述测试集对所述初始识别模型进行测试得到损失值;当所述损失值大于预设阈值时返回所述将所述目标声谱图集随机划分为训练集及测试集步骤;当所述损失值小于或等于预设阈值时,将所述初始识别模型作为用户状态识别模型。
- 如权利要求12所述的电子设备,其中,所述将所述目标声谱图集随机划分为训练集及测试集,包括:将所述目标声谱图集中的每个目标声谱图按照对应的初始标签进行分类,得到对应的分类目标声谱图集;从所述分类目标声谱图集中随机取出预设数量的目标声谱图作为测试子集,将所述分类声谱图集中所述测试子集的补集作为训练子集;汇总所有的所述训练子集得到训练集;汇总所有的所述测试子集得到测试集。
- 如权利要求13所述的电子设备,其中,所述根据所述测试集对所述初始识别模型进行测试得到损失值,包括:提取所述初始识别模型中每种所述初始标签对应的特征向量,得到目标特征向量;利用所述初始识别模型对所述测试集中的每个目标声谱图进行特征提取,得到对应的测试特征向量;计算每种所述初始标签对应的所述目标特征向量与所述测试特征向量的距离,得到损失距离值;计算所有所述损失距离值的平均值,得到所述损失值。
- 如权利要求9至14中任何一项所述的电子设备,其中,所述音频训练集为不同的疾病情况对应的咳嗽音频的集合。
- 一种计算机可读存储介质,存储有计算机程序,其中,所述计算机程序被处理器执行时实现如下步骤:获取音频训练集,对所述音频训练集中的每个音频进行特征转换,得到目标声谱图集;基于注意力机制与小样本学习,利用所述目标声谱图集对预构建的深度学习网络模型进行训练,得到用户状态识别模型;当接收到待识别用户的音频时,对所述待识别用户的音频进行特征转换,得到待识别声谱图;利用所述用户状态识别模型对所述待识别声谱图进行识别,得到用户状态识别结果。
- 如权利要求16所述的计算机可读存储介质,其中,所述对所述音频训练集中的每个音频进行特征转换,得到目标声谱图集,包括:将所述音频训练集中的每个音频进行重采样,得到对应的数字语音信号;对所述数字语音信号进行预加重,得到标准数字语音信号;汇总所有的所述标准数字语音信号,得到语音信号集;对所述语音信号集中包含的每个标准数字语音信号进行特征转换,得到目标声谱图集。
- 如权利要求17所述的计算机可读存储介质,其中,所述对所述语音信号集中包含的每个标准数字语音信号进行特征转换,得到目标声谱图集,包括:利用预设声音处理算法,将所述语音信号集中的每个标准数字语音信号映射在频域,得到对应的目标声谱图;汇总所有的所述目标声谱图得到所述目标声谱图集。
- 如权利要求16所述的计算机可读存储介质,其中,所述利用所述目标声谱图集对预构建的深度学习网络模型进行训练,得到用户状态识别模型,包括:将所述目标声谱图集随机划分为训练集及测试集;利用所述训练集对所述深度学习网络模型进行训练得到初始识别模型;根据所述测试集对所述初始识别模型进行测试得到损失值;当所述损失值大于预设阈值时返回所述将所述目标声谱图集随机划分为训练集及测试集步骤;当所述损失值小于或等于预设阈值时,将所述初始识别模型作为用户状态识别模型。
- 如权利要求19所述的计算机可读存储介质,其中,所述将所述目标声谱图集随机划分为训练集及测试集,包括:将所述目标声谱图集中的每个目标声谱图按照对应的初始标签进行分类,得到对应的分类目标声谱图集;从所述分类目标声谱图集中随机取出预设数量的目标声谱图作为测试子集,将所述分类声谱图集中所述测试子集的补集作为训练子集;汇总所有的所述训练子集得到训练集;汇总所有的所述测试子集得到测试集。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011074898.9A CN112233700A (zh) | 2020-10-09 | 2020-10-09 | 基于音频的用户状态识别方法、装置及存储介质 |
| CN202011074898.9 | 2020-10-09 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2021189903A1 true WO2021189903A1 (zh) | 2021-09-30 |
Family
ID=74120698
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2020/131983 Ceased WO2021189903A1 (zh) | 2020-10-09 | 2020-11-27 | 基于音频的用户状态识别方法、装置、电子设备及存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112233700A (zh) |
| WO (1) | WO2021189903A1 (zh) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114913860A (zh) * | 2022-04-27 | 2022-08-16 | 中国工商银行股份有限公司 | 声纹识别方法、装置、计算机设备、存储介质及程序产品 |
| CN115221350A (zh) * | 2022-07-29 | 2022-10-21 | 平安科技(深圳)有限公司 | 一种基于少样本度量学习的事件音频检测方法及系统 |
| CN115547339A (zh) * | 2022-08-10 | 2022-12-30 | 深圳市声扬科技有限公司 | 语音处理方法、处理装置、电子设备及存储介质 |
| CN116403572A (zh) * | 2023-05-04 | 2023-07-07 | 中国第一汽车股份有限公司 | 一种语音识别方法、装置、设备和存储介质 |
