Voice control method and device, storage medium and electronic equipment

Abstract

The invention discloses a voice control method and device, a storage medium and electronic equipment. The method comprises the following steps: acquiring to-be-detected voice data, and performing keyword detection on the to-be-detected voice data to obtain keywords in the to-be-detected voice data; voice data where the keyword is located are obtained from the voice data to be detected, and voice data to be recognized are obtained; performing voice recognition on the to-be-recognized voice data to obtain a first voice recognition result; and if the keyword is matched with the first voice recognition result, determining a control instruction corresponding to the to-be-detected voice data, and executing the control instruction. According to the invention, the false recognition rate of the wake-free word can be reduced.

Description

Technical Field

[0001] The present application belongs to the field of electronic technology, and in particular, relates to a voice control method, device, computer-readable storage medium and electronic device. Background Art

[0002] Voice wake-up-free technology is an intelligent voice technology that can interact with electronic devices by voice without the need for a wake-up word. When voice-controlling electronic devices, the use of voice wake-up-free technology can more conveniently control electronic devices. However, the voice control method of the prior art has a high misrecognition rate for wake-up-free words. Summary of the invention

[0003] The embodiments of the present application provide a voice control method, device, storage medium and electronic device, which can reduce the misrecognition rate of wake-up words.

[0004] In a first aspect, an embodiment of the present application provides a voice control method, comprising:

[0005] Acquire voice data to be detected, and perform keyword detection on the voice data to be detected to obtain keywords in the voice data to be detected;

[0006] Acquire the voice data containing the keyword from the voice data to be detected to obtain the voice data to be recognized;

[0007] Performing speech recognition on the speech data to be recognized to obtain a first speech recognition result;

[0008] If the keyword matches the first speech recognition result, a control instruction corresponding to the speech data to be detected is determined and the control instruction is executed.

[0009] In a second aspect, an embodiment of the present application provides a voice control device, comprising:

[0010] A keyword detection module, used to obtain the voice data to be detected, and perform keyword detection on the voice data to be detected to obtain the keywords in the voice data to be detected;

[0011] A data acquisition module, used to acquire the voice data containing the keyword from the voice data to be detected, so as to obtain the voice data to be recognized;

[0012] A speech recognition module, used for performing speech recognition on the speech data to be recognized to obtain a first speech recognition result;

[0013] An instruction execution module is used to determine a control instruction corresponding to the voice data to be detected and execute the control instruction if the keyword matches the first voice recognition result.

[0014] In a third aspect, an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed on a computer, the computer executes the voice control method provided by the embodiment of the present application.

[0015] In a fourth aspect, an embodiment of the present application further provides an electronic device, comprising a memory and a processor, wherein the processor is used to execute the voice control method provided in the embodiment of the present application by calling a computer program stored in the memory.

[0016] In an embodiment of the present application, by obtaining voice data to be detected and performing keyword detection on the voice data to be detected, keywords in the voice data to be detected are obtained; voice data to be recognized is obtained from the voice data to be detected, and voice recognition is performed on the voice data to be recognized to obtain a first voice recognition result; if the keyword matches the first voice recognition result, a control instruction corresponding to the voice data to be detected is determined, and the control instruction is executed. Thus, by combining keyword detection technology with voice recognition technology to identify keywords in voice, that is, wake-up-free words, the accuracy of recognition of wake-up-free words can be improved compared to a solution that only uses keyword detection technology to identify wake-up-free words in voice, thereby reducing the false wake-up rate of wake-up-free words. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The technical solution and beneficial effects of the present application will be made apparent by describing in detail the specific implementation methods of the present application in conjunction with the accompanying drawings.

[0018] Figure 1 This is a first flow chart of the voice control method provided in the embodiment of the present application.

[0019] Figure 2 This is a second flow chart of the voice control method provided in the embodiment of the present application.

[0020] Figure 3 It is a scenario diagram of the voice control method provided in an embodiment of the present application.

[0021] Figure 4 It is a structural diagram of the voice control device provided in an embodiment of the present application.

[0022] Figure 5 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] It should be noted that the terms "first", "second" and "third" in this application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or modules is not limited to the listed steps or modules, but some embodiments also include steps or modules that are not listed, or some embodiments also include other steps or modules inherent to these processes, methods, products or devices.

[0024] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0025] The embodiments of the present application provide a voice control method, a voice control device, a storage medium, and an electronic device. The execution subject of the voice control method may be the voice control device provided in the embodiments of the present application, or an electronic device integrating the voice control device, wherein the voice control device may be implemented in hardware or software. The electronic device may be a device such as a smart phone, a tablet computer, a PDA, a laptop computer, etc. that is equipped with a processor and has voice control capabilities.

[0026] See also Figure 1 , Figure 1 This is a schematic diagram of the first flow chart of the voice control method provided in the embodiment of the present application. The flow chart may include:

[0027] In 101, voice data to be detected is obtained, and keyword detection is performed on the voice data to be detected to obtain keywords in the voice data to be detected.

[0028] The voice data to be detected is the sound in the environment where the electronic device is located. The sound can be collected by a microphone provided by the electronic device, or by an external device connected to the electronic device.

[0029] For example, the sound in the environment where the mobile phone is located can be collected through the microphone built into the mobile phone, or the sound in the environment where the mobile phone is located can be collected through an external microphone connected to the mobile phone.

[0030] When an electronic device collects sound in the environment in which the electronic device is located through its own microphone, the audio collection function can be turned on first to activate the microphone of the electronic device. The audio collection function can be automatically started when the electronic device is turned on, or can be started by user control.

