A voice false wake-up recognition method and device, and an electronic device

Abstract

The present disclosure provides a voice false wake-up recognition method and device, and an electronic device, wherein the method comprises: detecting whether the device receives a wake-up voice; when the wake-up voice is detected, performing voice recognition on the wake-up voice; performing false wake-up condition rule matching based on the result of the voice recognition; when the wake-up voice matches the false wake-up condition rule, recognizing the wake-up voice as a false wake-up voice. Through the present disclosure, the problem of low statistical efficiency of voice false wake-up in the related art is solved, which is caused by the fact that the statistical reporting of voice false wake-up recognition depends on the active triggering of the user. Without the active operation of the user, the false wake-up statistical analysis reporting is completed, thereby improving the statistical efficiency of voice false wake-up.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of speech recognition, and in particular to a speech false wake-up recognition method and device and electronic equipment. BACKGROUND

[0002] With the development of speech recognition related technologies, human-computer interaction based on speech has become one of the technologies for measuring whether a terminal is advanced. Recognizing that a speech false wake-up has occurred and reporting statistics are important methods for improving the accuracy of speech recognition.

[0003] Speech false wake-up recognition statistics in related technologies rely on user-initiated triggering, but false wake-up may not be known to the user. Based on user cooperation for active reporting triggering, the reporting cooperation degree of the user will result in low statistical efficiency of speech false wake-up.

[0004] At present, there is no effective solution to the problem that speech false wake-up recognition statistics in related technologies rely on user-initiated triggering, resulting in low statistical efficiency of speech false wake-up. SUMMARY

[0005] The purpose of the present disclosure is to provide a speech false wake-up recognition method, device, electronic equipment and computer readable storage medium to at least solve the problem that speech false wake-up recognition statistics in related technologies rely on user-initiated triggering, resulting in low statistical efficiency of speech false wake-up, in view of the deficiencies in the prior art.

[0006] According to an aspect of the present disclosure, a speech false wake-up recognition method is provided, comprising:

[0007] detecting whether a wake-up speech is received by a device;

[0008] performing speech recognition on the wake-up speech when the wake-up speech is detected;

[0009] performing false wake-up condition rule matching based on the result of the speech recognition;

[0010] recognizing the wake-up speech as a false wake-up speech when the wake-up speech matches the false wake-up condition rule.

[0011] According to another aspect of the present disclosure, a speech false wake-up recognition device is provided, comprising:

[0012] a detection unit configured to detect whether a wake-up speech is received by a device;

[0013] a recognition unit configured to perform speech recognition on the wake-up speech when the wake-up speech is detected;

[0014] The matching unit is configured to perform false wake-up condition rule matching based on the result of the voice recognition.

[0015] The determining unit is configured to determine the wake-up voice as a false wake-up voice when the wake-up voice matches the false wake-up condition rule.

[0016] According to another aspect of the present disclosure, an electronic device is provided, comprising:

[0017] a processor; and

[0018] a memory storing a program,

[0019] wherein the program includes instructions that, when executed by the processor, cause the processor to perform the voice false wake-up recognition method in the present disclosure.

[0020] According to another aspect of the present disclosure, a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the voice false wake-up recognition method in the present disclosure is provided.

[0021] One or more technical solutions provided in the embodiments of the present disclosure determine whether the wake-up voice is a false wake-up voice by performing voice recognition on the wake-up voice when the wake-up voice is detected, and judging whether the wake-up voice is a false wake-up voice based on a false wake-up condition rule. The embodiments of the present disclosure do not require the user to actively report the trigger, but only need to determine the false wake-up voice by performing false wake-up condition rule matching through voice recognition technology, which can solve the problem that the statistical efficiency of voice false wake-up recognition is low due to the dependence of the statistical reporting on the active trigger of the user in the related art, and achieve the technical effect of improving the statistical efficiency of false wake-up voice. BRIEF DESCRIPTION OF DRAWINGS

[0022] More details, features and advantages of the present disclosure are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which:

[0023] Figure 1 A flowchart of a voice false wake-up recognition method according to an exemplary embodiment of the present disclosure is shown;

[0024] Figure 2 A flowchart of a voice false wake-up recognition statistical reporting method based on a condition rule according to a preferred embodiment of the present disclosure is shown;

[0025] Figure 3 A schematic block diagram of a voice false wake-up recognition device according to an exemplary embodiment of the present disclosure is shown;

[0026] Figure 4 A structural block diagram of an exemplary electronic device that can be used to implement the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0027] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be embodied in various forms and should not be interpreted in a limited sense as set forth in the embodiments set forth herein, but rather, the embodiments are provided to facilitate a more complete and thorough understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for illustrative purposes and are not intended to limit the scope of protection of the present disclosure.

[0028] It should be understood that each of the steps described in the method embodiments of the present disclosure can be performed in different orders and / or in parallel. In addition, the method embodiments can include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0029] The term "comprising" and variations thereof as used herein are open-ended, that is "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Related terms will be understood similarly. It is to be noted that the "first", "second", and / or other similar references made herein merely serve to distinguish one concept from another, and do not limit the scope of the application to the functions described in the context of those terms.

[0030] It should be noted that the terms "one", "more than one", and "plurality" are used in an illustrative and not a limiting sense, and those skilled in the art will understand that "one" or "more than one" should be understood as "one or more" unless the context clearly indicates otherwise.

[0031] The names of the messages or information exchanged between the devices in the embodiments of the present disclosure are only for illustrative purposes, and are not intended to limit the scope of the messages or information.

[0032] The scheme of the present disclosure will be described below with reference to the accompanying drawings.

[0033] An incorrect voice wake-up recognition method is provided in the exemplary embodiments of the present disclosure. Figure 1 A flowchart of the incorrect voice wake-up recognition method according to the exemplary embodiments of the present disclosure is shown in FIG. 1, which includes the following steps: Figure 1

[0034] Step S101, detecting whether a wake-up voice is received by the device;

[0035] Step S102, performing voice recognition on the wake-up voice when the wake-up voice is detected; ​

[0036] Step S103, performing false wake-up condition rule matching based on the result of the voice recognition;

[0037] Step S104, when the wake-up voice matches the false wake-up condition rule, identifying the wake-up voice as a false wake-up voice.

[0038] Through the above steps, when a wake-up voice is detected, voice recognition is performed on the wake-up voice, and whether the wake-up voice is a false wake-up voice is determined based on a false wake-up condition rule. Without the user actively reporting the trigger, only the false wake-up condition rule matching through the voice recognition technology can determine the false wake-up voice, which can solve the problem of low statistical efficiency of voice false wake-up in the related art caused by the dependence of voice false wake-up recognition statistics reporting on the active trigger of the user, and achieve the technical effect of improving the statistical efficiency of false wake-up voice.

[0039] In some embodiments, before the step S101 of detecting whether the terminal device receives a wake-up voice, the method can further include: setting a voice false wake-up recognition function switch of the terminal device to an open state; and obtaining an ambient volume before the wake-up voice is detected.

[0040] After the wake-up voice is detected, the method can further include: obtaining voiceprint information of the wake-up voice; and obtaining an ambient volume after the wake-up voice is detected.

[0041] In some embodiments, the step S103 of performing false wake-up condition rule matching based on the result of the voice recognition includes:

[0042] determining whether the result of the voice recognition exists;

[0043] if the result of the voice recognition does not exist, determining whether the voiceprint information of the wake-up voice belongs to recorded common voiceprint information;

[0044] if the voiceprint information of the wake-up voice does not belong to the recorded common voiceprint information, determining that the wake-up voice matches the false wake-up condition rule;

[0045] if the voiceprint information of the wake-up voice belongs to the recorded common voiceprint information, determining whether an ambient volume before the wake-up voice is detected and / or an ambient volume after the wake-up voice is detected is lower than a preset threshold;

[0046] if the ambient volume before the wake-up voice is detected and / or the ambient volume after the wake-up voice is detected is lower than the preset threshold, determining that the wake-up voice matches the false wake-up condition rule.