| CN116434288A (zh) * | 2021-12-31 | 2023-07-14 | 丰图科技(深圳)有限公司 | 状态识别方法、装置、终端和存储介质 |
| CN116798408A (zh) * | 2022-03-14 | 2023-09-22 | 中国移动通信集团设计院有限公司 | 语音识别方法、终端设备及计算机可读存储介质 |
| CN117476036A (zh) * | 2023-12-27 | 2024-01-30 | 广州声博士声学技术有限公司 | 一种环境噪声识别方法、系统、设备和介质 |
| CN118410332A (zh) * | 2023-12-27 | 2024-07-30 | 梅州市金航科技有限公司 | 基于无监督领域自适应的舵机实时故障诊断方法及装置 |
| CN120853617A (zh) * | 2025-09-19 | 2025-10-28 | 福建睿芯科技有限公司 | 一种基于声纹识别模型的设备工作状态识别方法 |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114049637A (zh) * | 2021-11-10 | 2022-02-15 | 重庆大学 | 一种目标识别模型的建立方法、系统、电子设备及介质 |
| CN116509371B (zh) * | 2022-01-21 | 2026-03-17 | 华为技术有限公司 | 一种音频检测的方法及电子设备 |
| CN114373484A (zh) * | 2022-03-22 | 2022-04-19 | 南京邮电大学 | 语音驱动的帕金森病多症状特征参数的小样本学习方法 |
| CN114722884B (zh) * | 2022-06-08 | 2022-09-30 | 深圳市润东来科技有限公司 | 基于环境音的音频控制方法、装置、设备及存储介质 |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104321015A (zh) * | 2012-03-29 | 2015-01-28 | 昆士兰大学 | 用于处理患者声音的方法与装置 |
| CN106073706A (zh) * | 2016-06-01 | 2016-11-09 | 中国科学院软件研究所 | 一种面向简易精神状态量表的个性化信息和音频数据分析方法及系统 |
| CN106202952A (zh) * | 2016-07-19 | 2016-12-07 | 南京邮电大学 | 一种基于机器学习的帕金森疾病诊断方法 |
| CN106847262A (zh) * | 2016-12-28 | 2017-06-13 | 华中农业大学 | 一种猪呼吸道疾病自动识别报警方法 |
| WO2019023879A1 (zh) * | 2017-07-31 | 2019-02-07 | 深圳和而泰智能家居科技有限公司 | 咳嗽声音识别方法、设备和存储介质 |
| WO2019119050A1 (en) * | 2017-12-21 | 2019-06-27 | The University Of Queensland | A method for analysis of cough sounds using disease signatures to diagnose respiratory diseases |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108205535A (zh) * | 2016-12-16 | 2018-06-26 | 北京酷我科技有限公司 | 情感标注的方法及其系统 |
| CN111666960B (zh) * | 2019-03-06 | 2024-01-19 | 南京地平线机器人技术有限公司 | 图像识别方法、装置、电子设备及可读存储介质 |
-
2020
- 2020-10-09 CN CN202011074898.9A patent/CN112233700A/zh active Pending
- 2020-11-27 WO PCT/CN2020/131983 patent/WO2021189903A1/zh not_active Ceased
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104321015A (zh) * | 2012-03-29 | 2015-01-28 | 昆士兰大学 | 用于处理患者声音的方法与装置 |
| CN106073706A (zh) * | 2016-06-01 | 2016-11-09 | 中国科学院软件研究所 | 一种面向简易精神状态量表的个性化信息和音频数据分析方法及系统 |
| CN106202952A (zh) * | 2016-07-19 | 2016-12-07 | 南京邮电大学 | 一种基于机器学习的帕金森疾病诊断方法 |
| CN106847262A (zh) * | 2016-12-28 | 2017-06-13 | 华中农业大学 | 一种猪呼吸道疾病自动识别报警方法 |
| WO2019023879A1 (zh) * | 2017-07-31 | 2019-02-07 | 深圳和而泰智能家居科技有限公司 | 咳嗽声音识别方法、设备和存储介质 |
| WO2019119050A1 (en) * | 2017-12-21 | 2019-06-27 | The University Of Queensland | A method for analysis of cough sounds using disease signatures to diagnose respiratory diseases |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116434288A (zh) * | 2021-12-31 | 2023-07-14 | 丰图科技(深圳)有限公司 | 状态识别方法、装置、终端和存储介质 |