[0031] Exemplarily, the electronic device may enable the wake-up-free function by default. The wake-up-free function may also be enabled when the wake-up-free function is needed. The wake-up-free function and the audio collection function of the electronic device may be enabled at the same time, or the audio collection function may be enabled after the wake-up-free function is enabled. The startup sequence of the two is not limited here. The startup mode of the wake-up-free function includes any one of manual startup by the user, startup by user voice control, self-start of the electronic device triggered by preset conditions, and startup by user gestures.

[0032] When the user manually starts the wake-up-free function, for example, a touch button for the wake-up-free function may be displayed on the setting interface of the electronic device, and the user can start the wake-up-free function by operating the touch button. Of course, by setting the existing touch buttons, it is also possible to enable both the original function and the wake-up-free function. For example, the Bluetooth touch button can be used to activate both the Bluetooth function and the wake-up-free function, that is, the Bluetooth function and the wake-up-free function are activated at the same time.

[0033] When the user voice controls to activate the wake-up-free function, the wake-up-free function of the electronic device can be activated, for example, by controlling the wake-up-free function of the electronic device through a voice assistant in the related art.

[0034] When the electronic device's self-starting wake-up-free function is triggered by preset conditions, the preset conditions may, for example, control the self-starting of the wake-up-free function when the user starts a specified application, and the specified application may be one or more; the preset conditions may also, for example, control the self-starting of the wake-up-free function when it is detected that the electronic device is in a specified environment, and the specified environment may be, for example, a driving environment, a call environment, a file transfer environment, etc.

[0035] When the user gesture activates the wake-up-free function, for example, the user draws a specified pattern on the screen of the electronic device using the finger joints, or for example, the user shows a specified gesture in front of the camera.

[0036] Since there are many ways to start the wake-up-free function, they are not listed here. It can be understood that the above-mentioned multiple starting methods can also be combined to start the wake-up-free function, and after starting the wake-up-free function, the electronic device enters the wake-up-free mode.

[0037] When the wake-up-free function is turned off, the wake-up-free mode is exited. After exiting the wake-up-free mode, the electronic device can also execute the common voice control method in the related art. Therefore, the present application can more flexibly perform voice control on the electronic device by adding the wake-up-free function to the electronic device. The electronic device can be voice controlled by the existing method in the related art or by the method provided by the present application.

[0038] For example, after the wake-up-free function is activated, the electronic device can collect voice data in real time through its own microphone to obtain the voice data to be detected. After obtaining the voice data to be detected, the electronic device can activate a keyword detection engine to perform keyword detection on the voice data to be detected and obtain keywords in the voice data to be detected.

[0039] It is understandable that the keywords mentioned in the embodiments of the present application are wake-up words. Among them, the keywords may include: "play next song", "play previous song", "navigate to", "call" and the like.

[0040] It is understandable that when no keyword is detected, the electronic device may continue to detect other collected voice data to be detected until the keyword is detected.

[0041] When the keyword detection engine is used to perform keyword detection on the voice data to be detected, the voice data to be detected can be divided into a plurality of sub-voice data to be detected, and the keyword detection engine is used to perform keyword detection on each sub-voice data to be detected. When a certain sub-voice data to be detected contains keywords other than the last keyword or does not contain any keyword, the output of the keyword detection engine is 0. When a certain sub-voice data to be detected contains the last keyword, the output of the keyword detection engine is a non-zero value. Each sub-voice data to be detected is voice data of a first preset duration. The first preset duration can be determined according to the duration of the voice data supported by the keyword detection engine. For example, the first preset duration can be 20ms, 30ms, and so on.

[0042] In an optional embodiment, the voice data to be detected is in the form of a voice stream, and the input of the keyword detection engine is voice data of a first preset duration. Then, each time the electronic device collects voice data of the first preset duration, the keyword detection engine performs keyword detection on the voice data. When the voice data contains keywords other than the last keyword or does not contain any keyword, the output of the keyword detection engine is 0. When the voice data contains the last keyword, the output of the keyword detection engine is a non-zero value. The first preset duration can be determined according to the duration of the voice data supported by the keyword detection engine. For example, the first preset duration can be 20ms, 30ms, and so on.

[0043] Among them, 0 means that the keyword is not detected, and a non-zero value means that the keyword is detected, and the value of the non-zero value corresponds to a certain keyword. For example, assuming that the keyword detection engine can detect a total of 8 keywords, the value of the non-zero value can be 1 to 8, and each value uniquely corresponds to a keyword among the 8 keywords.

[0044] In 102, the voice data containing the keyword is obtained from the voice data to be detected to obtain the voice data to be recognized.

[0045] When the keyword detection engine detects whether there are keywords in the voice data, it calculates the probability of each keyword existing in the voice data, and uses the maximum probability as the confidence output by the keyword detection engine, that is, the second confidence. When the keyword engine outputs a non-zero value and the second confidence is not less than the second confidence threshold, the keyword corresponding to the non-zero value can be used as the keyword in the voice data to be detected.

[0046] In order to avoid the situation where the user needs to say the keyword several times to control the electronic device to execute the corresponding control instruction due to the low wake-up rate of the keyword, the second confidence threshold is usually set relatively low, such as the second confidence threshold is 0.35, 0.38, and so on. However, since the second confidence threshold is set relatively low, it will also lead to a high misrecognition rate of keywords. For example, the user says a word similar to a keyword, but it is recognized as a keyword by the keyword detection engine. Based on this, in order to reduce the misrecognition rate of wake-up-free words, thereby reducing the false wake-up rate of voice control, in this embodiment, when the keyword is detected from the voice data to be detected by the keyword detection engine, the voice data to be recognized where the keyword is located will be further obtained from the voice data to be detected, so as to further confirm whether there is a keyword in the voice data to be detected through voice recognition technology.

