Voice control execution method and device, electronic equipment and storage medium

Abstract

The invention provides a voice control execution method and device, electronic equipment and a storage medium, and relates to the technical field of voice processing, and the main technical scheme comprises the steps: carrying out the recognition of a to-be-recognized voice through a preset acoustic model in a voice recognition model, obtaining a posterior probability corresponding to each frame of voice in the to-be-recognized voice, and carrying out the recognition of the to-be-recognized voice; the posterior probability is the occurrence probability of phoneme information corresponding to each frame of voice in the to-be-recognized voice; calling a preset entity word extraction model in the speech recognition model, decoding the posterior probability corresponding to each frame of speech, and determining execution attribute information corresponding to the speech to be recognized; and controlling to execute the voice to be recognized according to the recognition result of the execution attribute information. Compared with the prior art, the embodiment of the disclosure uses the preset entity word extraction model in combination with the posterior probability of the to-be-recognized speech, so that the functions of a language model, a decoder and a word segmentation model are realized, and the overall composition structure of the offline instruction word system is simplified.

Description

Technical Field

[0001] The present disclosure relates to the field of voice processing technology, and in particular to a method and device for executing voice control, an electronic device, and a storage medium. Background Art

[0002] With the progress of the times and the development of science and technology, more and more electronic devices can be controlled through voice dialogue. At present, there are two types of control when performing voice control, one is network control type and the other is offline control type. For network control type, in the scenario of network interruption, the device cannot be connected to the network, which directly leads to the paralysis of electronic devices; while the electronic devices of offline control type contain offline command word systems, which are directly embedded in electronic devices. The offline command word systems do not need to be connected to the network and can run locally, and are not affected by network reasons.

[0003] However, in the related art, the offline command word system obtains the audio recognition result through the acoustic model, language model and decoder decoding, then extracts the control command in the sentence through the word segmentation model, and then executes the corresponding voice control function according to the control command. The overall structure is relatively complex. Summary of the invention

[0004] The present invention provides a method and device for executing voice control, an electronic device and a storage medium, and its main purpose is to solve the problem that the overall structure of the offline instruction word system in the related art is relatively complex.

[0005] According to a first aspect of the present disclosure, a method for executing voice control is provided, comprising:

[0006] Recognize the speech to be recognized based on the preset acoustic model in the speech recognition model, and obtain the posterior probability corresponding to each frame of speech in the speech to be recognized, wherein the posterior probability is the probability of occurrence of the phoneme information corresponding to each frame of speech in the speech to be recognized;

[0007] Calling a preset entity word extraction model in the speech recognition model, decoding the posterior probability corresponding to each frame of speech, and determining the execution attribute information corresponding to the speech to be recognized;

[0008] According to the recognition result of the execution attribute information, the execution of the speech to be recognized is controlled.

[0009] Optionally, the recognizing the speech to be recognized based on a preset acoustic model in the speech recognition model to obtain the posterior probability corresponding to each frame of speech in the speech to be recognized includes:

[0010] Acquiring phoneme information corresponding to each frame of speech in the speech to be recognized based on a preset acoustic model in the speech recognition model;

[0011] The posterior probability corresponding to the phoneme information corresponding to each frame of speech is calculated using a preset probability algorithm.

[0012] Optionally, before calling the preset entity word extraction model in the speech recognition model and decoding the posterior probability corresponding to each frame of speech, the method includes:

[0013] Training the preset entity word extraction model to obtain the trained preset entity word extraction model;

[0014] The trained preset entity word extraction model is loaded into a preset speech recognition device.

[0015] Optionally, the training of the preset entity word extraction model includes:

[0016] Obtaining a preset amount of speech data for training;

[0017] Inputting the training speech data into the preset entity word extraction model to obtain training execution attribute information corresponding to the training speech data;

[0018] Based on the training execution attribute information, a loss value of the preset entity word extraction model is calculated by a preset loss function, wherein the loss value is a value that measures the degree of difference between the predicted execution attribute information and the actual execution attribute information of the preset entity word extraction model;

[0019] Based on the loss value, the preset entity word extraction model is optimized by a preset optimization algorithm to obtain the trained preset entity word extraction model.