| CN116798408A (zh) * | 2022-03-14 | 2023-09-22 | 中国移动通信集团设计院有限公司 | 语音识别方法、终端设备及计算机可读存储介质 |
| CN114913860A (zh) * | 2022-04-27 | 2022-08-16 | 中国工商银行股份有限公司 | 声纹识别方法、装置、计算机设备、存储介质及程序产品 |
| CN115221350A (zh) * | 2022-07-29 | 2022-10-21 | 平安科技(深圳)有限公司 | 一种基于少样本度量学习的事件音频检测方法及系统 |
| CN115547339A (zh) * | 2022-08-10 | 2022-12-30 | 深圳市声扬科技有限公司 | 语音处理方法、处理装置、电子设备及存储介质 |
| CN116403572A (zh) * | 2023-05-04 | 2023-07-07 | 中国第一汽车股份有限公司 | 一种语音识别方法、装置、设备和存储介质 |
| CN117476036A (zh) * | 2023-12-27 | 2024-01-30 | 广州声博士声学技术有限公司 | 一种环境噪声识别方法、系统、设备和介质 |
| CN117476036B (zh) * | 2023-12-27 | 2024-04-09 | 广州声博士声学技术有限公司 | 一种环境噪声识别方法、系统、设备和介质 |
| CN118410332A (zh) * | 2023-12-27 | 2024-07-30 | 梅州市金航科技有限公司 | 基于无监督领域自适应的舵机实时故障诊断方法及装置 |
| CN120853617A (zh) * | 2025-09-19 | 2025-10-28 | 福建睿芯科技有限公司 | 一种基于声纹识别模型的设备工作状态识别方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112233700A (zh) | 2021-01-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021189903A1 (zh) | 基于音频的用户状态识别方法、装置、电子设备及存储介质 | |
| WO2022105179A1 (zh) | 生物特征图像识别方法、装置、电子设备及可读存储介质 | |
| WO2021232594A1 (zh) | 语音情绪识别方法、装置、电子设备及存储介质 | |
| CN112447189A (zh) | 语音事件检测方法、装置、电子设备及计算机存储介质 | |
| WO2022121176A1 (zh) | 语音合成方法、装置、电子设备及可读存储介质 | |
| CN113205814B (zh) | 语音数据标注方法、装置、电子设备及存储介质 | |
| WO2021189855A1 (zh) | 基于ct序列的图像识别方法、装置、电子设备及介质 | |
| CN113157739B (zh) | 跨模态检索方法、装置、电子设备及存储介质 | |
| WO2022222943A1 (zh) | 科室推荐方法、装置、电子设备及存储介质 | |
| WO2022141867A1 (zh) | 语音识别方法、装置、电子设备及可读存储介质 | |
| CN113961473A (zh) | 数据测试方法、装置、电子设备及计算机可读存储介质 | |
| CN112581227A (zh) | 产品推荐方法、装置、电子设备及存储介质 | |
| WO2022194062A1 (zh) | 疾病标签检测方法、装置、电子设备及存储介质 | |
| CN113065607A (zh) | 图像检测方法、装置、电子设备及介质 | |
| CN111859985B (zh) | Ai客服模型测试方法、装置、电子设备及存储介质 | |
| CN111738005A (zh) | 命名实体对齐方法、装置、电子设备及可读存储介质 | |
| CN114708461A (zh) | 基于多模态学习模型的分类方法、装置、设备及存储介质 | |
| CN114511569B (zh) | 基于肿瘤标志物的医学图像识别方法、装置、设备及介质 | |
| CN111814743A (zh) | 笔迹识别方法、装置及计算机可读存储介质 | |
| CN111651292A (zh) | 数据校验方法、装置、电子设备及计算机可读存储介质 | |
| CN116521867B (zh) | 文本聚类方法、装置、电子设备及存储介质 | |
| CN116564322A (zh) | 语音转换方法、装置、设备及存储介质 | |
| CN116486972A (zh) | 电子病历生成方法、装置、设备及存储介质 | |
| CN113704405B (zh) | 基于录音内容的质检评分方法、装置、设备及存储介质 | |
| CN112328796B (zh) | 文本聚类方法、装置、设备及计算机可读存储介质 |
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: 20927189 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 20927189 Country of ref document: EP Kind code of ref document: A1 |