[0047] It is understandable that when a user performs voice control on an electronic device, the voice spoken by the user is usually a control instruction including keywords. For example, if the voice output by the user is "call mom", the keyword is "call", and the control instruction is "call mom". If the voice output by the user is "navigate to xx restaurant", the keyword is "navigate to", and the control instruction is "navigate to xx restaurant". In other words, when the user performs voice control on an electronic device, the voice spoken by the user does not only include keywords. If voice recognition is performed on the entire voice spoken by the user, the power consumption of the electronic device will be increased, and the speed of voice control will be affected. Based on this, in this embodiment, after the keywords are detected from the voice data to be detected, the voice data where the keywords are located will also be obtained from the voice data to be detected to obtain the voice data to be recognized, that is, a part of the voice data in the voice data to be detected where the keywords exist is determined as the voice data to be recognized.

[0048] For example, assuming that the voice data to be detected is voice data with a duration of 3 seconds, and the voice data containing the keyword is the voice data from 0.5 seconds to 2 seconds in the voice data to be detected, then the voice data from 0.5 seconds to 2 seconds in the voice data to be detected can be determined as the voice data to be recognized.

[0049] In 103, speech recognition is performed on the speech data to be recognized to obtain a first speech recognition result.

[0050] In this embodiment, after obtaining the voice data to be recognized, the electronic device may further perform voice recognition on the voice data to be recognized through a voice recognition engine to obtain a first voice recognition result.

[0051] In an optional embodiment, when the speech recognition engine performs speech recognition on the speech data to be recognized, the speech recognition can be performed on the speech data to be recognized by the local speech recognition engine, thereby avoiding the time consumption of network transmission and improving the recognition speed of keywords.

[0052] Since the power consumption of the keyword detection engine is lower than that of the speech recognition engine, in this embodiment, only the low-power keyword detection engine is started first, and after the keyword detection engine detects the keyword, the high-power speech recognition engine is started. In addition, the high-power speech recognition engine only recognizes the speech data where the keyword is located, and the duration is generally only a few seconds, and the impact on power consumption can be ignored, thereby achieving a reduction in the misrecognition rate of keywords while ensuring low power consumption. Due to the increase in the misrecognition rate, the second confidence threshold can be further reduced, thereby achieving the effect of further improving the recognition rate of keywords, that is, the recognition rate and misrecognition rate performance of keywords are both improved.

[0053] In 103, if the keyword matches the first voice recognition result, a control instruction corresponding to the voice data to be detected is determined and the control instruction is executed.

[0054] In this embodiment, if the keyword matches the first voice recognition result, then the control instruction corresponding to the voice data to be detected can be determined and executed.

[0055] For example, the electronic device may perform speech recognition on the speech data to be detected through a speech recognition engine to obtain a second speech recognition result, and the second speech recognition result includes the text to be analyzed. Subsequently, the electronic device may perform semantic analysis on the text to be analyzed to obtain a semantic analysis result; then determine a control instruction corresponding to the semantic analysis result, use it as a control instruction corresponding to the speech to be detected, and execute the control instruction.

[0056] For example, assuming that the control instruction corresponding to the voice data to be detected is "call mom", the electronic device can execute the instruction to call mom; assuming that the control instruction corresponding to the voice data to be detected is "navigate to xx restaurant", the electronic device can execute the instruction to navigate to xx restaurant.

[0057] It is understandable that if the keyword does not match the first voice recognition result, the electronic device can return to execute 101 to perform keyword detection on the newly acquired voice data to be detected until the detected keyword matches the first voice recognition result.

[0058] In this embodiment, the keywords in the voice data to be detected are obtained by acquiring voice data to be detected and performing keyword detection on the voice data to be detected; the voice data to be recognized is acquired from the voice data to be detected, and voice recognition is performed on the voice data to be recognized to obtain a first voice recognition result; if the keyword matches the first voice recognition result, the control instruction corresponding to the voice data to be detected is determined, and the control instruction is executed. Thus, the keywords in the voice, that is, the wake-up words, are recognized by combining the keyword detection technology with the voice recognition technology. Compared with the solution of only using the keyword detection technology to recognize the wake-up words in the voice, the accuracy of the recognition of the wake-up words can be improved, thereby reducing the false wake-up rate of the wake-up words.

[0059] In an optional embodiment, acquiring the voice data containing the keyword from the voice data to be detected to obtain the voice data to be recognized includes:

[0060] Determine the end time of the voice data where the last keyword in the keywords is located;

[0061] According to the end time, the voice data to be recognized is obtained from the voice data to be detected.

[0062] It should be noted that when the keyword detection engine is used to perform keyword detection on the voice data to be detected, part of the voice data to be detected, such as voice data of a first preset duration, is usually input into the keyword detection engine in chronological order for keyword detection, and the voice data of the preset duration usually only includes part of the keywords, such as only one or more keywords in the keywords, and the keyword detection engine outputs a non-zero value and a second confidence level only when the voice data containing the last keyword in the keywords is detected, so that the electronic device can determine the keyword corresponding to the non-zero value as the keyword in the voice data to be detected when the second confidence level is not less than the second confidence level threshold.

[0063] Since the keyword detection engine will output a non-zero value and a second confidence level when detecting the voice data containing the last keyword in the keywords, when the keyword detection engine outputs a non-zero value and the output second confidence level is not less than the second confidence level threshold, the electronic device can determine the end time of the voice data and, based on the end time, obtain the voice data to be recognized from the voice data to be detected.

[0064] The end time of the voice data where the last keyword in the keywords is located may be the acquisition completion time of the last audio frame included in the voice data.