[0020] Optionally, before recognizing the speech to be recognized based on a preset acoustic model in the speech recognition model and obtaining the posterior probability corresponding to each frame of speech in the speech to be recognized, the method includes:

[0021] The preset acoustic model long short-term memory network is loaded into the preset speech recognition device, and the preset acoustic model long short-term memory network encodes the speech to be recognized to obtain the phoneme vector of each frame of speech, and the phoneme vector corresponds to the posterior probability of the speech.

[0022] Optionally, the execution attribute information includes: expectation information, domain information and classification information; wherein,

[0023] The expected information is the action and / or control expected to be performed in the speech to be recognized;

[0024] The domain information is customized information about the type of the speech to be recognized;

[0025] The classification information is the application scenario classification corresponding to the speech to be recognized.

[0026] According to a second aspect of the present disclosure, there is provided a voice control execution device, comprising:

[0027] A recognition unit, configured to recognize the speech to be recognized based on a preset acoustic model in the speech recognition model, and obtain a posterior probability corresponding to each frame of speech in the speech to be recognized, wherein the posterior probability is a probability of occurrence of phoneme information corresponding to each frame of speech in the speech to be recognized;

[0028] A decoding unit, used to call a preset entity word extraction model in the speech recognition model, decode the posterior probability corresponding to each frame of speech, and determine the execution attribute information corresponding to the speech to be recognized;

[0029] An execution unit is used to control the execution of the speech to be recognized according to the recognition result of the execution attribute information.

[0030] Optionally, the identification unit includes:

[0031] An acquisition module, used for acquiring phoneme information corresponding to each frame of speech in the speech to be recognized based on a preset acoustic model in the speech recognition model;

[0032] The calculation module is used to calculate the posterior probability corresponding to the phoneme information corresponding to each frame of speech through a preset probability algorithm.

[0033] Optionally, the device further comprises:

[0034] A training unit, configured to train a preset entity word extraction model before the determination unit calls a preset entity word extraction algorithm and determines the execution attribute information corresponding to the speech to be recognized according to the posterior probability corresponding to each frame of speech, so as to obtain the trained preset entity word extraction model;

[0035] The loading unit is used to load the trained preset entity word extraction model into a preset speech recognition device.

[0036] Optionally, the training unit includes:

[0037] An acquisition module, used to acquire a preset amount of speech data for training;

[0038] An input module, used for inputting the training speech data into the preset entity word extraction model to obtain the training execution attribute information corresponding to the training speech data;

[0039] A calculation module, used to calculate the loss value of the preset entity word extraction model based on the training execution attribute information through a preset loss function, wherein the loss value is a value that measures the degree of difference between the predicted execution attribute information and the actual execution attribute information of the preset entity word extraction model;

[0040] The optimization module is used to optimize the preset entity word extraction model based on the loss value through a preset optimization algorithm to obtain the trained preset entity word extraction model.

[0041] Optionally, the loading unit is also used to load a preset acoustic model long short-term memory network into a preset speech recognition device before the recognition unit recognizes the speech to be recognized, and the preset acoustic model long short-term memory network encodes the speech to be recognized to obtain a phoneme vector for each frame of speech, and the phoneme vector corresponds to the posterior probability of the speech.

[0042] According to a third aspect of the present disclosure, a vehicle is provided, wherein the vehicle includes the voice control execution device as described in the second aspect of the present disclosure.

[0043] According to a fourth aspect of the present disclosure, there is provided an electronic device, including:

[0044] at least one processor; and

[0045] a memory communicatively connected to the at least one processor; wherein,

[0046] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect.

[0047] According to a fifth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method described in the first aspect.