[0047] The preset threshold can be set or adjusted according to actual needs, which is not limited here.

[0048] If the result of the voice recognition exists, it is determined whether the result of the voice recognition has a corresponding semantic result.

[0049] If the result of the voice recognition has no corresponding semantic result, the step of determining whether the voiceprint information of the wake-up voice belongs to the recorded common voiceprint information is performed.

[0050] In some embodiments, after the wake-up voice is recognized as a false wake-up voice, the following steps can also be included:

[0051] Outputting prompt information, wherein the prompt information is used to prompt the user that the wake-up voice is determined as a false wake-up voice.

[0052] Determining whether a cancel operation of the user is detected, wherein the cancel operation is used to indicate that the wake-up voice is determined as a false wake-up voice is canceled.

[0053] If the cancel operation of the user is detected, the wake-up voice is determined as a false wake-up voice is canceled.

[0054] If the cancel operation of the user is not detected, the wake-up voice is reported for analysis.

[0055] In some embodiments, the wake-up voice is reported for analysis can include:

[0056] Calculating the confidence degree of the wake-up voice determined as a false wake-up voice.

[0057] Obtaining the wake-up voice with a confidence degree higher than a target confidence degree.

[0058] Updating the false wake-up condition rule by using the wake-up voice with the confidence degree higher than the target confidence degree.

[0059] In some embodiments, the wake-up voice is reported for analysis can also include:

[0060] Classifying and analyzing the wake-up voice determined as a false wake-up voice.

[0061] The embodiments of the present application are described and explained below by preferred embodiments.

[0062] The preferred embodiments are based on conditional rule determination. After voice wake-up occurs, a series of preconditions and postconditions are matched to determine whether the voice belongs to a false wake-up, and relevant information is reported.

[0063] The following technical terms are first introduced and explained below:

[0064] ASR: Automatic Speech Recognition, refers to automatic speech recognition technology;

[0065] ASR result: whether the corresponding text is returned to the recording result;

[0066] Ambient volume: the volume captured by the microphone before and after the wake-up;

[0067] Effective intent: whether the ASR returns a corresponding semantic result.

[0068] Figure 2 A flowchart of a method for reporting statistics of condition rule-based voice false wake-up recognition is shown according to a preferred embodiment of the present disclosure, as shown in the figure, the method comprises the following steps: Figure 2

[0069] Step S201, the user opens the condition rule-based voice false wake-up recognition statistical reporting switch;

[0070] Step S202, record the machine ambient volume;

[0071] Step S203, the machine receives a wake-up instruction;

[0072] Step S204, record the wake-up voiceprint information;

[0073] Step S205, wait for the ASR result;

[0074] Step S206, determine whether there is an ASR result; if yes, execute step S207; if no, execute step S208;

[0075] Step S207, determine whether there is an effective intent; if no, execute step S208;

[0076] Step S208, determine whether the wake-up voiceprint is a common voiceprint; if yes, execute step S209; if no, execute step S210;

[0077] Step S209, determine whether the ambient volume before and after the wake-up is lower than the threshold; if yes, execute step S210;

[0078] Step S210, determine that it is a false wake-up;

[0079] Step S211, non-disturbing way to prompt the user that this wake-up is determined to be a false wake-up;

[0080] Step S212, determine whether the user has a cancel operation, such as exiting the prompt interface or making a voice wake-up; if yes, execute step S213; if no, execute step S214;

[0081] Step S213, cancel this false wake-up determination; ​

[0082] Step S214, the timing of reporting false wake-up information;

[0083] Step S215, the server uses big data statistical analysis false wake-up, false wake-up data classification research;

[0084] Step S216, artificial review false wake-up confidence high data, mark whether it belongs to false wake-up;

[0085] Step S217, iteration optimization false wake-up model.