[0065] In an optional embodiment, each time the electronic device collects voice data of the first preset time length, the voice data is input into the keyword detection engine for keyword detection. Each time the voice data of the first preset time length is collected, the electronic device records the collection start time and collection end time of the voice data. Then, after determining the voice data where the last keyword in the keyword is located, the electronic device can use the collection end time of the voice data as the end time of the voice data.

[0066] In an optional embodiment, before acquiring the voice data to be recognized from the voice data to be detected according to the end time, the method further includes:

[0067] Determine the target duration based on the number of words in the keyword. The target duration is positively correlated with the number of words.

[0068] According to the end time, the voice data to be recognized is obtained from the voice data to be detected, including:

[0069] According to the end time, voice data of a target duration is obtained from the voice data to be detected as the voice data to be recognized.

[0070] It is understandable that the more words a keyword has, the more time the user needs to spend saying the corresponding keyword, and the longer the duration of the voice data containing the keyword. Based on this, in this embodiment, the duration of the voice data to be recognized can be determined based on the number of words in the keyword, that is, the target duration, and then according to the end time, the voice data of the target duration is obtained from the voice data to be detected as the voice data to be recognized. To a certain extent, voice recognition of the entire voice data to be detected can be avoided, thereby reducing the power consumption of the electronic device, and increasing the speed of voice recognition, thereby increasing the speed of keyword detection. Among them, the target duration is positively correlated with the number of words, that is, the more words there are, the longer the target duration, and conversely, the fewer words there are, the shorter the target duration.

[0071] For example, if the keyword is "play next song", the target duration may be 2.6 seconds, and if the keyword is "navigate to", the target duration may be "1.2" seconds.

[0072] In an optional embodiment, voice data of each of multiple users saying a keyword of a certain number of words multiple times can be collected in advance to obtain multiple voice data; then the duration of each voice data is determined to obtain multiple durations; finally, the duration corresponding to the keyword of the number of words is determined based on the multiple durations; when the keyword of the number of words is obtained subsequently, the duration can be determined as the target duration corresponding to the keyword.

[0073] When determining the duration corresponding to the keyword of the number of words based on multiple durations, the average of the multiple durations can be used as the duration corresponding to the keyword of the number of words; the largest duration among the multiple durations can be determined as the duration corresponding to the keyword of the number of words; or the duration with the largest number among the multiple durations can be determined as the duration corresponding to the keyword of the number of words.

[0074] For example, assuming that there are 1000 pieces of pre-collected speech data of each user saying a keyword with 3 characters multiple times, and 990 pieces of speech data have a duration of 1.2 seconds, then 1.2 seconds can be determined as the duration corresponding to the keyword with 3 characters. When the number of characters of the keyword obtained later is 3, the target duration corresponding to the keyword can be determined to be 1.2 seconds.

[0075] In an optional embodiment, before determining the target duration according to the word count of the keyword, the method further includes:

[0076] Perform speech speed detection on the speech data to be detected to obtain the speech speed corresponding to the speech data to be detected;

[0077] Determine the target duration based on the word count of the keyword, including:

[0078] Determine the target duration based on the number of words and speaking speed. The target duration is inversely correlated with the speaking speed.

[0079] It is understandable that when the number of words in a keyword is the same, a user with a faster speaking speed takes a shorter time to say the keyword than a user with a slower speaking speed. Based on this, in this embodiment, the target duration can be determined by combining the number of words in the keyword and the speaking speed of the voice data to be detected. The target duration is positively correlated with the number of words and negatively correlated with the speaking speed, that is, the more words, the slower the speaking speed, and the longer the target duration. Conversely, the fewer words, the faster the speaking speed, and the shorter the target duration.

[0080] In an optional embodiment, obtaining the voice data to be recognized from the voice data to be detected according to the end time includes:

[0081] The corresponding voice data before the end time in the voice data to be detected is determined as the voice data to be recognized.

[0082] For example, voice data of a target duration before the end time in the voice data to be detected may be determined as the voice data to be recognized.

[0083] For another example, voice data of the first duration before the end time in the voice data to be detected may be determined as the voice data to be recognized.

[0084] The first duration may be set in advance, or may be determined based on the number of words of the keyword with the largest number of words among all the keywords that can be detected by the keyword detection engine.

[0085] In an optional embodiment, in the process of detecting keywords by the keyword detection engine, real-time voice data will be cached at the same time, and considering the hardware cost, usually only the voice data of the second preset duration is cached. The second preset duration is greater than the maximum target duration. For example, if the maximum target duration is 2.6 seconds, the second preset duration can be 3 seconds. Then, when it is necessary to obtain the voice data to be recognized later, the cached voice data of the target duration before the end time can be obtained as the voice data to be recognized.

[0086] In an optional embodiment, obtaining the voice data to be recognized from the voice data to be detected according to the end time includes:

[0087] The corresponding voice data before the end time and the corresponding voice data after the end time in the voice data to be detected are determined as the voice data to be recognized.

[0088] For example, voice data of the second duration before the end time and voice data of the third duration after the end time in the voice data to be detected may be determined as voice data to be recognized.

[0089] Among them, the second duration is greater than the third duration.

[0090] In an optional embodiment, the second duration may be a target duration. For example, assuming the target duration is 1.2 seconds, the second duration may be 1.2 seconds, and the third duration may be 0.2 seconds.

[0091] In an optional embodiment, the sum of the second duration and the third duration may be the target duration. For example, assuming the target duration is 1.2 seconds, the second duration may be 1.1 seconds, and the third duration may be 0.1 seconds.

[0092] In an optional embodiment, the first voice recognition result includes text, and if the keyword matches the first voice recognition result, determining a control instruction corresponding to the voice data to be detected includes:

[0093] If the keyword matches the text, a control instruction corresponding to the voice data to be detected is determined.