[0048] According to a sixth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0049] The execution method and device of voice control, electronic device and storage medium provided by the present disclosure recognize the voice to be recognized based on the preset acoustic model in the voice recognition model, obtain the posterior probability corresponding to each frame of the voice to be recognized, and the posterior probability is the probability of the occurrence of the phoneme information corresponding to each frame of the voice to be recognized; call the preset entity word extraction model in the voice recognition model, decode the posterior probability corresponding to each frame of the voice, and determine the execution attribute information corresponding to the voice to be recognized; according to the recognition result of the execution attribute information, control the execution of the voice to be recognized. Compared with the related art, the embodiment of the present disclosure uses the preset entity word extraction model in combination with the posterior probability of the voice to be recognized, realizes the functions of the language model, decoder and word segmentation model, and simplifies the overall composition structure of the offline instruction word system.

[0050] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0052] Figure 1 A flowchart of a method for executing voice control provided by an embodiment of the present disclosure;

[0053] Figure 2 A schematic diagram of the structure of a voice control execution device provided by an embodiment of the present disclosure;

[0054] Figure 3 A schematic diagram of the structure of another voice control execution device provided by an embodiment of the present disclosure;

[0055] Figure 4 A schematic block diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0056] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0057] The following describes the voice control execution method and device, electronic device and storage medium according to the embodiments of the present disclosure with reference to the accompanying drawings.

[0058] Figure 1 A flowchart of a method for executing voice control provided in an embodiment of the present disclosure is provided.

[0059] like Figure 1 As shown, the method comprises the following steps:

[0060] Step 101, recognize the speech to be recognized based on the preset acoustic model in the speech recognition model, and obtain the posterior probability corresponding to each frame of speech in the speech to be recognized, wherein the posterior probability is the probability of occurrence of the phoneme information corresponding to each frame of speech in the speech to be recognized.

[0061] The present disclosure can be applied to a variety of offline scenarios and supports a variety of voice customization, such as: voice customization under functional and proprietary industry functions: integrated stove scenario 'turn on heating' 'wind speed three gears', smart toilet scenario: 'toilet flushing', massage chair scenario 'increase strength' 'decompression mode', vehicle scenario 'turn on air conditioning' 'turn on music', etc. At the same time, generalized voice can also be executed, such as: 'help me turn it up a little bit', 'set the temperature to 20 degrees' and other offline voice commands.

[0062] In the embodiment of the present disclosure, the acoustic model in the speech recognition model is used to recognize the speech to be recognized, wherein the posterior probability is a probability value, and the representation method is to represent it with a value. For details about the posterior probability, please refer to the detailed description in the related art, so it will not be repeated here.

[0063] Step 102, calling a preset entity word extraction model in the speech recognition model, decoding the posterior probability corresponding to each frame of speech, and determining the execution attribute information corresponding to the speech to be recognized.

[0064] In the embodiment of the present disclosure, the execution attribute information may be in text form or in other character string forms. Specifically, the embodiment of the present disclosure does not limit the form of the execution attribute information.

[0065] The execution attribute information includes: expected information, domain information and classification information. In the execution attribute information of the speech to be recognized, the amount of domain information can be zero, while the amount of expected information and classification information cannot be zero. At the same time, in the execution attribute information of the speech to be recognized, the amount of expected information, domain information and classification information can be multiple. Specifically, the embodiments of the present disclosure are not limited by the amount of expected information, domain information and classification information in the speech to be recognized.

[0066] Step 103: Control the execution of the speech to be recognized according to the recognition result of the execution attribute information.

[0067] In the embodiment of the present disclosure, the execution attribute information needs to be output to the execution module. After the execution module performs recognition processing on the execution attribute information of the speech to be recognized, it controls the execution of the speech to be recognized containing the execution attribute information. Regarding the recognition processing of the execution attribute information of the speech to be recognized by the execution module, the details can be referred to the detailed description in the related technology, so it will not be repeated here one by one.