[0086] It should be noted that, Figure 2 False wake-up condition rule matching in the above steps S206 to S209.

[0087] The preferred embodiment provides a voice false wake-up recognition statistical reporting method based on condition rules, which combines pre-wake-up (environmental volume), wake-up (voiceprint), post-wake-up (ASR, intent, etc.) condition rule matching, without the need for user active operation, to complete false wake-up statistical analysis reporting. The interaction and mode of the voice false wake-up recognition statistical reporting based on condition rules do not rely on user active operation, at the same time, the voice product is made as an intelligent system for self-diagnosis and optimization, which embodies the high-tech feeling of the product.

[0088] It should be noted that the steps shown in the above process or the flowchart of the accompanying drawings can be executed in a computer system such as a group of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from here.

[0089] The exemplary embodiments of the present disclosure also provide a voice false wake-up recognition device, which is used to implement the above-mentioned embodiments and preferred embodiments, and will not be described again. As used below, the terms "module", "unit", "sub-unit" and the like can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware implementation is also possible and contemplated.

[0090] Figure 3 A schematic block diagram of a voice false wake-up recognition device according to an exemplary embodiment of the present disclosure is shown, as shown in Figure 3 The device includes:

[0091] The detection unit 31 is configured to detect whether the device receives the wake-up voice;

[0092] The recognition unit 32 is configured to perform voice recognition on the wake-up voice when the wake-up voice is detected.

[0093] The matching unit 33 is configured to perform false wake-up condition rule matching based on the result of the voice recognition.

[0094] The determining unit 34 is configured to recognize the wake-up voice as false wake-up voice when the wake-up voice matches the false wake-up condition rule.

[0095] In some embodiments, the matching unit 33 comprises:

[0096] The first judging module is configured to judge whether there is a result of the voice recognition.

[0097] The second judging module is configured to, if there is no result of the voice recognition, judge whether the voiceprint information of the wake-up voice belongs to recorded common voiceprint information.

[0098] The first determining module is configured to, if the voiceprint information of the wake-up voice does not belong to the recorded common voiceprint information, determine that the wake-up voice matches the false wake-up condition rule.

[0099] The third judging module is configured to, if the voiceprint information of the wake-up voice belongs to the recorded common voiceprint information, judge whether the environmental volume before the wake-up voice is detected and / or the environmental volume after the wake-up voice is detected is lower than a preset threshold.

[0100] The second determining module is configured to, if the environmental volume before the wake-up voice is detected and / or the environmental volume after the wake-up voice is detected is lower than the preset threshold, determine that the wake-up voice matches the false wake-up condition rule.

[0101] In some embodiments, the matching unit 33 further comprises:

[0102] The fourth judging module is configured to, if there is a result of the voice recognition, judge whether the result of the voice recognition has a corresponding semantic result.

[0103] The executing module is configured to, if the result of the voice recognition has no corresponding semantic result, perform the step of judging whether the voiceprint information of the wake-up voice belongs to recorded common voiceprint information.

[0104] In some embodiments, the apparatus further comprises:

[0105] The output unit is configured to, after the wake-up voice is recognized as false wake-up voice, output prompt information, wherein the prompt information is used to prompt a user that the wake-up voice is determined as false wake-up voice.

[0106] The judging unit is configured to judge whether a cancel operation of a user is detected, wherein the cancel operation is used to indicate canceling the determination of the wake-up voice as false wake-up voice.

[0107] a cancel unit, configured to cancel the wake-up voice as false wake-up voice if the cancel operation of the user is detected;

[0108] an analysis unit, configured to report the wake-up voice for analysis if the cancel operation of the user is not detected.

[0109] In some embodiments, the analysis unit comprises:

[0110] a calculation module, configured to calculate a confidence degree of the wake-up voice as false wake-up voice;

[0111] an acquisition module, configured to acquire the wake-up voice with a confidence degree higher than a target confidence degree;

[0112] an update module, configured to update the false wake-up condition rule by using the wake-up voice with the confidence degree higher than the target confidence degree.