[0094] For example, to further reduce the power consumption of speech recognition, when the speech recognition engine performs speech recognition on the speech data to be recognized, the text included in the first speech recognition result output by the speech recognition engine may be the recognized phonemes, without outputting the text mapped to the phonemes. For example, the text may include "daohangdao", "dadianhuagei", and so on.

[0095] For another example, to further reduce the misrecognition rate, when the speech recognition engine performs speech recognition on the speech data to be recognized, the text included in the first speech recognition result output by the speech recognition engine may be the text to which the recognized phonemes are mapped. For example, the text may include "navigate to" or "call".

[0096] It is understandable that when acquiring the voice data containing the keywords, various factors may cause the acquired voice data to include not only the keywords but also other content. For example, the acquired voice data includes "please call". Based on this, in this embodiment, when the keywords are included in the text, it can be determined that the keywords match the text. Then, the control instructions corresponding to the voice data to be detected can be further determined.

[0097] In order to facilitate matching, the text and the keyword can be in the same expression form. For example, if the text is a phoneme, the keyword is also a phoneme; if the text is the text mapped to the phoneme, the keyword is also the corresponding text.

[0098] For example, assuming that the text and keywords are both in phoneme form, if the text includes "dadianhuagei" and the keyword is "dadianhuagei", it can be determined that the text and keyword match; assuming that the text and keywords are both in corresponding text form, if the text includes "navigate to" and the keyword is "navigate to", it can be determined that the text and keyword match.

[0099] In an optional embodiment, the first speech recognition result further includes a first confidence level, and if the keyword matches the text, determining a control instruction corresponding to the speech data to be detected includes:

[0100] If the keyword matches the text and the first confidence level is greater than a first confidence level threshold, a control instruction corresponding to the voice data to be detected is determined.

[0101] In order to further reduce the misrecognition rate of keywords, in this embodiment, the confidence level output by the speech recognition engine, that is, the first confidence level, can also be used as a judgment condition to determine whether to perform voice control on the electronic device. For example, a confidence threshold can be pre-set as the first confidence threshold. If the keyword matches the text and the first confidence level is greater than the first confidence threshold, the electronic device can be voice controlled, that is, the control instruction corresponding to the voice data to be detected is determined and executed; if the keyword matches the text and the first confidence level is not greater than the first confidence threshold, the electronic device is not voice controlled.

[0102] The first confidence threshold can be set before or after leaving the factory. The first confidence threshold can be set by a professional after testing before leaving the factory, or can be set by the user after leaving the factory, or can be set by the electronic device based on certain rules.

[0103] In an optional embodiment, the method further includes:

[0104] If the keyword matches the text, the first confidence is greater than the first confidence threshold, and the difference between the first confidence and the first confidence threshold is greater than the difference threshold, then obtaining the historical confidence corresponding to each historical voice data to be recognized in the historical voice data to be recognized obtained in the first historical period;

[0105] Determine a target historical confidence from the historical confidences, where the target historical confidence is a historical confidence that is greater than a first confidence threshold and whose difference from the first confidence threshold is greater than a difference threshold;

[0106] determining a first quantity of the first confidence and the target historical confidence, and determining a second quantity of the first confidence and the historical confidence;

[0107] If the first quantity is not less than the first quantity threshold, and the ratio of the first quantity to the second quantity is not less than the ratio threshold, the first confidence threshold is increased.

[0108] Taking into account that different users have different speaking styles, but the first confidence threshold corresponding to the same batch of electronic devices is the same, in order to ensure a high recognition rate for keywords for users with relatively non-standard speech, the first confidence threshold is usually set lower. In order to ensure a low misrecognition rate for keywords for users with relatively standard speech, the first confidence threshold can be increased during the user's actual voice control.

[0109] For example, if a certain electronic device obtains more speech data to be recognized in a first historical period, the confidence corresponding to the speech data to be recognized is greater than the first confidence threshold, and the difference with the first confidence threshold is greater than the difference threshold, then the first confidence threshold can be increased. The first historical period can be preset. For example, the historical period can be within one month, within half a month, or within 10 days, etc.

[0110] For example, assuming that the first quantity threshold is 75, the ratio threshold is 4 / 5, and an electronic device acquires 99 historical voice data to be recognized within a month, among which, the historical confidence corresponding to 79 historical voice data to be recognized is greater than the first confidence threshold, and the difference with the first confidence threshold is greater than the difference threshold. If the text matches the keyword, the first confidence is greater than the first confidence threshold, and the difference between the first confidence and the first confidence threshold is greater than the difference threshold, then the total number of the first confidence and the target historical confidence can be determined, that is, the first number is 79+1=80, the total number of the first confidence and the historical confidence, that is, the second number is 99+1=100, and the ratio of the first number to the second number is 4 / 5, then the electronic device can increase the first confidence threshold. Among them, the first quantity threshold and the ratio threshold can be preset.

[0111] In an optional embodiment, increasing the first confidence threshold includes:

[0112] According to the first confidence and the target historical confidence, the first confidence threshold is increased.

[0113] For example, the electronic device may determine the minimum confidence from the first confidence and the target historical confidence, and set the first confidence threshold to be smaller than the minimum confidence, and the difference between the first confidence threshold and the minimum confidence is smaller than the first difference threshold. The first difference threshold may be preset based on actual conditions.

[0114] In an optional embodiment, the method further includes:

[0115] If the keyword matches the text and the first confidence is not greater than the first confidence threshold, then obtaining the historical text corresponding to each historical voice data to be recognized in the historical voice data to be recognized obtained in the second historical period;

[0116] If there are target historical texts matching the text in the historical texts, and the number of the target historical texts is not less than the second number threshold, the first confidence threshold is reduced.