[0068] The execution method of voice control provided by the present disclosure recognizes the speech to be recognized based on the preset acoustic model in the speech recognition model, obtains the posterior probability corresponding to each frame of speech in the speech to be recognized, and the posterior probability is the probability of the occurrence of the phoneme information corresponding to each frame of speech in the speech to be recognized; calls the preset entity word extraction model in the speech recognition model, decodes the posterior probability corresponding to each frame of speech, and determines the execution attribute information corresponding to the speech to be recognized; and controls the execution of the speech to be recognized according to the recognition result of the execution attribute information. Compared with the related art, the embodiment of the present disclosure uses the preset entity word extraction model in combination with the posterior probability of the speech to be recognized, realizes the functions of the language model, decoder and word segmentation model, and simplifies the overall composition structure of the offline instruction word system.

[0069] In one possible implementation of the disclosed embodiment, the essence of the posterior probability corresponding to each frame of speech in the speech to be recognized is: the posterior probability corresponding to the phoneme information corresponding to each frame of speech in the speech to be recognized. The acquisition of the posterior probability can be implemented in the following ways but not limited to: acquiring the phoneme information corresponding to each frame of speech in the speech to be recognized based on the preset acoustic model in the speech recognition model; calculating the posterior probability corresponding to the phoneme information corresponding to each frame of speech by a preset probability algorithm. Among them, the phoneme information is the smallest speech unit divided according to the natural properties of the speech to be recognized. From the perspective of acoustic properties, the phoneme information is the smallest speech unit divided from the perspective of sound quality. From the perspective of physiological properties, one pronunciation action forms one phoneme information. Specifically, regarding the phoneme information, please refer to the detailed description in the relevant technology, so it will not be repeated here.

[0070] The preset probability algorithm is a user-selected probability algorithm, such as Bayes' theorem, maximum likelihood estimation method, maximum a posteriori estimation method, etc. Specifically, the selection of the preset probability algorithm can be determined according to the actual application situation, and the embodiments of the present disclosure do not limit it.

[0071] Related to the above embodiment, regarding the acquisition of the preset acoustic model in the speech recognition model, the following method can be used but is not limited to: the preset acoustic model long short-term memory network is loaded into the preset speech recognition device, and the preset acoustic model long short-term memory network encodes the speech to be recognized to obtain the phoneme vector of each frame of speech, and the phoneme vector corresponds to the posterior probability of the speech. Among them, the long short-term memory network can be used as the preset acoustic model. Specifically, for the long short-term memory network, please refer to the detailed description in the relevant technology, so it will not be repeated here.

[0072] In one possible implementation of the embodiment of the present disclosure, it is necessary to perform model training on the preset entity word extraction model in the speech recognition model so that the preset entity word extraction model can realize the corresponding function. Therefore, in order to obtain the preset entity word extraction model that can realize the corresponding function, the following method can be adopted but not limited to: training the preset entity word extraction model to obtain the trained preset entity word extraction model; loading the trained preset entity word extraction model into a preset speech recognition device. The preset speech recognition device is the device applied to the offline scene of the embodiment of the present disclosure, that is, the preset speech recognition device is the device applied to the offline scene of the embodiment of the present disclosure.

[0073] Related to the above-mentioned embodiment, the training of the preset entity word extraction model can be implemented by but not limited to the following methods: obtaining a preset amount of training voice data; inputting the training voice data into the preset entity word extraction model to obtain training execution attribute information corresponding to the training voice data; based on the training execution attribute information, calculating the loss value of the preset entity word extraction model through a preset loss function, wherein the loss value is a value that measures the degree of difference between the predicted execution attribute information and the actual execution attribute information of the preset entity word extraction model; based on the loss value, optimizing the preset entity word extraction model through a preset optimization algorithm to obtain the trained preset entity word extraction model.