[0113] In some embodiments, the analysis unit further comprises:

[0114] a classification module, configured to classify and analyze the wake-up voice as false wake-up voice.

[0115] In some embodiments, the apparatus further comprises:

[0116] a first acquisition unit, configured to set a voice false wake-up identification function switch of a terminal device to an open state before the detection device receives a wake-up voice; and acquire an environmental volume before the wake-up voice is detected.

[0117] a second acquisition unit, configured to acquire voiceprint information of the wake-up voice after the wake-up voice is detected; and acquire an environmental volume after the wake-up voice is detected.

[0118] It should be noted that each of the above modules can be a functional module or a program module, and can be implemented by software or hardware. For the modules implemented by hardware, each of the above modules can be located in the same processor; or each of the above modules can be located in different processors in any combination.

[0119] The example embodiments of the present disclosure further provide an electronic device, comprising: at least one processor; and a memory connected with the at least one processor in communication. The memory stores a computer program capable of being executed by the at least one processor, and the computer program, when executed by the at least one processor, is configured to cause the electronic device to perform the method according to the embodiments of the present disclosure.

[0120] The exemplary embodiments of the present disclosure further provide a non-transitory computer readable storage medium storing a computer program, wherein the computer program, when executed by a processor of a computer, causes the computer to perform the method according to the embodiments of the present disclosure.

[0121] The exemplary embodiments of the present disclosure further provide a computer program product comprising a computer program, wherein the computer program, when executed by a processor of a computer, causes the computer to perform the method according to the embodiments of the present disclosure.

[0122] Reference Figure 4 A block diagram of the structure of an electronic device 400 that can be a server or a client of the present disclosure, which is an example of a hardware device that can be applied to aspects of the present disclosure, will now be described. The electronic device is intended to represent a wide variety of digital electronic computer devices such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device can also represent a variety of forms of mobile devices such as personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections, and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document.

[0123] As shown in Figure 4 The electronic device 400 includes a computing unit 401 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 402 or a computer program loaded into a random access memory (RAM) 403 from a storage unit 408. 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 through a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0124] A plurality of components in the electronic device 400 are connected to the I / O interface 405, including: an input unit 406, an output unit 407, a storage unit 408, and a communication unit 409. The input unit 406 can be any type of device that can input information to the electronic device 400, and can receive inputted digital or character information, and generate key signal inputs related to user settings and / or function controls of the electronic device. The output unit 407 can be any type of device that can present information, and can include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 408 can include, but is not limited to, a magnetic disk, an optical disk. The communication unit 409 allows the electronic device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and can include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0125] The computing unit 401 can be various general and / or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 401 performs various methods and processes described above. For example, in some embodiments, the voice false wake-up recognition method can be implemented as a computer software program, which is tangibly embodied in a machine-readable medium, such as the storage unit 408. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 400 via the ROM 402 and / or the communication unit 409. In some embodiments, the computing unit 401 can be configured to perform the voice false wake-up recognition method by any other appropriate means, such as by means of firmware.

[0126] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, causes the functions / operations specified in the flow charts and / or block diagrams to be implemented. The program code can be implemented in a machine language, in part, in a machine language, in part, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0127] In the context of this disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0128] As used in this disclosure, the terms "machine-readable medium" and "computer- readable medium" refer to any computer program product, apparatus and / or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal that can be used to provide machine instructions and / or data to a programmable processor.

[0129] To provide for interaction with a user, the systems and techniques described here 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 a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, 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, speech, or tactile input.