[0117] In order to ensure a low misrecognition rate of keywords, the first confidence threshold is usually set higher. However, considering that different users speak differently, if the first confidence threshold is set higher, the keyword recognition rate may be lower for users with relatively non-standard speaking styles, causing the user to say the same keyword multiple times within a certain period of time without being recognized by the electronic device. In order to improve the keyword recognition rate for these users, the first confidence threshold can be lowered during the actual voice control process of these users.

[0118] For example, if the historical texts corresponding to the historical voice data to be recognized acquired by an electronic device multiple times within the second historical period all match the text, the first confidence threshold can be reduced. The second historical period can be preset. For example, the second historical period can be within 5 minutes, within 10 minutes, within 30 minutes, and so on.

[0119] For example, assuming that the second quantity threshold is 9, assuming that the text corresponding to the voice data to be recognized obtained by an electronic device at the 10th minute matches the keyword, and the confidence corresponding to the voice data to be recognized, that is, the first confidence is not greater than the first confidence threshold, and among the historical voice data to be recognized obtained within the first 9 minutes, 9 historical texts corresponding to the historical voice data to be recognized all match the text, and the number of historical texts corresponding to the 9 historical voice data to be recognized is not less than the second quantity threshold, then it can be determined that the user may have said the same keyword multiple times within these 10 minutes, but because the confidence threshold may be set too high, none of them were recognized by the electronic device, then the electronic device can reduce the first confidence threshold so that the user can be recognized by the electronic device when he speaks the same keyword later. Among them, the second quantity threshold can be set in advance.

[0120] When the two texts include the same keyword, the two texts are determined to match. For example, if a text includes the keyword "call" and another text also includes the keyword "call", the text is determined to match the other text.

[0121] In an optional embodiment, reducing the confidence threshold includes:

[0122] Obtain the target history confidence corresponding to the target history text;

[0123] Adjust the confidence threshold to a smaller value based on the target's historical confidence and confidence level.

[0124] For example, the electronic device may determine the minimum confidence from the confidence and the target historical confidence, and set the confidence threshold to be smaller than the minimum confidence, and the difference from the minimum confidence is smaller than the second difference threshold. The second difference threshold may be preset based on actual conditions.

[0125] In an optional embodiment, taking into account the situation that a user speaks the same text multiple times within a certain period of time, and only a few texts have corresponding confidences less than a first confidence threshold, when the keyword matches the text and the first confidence is not greater than the first confidence threshold, the historical text and historical confidence corresponding to each historical voice data to be recognized obtained in the second historical period of time are obtained; if there is a target historical text matching the text in the historical text, the historical confidence corresponding to the target historical text is not greater than the first confidence threshold, and the number of target historical texts is not less than the second number threshold, then the first confidence threshold is adjusted down.

[0126] For example, if the historical texts corresponding to the historical voice data to be recognized acquired by an electronic device multiple times in the second historical period all match the text, but the confidence levels are all less than the first confidence threshold, the first confidence threshold can be adjusted down. The second historical period can be preset. For example, the second historical period can be within 5 minutes, within 10 minutes, within 30 minutes, and so on.

[0127] For example, assuming that the second quantity threshold is 9, assuming that the text corresponding to the voice data to be recognized obtained by an electronic device at the 10th minute matches the keyword, and the confidence corresponding to the voice data to be recognized, that is, the first confidence is not greater than the first confidence threshold, and among the historical voice data to be recognized obtained within the first 9 minutes, 9 historical texts corresponding to the historical voice data to be recognized all match the text, and the historical confidence corresponding to the historical texts corresponding to the 9 historical voice data to be recognized is not greater than the first confidence threshold, and the number of historical texts corresponding to the 9 historical voice data to be recognized is not less than the second quantity threshold, then it can be determined that the user said the same keyword multiple times within these 10 minutes, but because the confidence threshold is set high, it was not recognized by the electronic device, then the electronic device can reduce the first confidence threshold. Among them, the second quantity threshold can be set in advance.

[0128] It should be noted that, when speech recognition is performed on a certain speech data to be recognized, the speech recognition result obtained includes text and confidence. The text can be used as the text corresponding to the speech data to be recognized, the confidence can be used as the confidence corresponding to the speech data to be recognized, and the confidence can also be used as the confidence corresponding to the text.

[0129] For example, speech recognition is performed on a certain historical speech data to be recognized to obtain a historical speech recognition result. The historical speech recognition result includes a historical text and a historical confidence. The historical text is the historical text corresponding to the historical speech data to be recognized. The historical confidence can be the historical confidence corresponding to the historical speech data to be recognized, or it can be the historical confidence corresponding to the historical text.

[0130] In an optional embodiment, performing keyword detection on the voice data to be detected to obtain keywords in the voice data to be detected includes:

[0131] Perform keyword detection on the speech data to be detected by a keyword detection engine to obtain a keyword detection result, wherein the keyword detection result includes a keyword and a second confidence level;

[0132] Acquire the voice data containing the keyword from the voice data to be detected to obtain the voice data to be recognized, including:

[0133] If the second confidence is not less than the second confidence threshold and not greater than the third confidence threshold, the voice data containing the keyword is obtained from the voice data to be detected to obtain the voice data to be recognized.

[0134] In order to further reduce the power consumption of the electronic device, for the voice data to be detected whose corresponding second confidence is not less than the second confidence threshold, it is also possible to directly determine the control instruction corresponding to the voice data to be detected and execute the control instruction when the second confidence is relatively high, such as greater than the fourth confidence threshold.