[0074] In the embodiments of the present disclosure, the preset number refers to: a custom set quantity value, and in the training of the preset entity word extraction model, when the amount of training voice data is within a certain range, the model training effect is best. When the amount of training voice data is too much, the training voice data will affect each other, resulting in a high misrecognition rate of the preset entity word extraction model. When the amount of training voice data is too small, due to insufficient data during training, the preset entity word extraction model will also have a high misrecognition rate. Specifically, the amount of training voice data can be determined according to the actual application situation, and the embodiments of the present disclosure do not limit it.

[0075] The preset loss function is a user-selected operation function, such as: mean square error function, mean absolute error function, quantile loss function, etc. The preset optimization algorithm is a user-selected algorithm, such as: gradient descent method, Newton method, quasi-Newton method, improved iterative scaling method, etc. Specifically, the selection of the preset loss function and the preset optimization algorithm can be determined according to the actual application situation, and the embodiments of the present disclosure do not limit it.

[0076] In one implementable manner of the embodiment of the present disclosure, as a refinement of the above-mentioned step 102, the execution attribute information includes: expectation information, domain information and classification information; wherein the expectation information is the action and / or control expected to be performed in the speech to be recognized; the domain information is the customized type information of the speech to be recognized; and the classification information is the application scenario classification corresponding to the speech to be recognized.

[0077] For example, if the speech to be recognized is "turn on the TV", then in the execution attribute information of the speech to be recognized, the expected information is "turn on", the domain information is "function", and the classification information is "TV". If the speech to be recognized is "air conditioner wind speed three gears", then in the execution attribute information of the speech to be recognized, the expected information is "adjust", the domain information is "gear", and the classification information is "air conditioner".

[0078] It should be noted here that the domain information of the same type of speech to be recognized is the same, and the domain information can be customized. When training the preset entity word extraction model, the domain information can be customized. For example, the speech to be recognized for training is the third gear of air-conditioning wind speed, the second gear of fan, etc. When training the preset entity word extraction model, the speech to be recognized for training will be classified into the same category, and the domain information can be customized as gear. At this time, when the trained preset entity word extraction model determines the execution attribute information corresponding to the speech to be recognized, if the speech to be recognized is the third gear of air-conditioning wind speed, the second gear of fan, etc., the output domain information is gear. Specifically, the type of speech to be recognized and the customized naming of the domain information can be determined according to the actual application situation, and the embodiments of the present disclosure are not limited.

[0079] In practical applications, since most speech recognitions have a high recognition rate in quiet scenes, but a low recognition rate in scenes with noise or high background noise, before recognizing the speech to be recognized, the following method may be used but is not limited to: performing noise reduction processing on the original speech to obtain the speech to be recognized. By performing noise reduction processing on the original speech, the recognition rate of the speech to be recognized can be greatly improved.

[0080] In summary, the embodiments of the present disclosure can achieve the following effects:

[0081] 1. The preset entity word extraction model is used to realize the functions of the language model, decoder and word segmentation model, which simplifies the overall structure of the offline instruction word system, reduces the memory and resource usage, and can be run under low resources.

[0082] 2. By performing noise reduction processing on the original speech, the speech to be recognized is obtained, which greatly improves the recognition rate of the speech to be recognized.

[0083] Corresponding to the above-mentioned voice control execution method, the present invention also provides a voice control execution device. Since the device embodiment of the present invention corresponds to the above-mentioned method embodiment, the details not disclosed in the device embodiment can be referred to the above-mentioned method embodiment, and will not be repeated in the present invention.

[0084] Figure 2 A schematic diagram of the structure of a voice control execution device provided in an embodiment of the present disclosure, such as Figure 2 As shown, including:

[0085] The recognition unit 21 is used to recognize the speech to be recognized based on the preset acoustic model in the speech recognition model, and obtain the posterior probability corresponding to each frame of speech in the speech to be recognized, wherein the posterior probability is the probability of occurrence of the phoneme information corresponding to each frame of speech in the speech to be recognized;

[0086] A decoding unit 22 is used to call a preset entity word extraction model in the speech recognition model, decode the posterior probability corresponding to each frame of speech, and determine the execution attribute information corresponding to the speech to be recognized;

[0087] The execution unit 23 is used to control the execution of the speech to be recognized according to the recognition result of the execution attribute information.