[0130] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0131] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

Claims

1. A method of voice miswakeup recognition, the method comprising: The method comprises the following steps: detecting whether a wake-up voice is received by a device; performing voice recognition on the wake-up voice when the wake-up voice is detected; judging whether there is a result of the voice recognition; judging whether voiceprint information of the wake-up voice belongs to recorded common voiceprint information if there is no result of the voice recognition; determining that the wake-up voice matches a false wake-up condition rule if the voiceprint information of the wake-up voice does not belong to the recorded common voiceprint information; judging whether an ambient volume before the wake-up voice is detected and / or an ambient volume after the wake-up voice is detected is lower than a preset threshold if the voiceprint information of the wake-up voice belongs to the recorded common voiceprint information; determining that the wake-up voice matches the false wake-up condition rule if the ambient volume before the wake-up voice is detected and / or the ambient volume after the wake-up voice is detected is lower than the preset threshold; recognizing the wake-up voice as a false wake-up voice when the wake-up voice matches the false wake-up condition rule.

2. The voice miswakeup recognition method of claim 1, wherein, After judging whether there is a result of the voice recognition, the method further comprises the following steps: judging whether there is a corresponding semantic result of the result of the voice recognition if there is a result of the voice recognition; performing the step of judging whether the voiceprint information of the wake-up voice belongs to recorded common voiceprint information if there is no corresponding semantic result of the result of the voice recognition.

3. The voice miswakeup recognition method of claim 1, wherein, After recognizing the wake-up voice as a false wake-up voice, the method further comprises the following steps: outputting prompt information, wherein the prompt information is used to prompt a user that the wake-up voice is determined as a false wake-up voice; judging whether a cancel operation of the user is detected, wherein the cancel operation is used to indicate that the wake-up voice is determined as a false wake-up voice is cancelled; cancelling the determination of the wake-up voice as a false wake-up voice if the cancel operation of the user is detected; reporting the wake-up voice for analysis if the cancel operation of the user is not detected.

4. The voice miswakeup recognition method of claim 3, wherein, The reporting of the wake-up voice for analysis comprises the following steps: calculating a confidence degree of the determination of the wake-up voice as a false wake-up voice; obtaining the wake-up voice with a confidence degree higher than a target confidence degree; updating the false wake-up condition rule by using the wake-up voice with the confidence degree higher than the target confidence degree.

5. The voice miswakeup recognition method of claim 3, wherein, The reporting of the wake-up voice for analysis comprises the following steps: performing classification analysis on the wake-up voice determined as a false wake-up voice.

6. The method according to any one of claims 1 to 5, wherein before detecting whether a wake-up voice is received by a device, the method further comprises the following steps: setting a voice false wake-up recognition function switch of a terminal device to an open state; and obtaining an ambient volume before the wake-up voice is detected; after the wake-up voice is detected, the method further comprises the following steps: obtaining voiceprint information of the wake-up voice; and obtaining an ambient volume after the wake-up voice is detected.

7. A voice mis-recognition detection apparatus characterized by comprising: The method comprises the following steps: a detecting unit, configured to detect whether a wake-up voice is received by a device; an recognizing unit, configured to perform voice recognition on the wake-up voice when the wake-up voice is detected; a matching unit, configured to judge whether there is a result of the voice recognition; If the result of the voice recognition does not exist, it is judged whether the voiceprint information of the wake-up voice belongs to the recorded common voiceprint information; if the voiceprint information of the wake-up voice does not belong to the recorded common voiceprint information, it is determined that the wake-up voice matches the false wake-up condition rule; if the voiceprint information of the wake-up voice belongs to the recorded common voiceprint information, it is judged whether the environmental volume before the wake-up voice is detected and / or the environmental volume after the wake-up voice is detected is lower than a preset threshold; if the environmental volume before the wake-up voice is detected and / or the environmental volume after the wake-up voice is detected is lower than the preset threshold, it is determined that the wake-up voice matches the false wake-up condition rule; A determination unit is configured to recognize the wake-up voice as a false wake-up voice when the wake-up voice matches the false wake-up condition rule.

8. An electronic device, comprising: Comprise: A processor; And A memory for storing programs, Wherein the program includes instructions which, when executed by the processor, cause the processor to perform the voice false wake-up recognition method according to any one of claims 1-6.

9. A non-transitory computer-readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to make the computer perform the voice false wake-up recognition method according to any one of claims 1-6.

Images