[0135] The fourth confidence threshold may be preset, for example, the fourth confidence threshold may be 0.9, 0.91, and so on.

[0136] In order to reduce the misrecognition rate, for the voice data to be detected whose corresponding second confidence is not less than the second confidence threshold, when the second confidence is relatively low, such as not greater than the third confidence threshold, the step of obtaining the voice data containing the keyword from the voice data to be detected to obtain the voice data to be recognized can be performed.

[0137] The third confidence threshold can be preset. The third confidence is not greater than the fourth confidence threshold. For example, the third confidence threshold can be 0.7, 0.9, 0.91, and so on.

[0138] In an optional embodiment, the third confidence thresholds corresponding to different keywords may be the same. For example, the third confidence thresholds corresponding to different keywords are all 0.9.

[0139] In an optional embodiment, taking into account that the confidence output by the keyword detection engine for different keywords is not the same, for example, for some keywords, the confidence output by the keyword detection engine is generally high, while for other keywords, the confidence output by the keyword detection engine is generally low, therefore, in this embodiment, different confidence thresholds can be set for different keywords, and after obtaining the keyword and the second confidence corresponding to the voice data to be detected, the confidence threshold corresponding to the keyword corresponding to the voice data to be detected is determined as the third confidence threshold; then, based on the second confidence, the second confidence threshold and the third confidence threshold, it is determined whether to execute the step of obtaining the voice data where the keyword is located from the voice data to be detected to obtain the voice data to be recognized.

[0140] For example, for a certain keyword or certain keywords, the corresponding confidence level is usually between 0.38 and 0.5, then the confidence level threshold corresponding to the keyword or keywords can be set to 0.5. To further reduce the misrecognition rate, the confidence level threshold corresponding to the keyword or keywords can also be set to a larger value, for example, the confidence level threshold corresponding to the keyword or keywords can be set to 0.55.

[0141] For another example, for a certain keyword or certain keywords, the corresponding confidence level is usually between 0.6 and 0.7, then the confidence level threshold corresponding to the keyword or keywords can be set to 0.7. To further reduce the misrecognition rate, the confidence level threshold corresponding to the keyword or keywords can also be set to a larger value, for example, the confidence level threshold corresponding to the keyword or keywords can be set to 0.8.

[0142] In actual applications, if the determined third confidence threshold is less than the fourth confidence threshold, the step of obtaining the voice data containing the keyword from the voice data to be detected to obtain the voice data to be recognized can be performed when the second confidence is greater than the third confidence threshold but not greater than the fourth confidence threshold; or the step of directly determining the control instruction corresponding to the voice data to be detected and executing the control instruction can be performed when the second confidence is greater than the third confidence threshold but not greater than the fourth confidence threshold. The specific details shall be subject to actual needs.

[0143] For example, if the determined third confidence threshold is less than the fourth confidence threshold, then when the second confidence is greater than the third confidence threshold but not greater than the fourth confidence threshold, the remaining power of the battery of the electronic device and / or the remaining available resources of the processor of the electronic device can be obtained; if the remaining power is not less than the power threshold and / or the remaining available resources are not less than the resource threshold, then the step of obtaining the voice data containing the keyword from the voice data to be detected to obtain the voice data to be recognized is executed; if the remaining power is less than the power threshold and / or the remaining available resources are less than the resource threshold, then the step of determining the control instruction corresponding to the voice data to be detected and executing the control instruction is executed.

[0144] In an optional embodiment, determining a control instruction corresponding to the voice data to be detected includes:

[0145] Performing speech recognition on the speech data to be detected to obtain a second speech recognition result, wherein the second speech recognition result includes the text to be analyzed;

[0146] Perform semantic analysis on the text to be analyzed to obtain semantic analysis results;

[0147] Determine the control instruction corresponding to the semantic analysis result, and obtain the control instruction corresponding to the voice data to be detected.

[0148] It is understandable that when the keyword matches the text, the speech recognition engine can perform speech recognition on the speech data to be detected to obtain a second speech recognition result, which includes the text to be analyzed. Then, the semantic analysis engine performs semantic analysis on the recognized text to obtain a semantic analysis result, and then determines the control instruction corresponding to the semantic analysis result.

[0149] The control instructions may include but are not limited to: playing the next song, playing a certain song, turning on a certain appliance, calling a certain person, navigating to a certain location, etc.

[0150] In an optional embodiment, performing speech recognition on the speech data to be detected to obtain a second speech recognition result includes:

[0151] If the keyword is a keyword of the target category, speech recognition is performed on the speech data to be detected by a local speech recognition engine to obtain a second speech recognition result.

[0152] To avoid leakage of user privacy, some keywords related to user privacy can be set as target category keywords in advance. For example, "call" and "send text message to" involve obtaining user address books, and user address books are usually private data. Therefore, the above keywords can be set as target category keywords. When the detected keyword is a target category keyword, only the local speech recognition engine is used to perform speech recognition on the speech data to be detected to obtain a second speech recognition result.

[0153] In an optional embodiment, performing speech recognition on the speech data to be detected to obtain a second speech recognition result includes:

[0154] If the keyword is not a keyword of the target category, the local speech recognition engine and the cloud speech recognition engine are used to perform speech recognition on the speech data to be detected;

[0155] If a first candidate voice recognition result output by the cloud voice recognition engine is obtained within a preset period of time, the first candidate voice recognition result is determined as the second voice recognition result;

[0156] If the first candidate voice recognition result is not obtained within the preset time period, the second candidate voice recognition result output by the local voice recognition engine is determined as the second voice recognition result.