[0088] The speech control execution device provided by the present disclosure recognizes the speech to be recognized based on the preset acoustic model in the speech recognition model, obtains the posterior probability corresponding to each frame of speech in the speech to be recognized, and the posterior probability is the probability of the occurrence of the phoneme information corresponding to each frame of speech in the speech to be recognized; calls the preset entity word extraction model in the speech recognition model, decodes the posterior probability corresponding to each frame of speech, and determines the execution attribute information corresponding to the speech to be recognized; and controls the execution of the speech to be recognized according to the recognition result of the execution attribute information. Compared with the related art, the embodiment of the present disclosure uses the preset entity word extraction model in combination with the posterior probability of the speech to be recognized, realizes the functions of the language model, decoder and word segmentation model, and simplifies the overall composition structure of the offline instruction word system.

[0089] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 3As shown, the identification unit 21 includes:

[0090] An acquisition module 211 is used to acquire phoneme information corresponding to each frame of speech in the speech to be recognized based on a preset acoustic model in the speech recognition model;

[0091] The calculation module 212 is used to calculate the posterior probability corresponding to the phoneme information corresponding to each frame of speech by using a preset probability algorithm.

[0092] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 3 As shown, the device also includes:

[0093] A training unit 24 is used to train a preset entity word extraction model before the determination unit 22 calls the preset entity word extraction algorithm and determines the execution attribute information corresponding to the speech to be recognized according to the posterior probability corresponding to each frame of speech, so as to obtain the trained preset entity word extraction model, wherein the preset entity word extraction model includes the preset entity word extraction algorithm;

[0094] The loading unit 25 is used to load the trained preset entity word extraction model into a preset speech recognition device.

[0095] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 3 As shown, the training unit 24 includes:

[0096] An acquisition module 241 is used to acquire a preset amount of training speech data;

[0097] An input module 242, used for inputting the training speech data into the preset entity word extraction model to obtain the training execution attribute information corresponding to the training speech data;

[0098] A calculation module 243 is used to calculate the loss value of the preset entity word extraction model based on the training execution attribute information through a preset loss function, wherein the loss value is a value for measuring the degree of difference between the predicted execution attribute information and the actual execution attribute information of the preset entity word extraction model;

[0099] The optimization module 244 is used to optimize the preset entity word extraction model based on the loss value through a preset optimization algorithm to obtain the trained preset entity word extraction model.

[0100] Furthermore, in a possible implementation of the embodiment of the present disclosure, the loading unit 25 is also used to load a preset acoustic model long short-term memory network into a preset speech recognition device before the recognition unit 21 recognizes the speech to be recognized, and the preset acoustic model long short-term memory network encodes the speech to be recognized to obtain a phoneme vector for each frame of speech, and the phoneme vector corresponds to the posterior probability of the speech.

[0101] In an embodiment of the present disclosure, a vehicle is also provided, wherein the vehicle is equipped with a voice-controlled execution device.

[0102] It should be noted that the above explanation of the method embodiment is also applicable to the device of the embodiment of the present disclosure, and the principle is the same, which is no longer limited in the embodiment of the present disclosure.

[0103] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0104] Figure 4 A schematic block diagram of an example electronic device 400 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0105] like Figure 4 As shown, the device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 402 or a computer program loaded from a storage unit 408 to a RAM (Random Access Memory) 403. In the RAM 403, various programs and data required for the operation of the device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An I / O (Input / Output) interface 405 is also connected to the bus 404.

[0106] A number of components in the device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, an optical disk, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0107] The computing unit 401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Units), various dedicated AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, a DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as the execution method of voice control. For example, in some embodiments, the execution method of voice control may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 400 via the ROM 402 and / or the communication unit 409. When the computer program is loaded into the RAM 403 and executed by the computing unit 401, one or more steps of the method described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to execute the aforementioned voice control execution method in any other appropriate manner (for example, by means of firmware).

[0108] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application Specific Standard Products), SOCs (System On Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that may be executed and / or interpreted on a programmable system including at least one programmable processor that may be a dedicated or general-purpose programmable processor that may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0109] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0110] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include electrical connections based on one or more lines, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only-Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0111] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0112] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: LAN (Local Area Network), WAN (Wide Area Network), the Internet, and blockchain networks.

[0113] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0114] It should be noted that artificial intelligence is a discipline that studies how computers can simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), and includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0115] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0116] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for executing voice control, characterized in that: include: Recognize the speech to be recognized based on the preset acoustic model in the speech recognition model, and obtain the posterior probability corresponding to each frame of speech in the speech to be recognized, wherein the posterior probability is the probability of occurrence of the phoneme information corresponding to each frame of speech in the speech to be recognized; Calling a preset entity word extraction model in the speech recognition model, decoding the posterior probability corresponding to each frame of speech, and determining the execution attribute information corresponding to the speech to be recognized; According to the recognition result of the execution attribute information, the execution of the speech to be recognized is controlled.

2. The method according to claim 1, characterized in that Recognizing the speech to be recognized based on the preset acoustic model in the speech recognition model to obtain the posterior probability corresponding to each frame of speech in the speech to be recognized includes: Acquiring phoneme information corresponding to each frame of speech in the speech to be recognized based on a preset acoustic model in the speech recognition model; The posterior probability corresponding to the phoneme information corresponding to each frame of speech is calculated using a preset probability algorithm.

3. The method according to claim 1, characterized in that Before calling the preset entity word extraction model in the speech recognition model to decode the posterior probability corresponding to each frame of speech, the method further includes: Training the preset entity word extraction model to obtain the trained preset entity word extraction model; The trained preset entity word extraction model is loaded into a preset speech recognition device.

4. The method according to claim 3, characterized in that The training of the preset entity word extraction model includes: Obtaining a preset amount of speech data for training; Inputting the training speech data into the preset entity word extraction model to obtain training execution attribute information corresponding to the training speech data; Based on the training execution attribute information, a loss value of the preset entity word extraction model is calculated by a preset loss function, wherein the loss value is a value that measures the degree of difference between the predicted execution attribute information and the actual execution attribute information of the preset entity word extraction model; Based on the loss value, the preset entity word extraction model is optimized by a preset optimization algorithm to obtain the trained preset entity word extraction model.

5. The method according to claim 1, characterized in that Before recognizing the speech to be recognized based on the preset acoustic model in the speech recognition model and obtaining the posterior probability corresponding to each frame of speech in the speech to be recognized, the method further includes: The preset acoustic model long short-term memory network is loaded into the preset speech recognition device, and the preset acoustic model long short-term memory network encodes the speech to be recognized to obtain the phoneme vector of each frame of speech, and the phoneme vector corresponds to the posterior probability of the speech.

6. The method according to any one of claims 1 to 5, characterized in that The execution attribute information includes: expectation information, domain information and classification information; wherein, The expected information is the action and / or control expected to be performed in the speech to be recognized; The domain information is customized information about the type of the speech to be recognized; The classification information is the application scenario classification corresponding to the speech to be recognized.

7. A voice-controlled execution device, characterized in that: include: A recognition unit, configured to recognize the speech to be recognized based on a preset acoustic model in the speech recognition model, and obtain a posterior probability corresponding to each frame of speech in the speech to be recognized, wherein the posterior probability is a probability of occurrence of phoneme information corresponding to each frame of speech in the speech to be recognized; A decoding unit, used to call a preset entity word extraction model in the speech recognition model, decode the posterior probability corresponding to each frame of speech, and determine the execution attribute information corresponding to the speech to be recognized; An execution unit is used to control the execution of the speech to be recognized according to the recognition result of the execution attribute information.

8. A vehicle, characterized in that: The vehicle includes the voice control execution device as claimed in claim 7.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-6.

Images