[0157] Due to the limitation of storage space and processing resources of electronic devices, the accuracy of speech recognition of the local cloud recognition engine is relatively low compared to that of the cloud speech recognition engine. Therefore, in this embodiment, when the detected keyword is not a keyword of the target category, the cloud speech recognition engine and the local recognition engine can be used to perform speech recognition on the speech data to be detected. Considering that the interaction with the cloud speech recognition engine involves data communication, when the network quality is poor, the cloud speech recognition engine usually does not promptly feedback the output first speech recognition result. In order to ensure the response speed of voice control, in this embodiment, when the first candidate speech recognition result is obtained within the target time period, the first candidate speech recognition result can be determined as the second speech recognition result; when the first candidate speech recognition result is not received within the target time period, the second candidate speech recognition result output by the local speech recognition engine can be determined as the second speech recognition result.

[0158] The target period can be set by the user or by the electronic device based on certain rules. In order to ensure the response speed of the voice control, the target period can be set shorter. For example, the target period can be 500 milliseconds, 1 second, etc.

[0159] In an optional embodiment, performing speech recognition on the speech data to be detected to obtain a second speech recognition result includes:

[0160] If the keyword is not a keyword of the target category, it is determined whether the current network quality is lower than the quality threshold;

[0161] If the current network quality is lower than the quality threshold, the local speech recognition engine performs speech recognition on the speech data to be detected to obtain a second speech recognition result;

[0162] If the current network quality is not lower than the quality threshold, the cloud-based speech recognition engine performs speech recognition on the speech data to be detected to obtain a second speech recognition result.

[0163] It can be understood that if the keyword is not a keyword of the target category, either the local speech recognition engine or the cloud speech recognition engine can be used for speech recognition. Considering that when the network quality is lower than the quality threshold, it will affect the speed at which the cloud recognition engine feeds back the speech recognition results, and thus affect the response speed of the voice control. Based on this, in this embodiment, if the keyword is not a keyword of the target category, then when the current network quality is lower than the quality threshold, the local speech recognition engine is used to perform speech recognition on the speech data to be detected to obtain a second speech recognition result; when the current network quality is not lower than the quality threshold, the cloud speech recognition engine is used to perform speech recognition on the speech data to be detected to obtain a second speech recognition result.

[0164] Specifically, it may be detected based on the network quality parameter whether the current network quality is lower than a preset threshold.

[0165] The network quality parameters may include network signal strength, network transmission delay or network packet loss rate, etc. Based on this, the electronic device determines whether the current network quality is lower than the quality threshold according to the following method;

[0166] (1) monitoring in real time whether the network signal strength of the current network is lower than the signal strength threshold, and when the network signal strength is lower than the signal strength threshold, determining that the current network quality is lower than the quality threshold;

[0167] (2) monitoring in real time whether the network transmission delay of the current network is greater than the network transmission delay threshold, and when it is detected that the network transmission delay is greater than the network transmission delay threshold, determining that the current network quality is lower than the quality threshold;

[0168] (3) Real-time monitoring of whether a network packet loss rate of the current network is greater than a network packet loss rate threshold. When it is detected that the network packet loss rate is greater than the network packet loss rate threshold, it is determined that the current network quality is lower than the quality threshold.

[0169] Among them, the signal strength threshold, network transmission delay threshold, and network packet loss rate threshold can be pre-set based on actual needs.

[0170] It should be noted that the method for detecting whether the network quality is lower than the quality threshold is not limited to the above description.

[0171] In an optional embodiment, obtaining the voice data to be detected includes:

[0172] Determine the current usage scenario;

[0173] If the current usage scenario is a preset usage scenario, the wake-up-free function is started and the voice data to be detected is obtained. The preset usage scenario includes at least one of a driving scenario, an audio playback scenario, a call scenario, and a shooting scenario.

[0174] Among them, the current usage scenario can be determined by the function of the electronic device used by the current application. For example, if the positioning function is being used through navigation software, it means that the current usage scenario is a driving scenario. For another example, if the speaker of the electronic device is enabled through certain applications for audio playback, it means that the current usage scenario is an audio playback scenario, where the application may be, for example, Kugou Music, QQ Music, NetEase Cloud Music, Kuwo Music, Douyin, Kuaishou, Tencent Video, Youku Video, iQiyi Video, etc. For another example, if the electronic device is connected to the network and the microphone is enabled through certain applications for network communication, it means that the current usage scenario is a call scenario, and the application may be, for example, a phone, WeChat, QQ, etc. For another example, if the camera of the electronic device is enabled through certain applications for image acquisition, it means that the current usage scenario is a shooting scene, and the application may be, for example, a camera, WeChat, Alipay, etc. that comes with the electronic device.

[0175] It can be understood that the above-mentioned preset usage scenarios are limited to examples, and the purpose is to illustrate that when the electronic device enters such preset usage scenarios, the wake-up-free function can be automatically started, thereby avoiding the need for users to manually operate the wake-up-free function, making it more convenient for users to use and improving the startup efficiency of the wake-up-free function.

[0176] It should also be noted that if the wake-up-free function has been activated before detecting the current usage scenario, the wake-up-free function will not be activated again here. The wake-up-free function will only be activated if it has been turned off before.

[0177] In an optional embodiment, if the current usage scenario is an audio playback scenario, before performing keyword detection on the voice data to be detected and obtaining the keywords in the voice data to be detected, the method further includes:

[0178] Get the audio data to be played;

[0179] Perform echo elimination on the voice data to be detected according to the audio data to obtain the target voice data to be detected;

[0180] Perform keyword detection on the voice data to be detected to obtain keywords in the voice data to be detected, including:

[0181] Perform keyword detection on the target voice data to be detected to obtain keywords in the voice data to be detected;

[0182] Acquire the voice data containing the keyword from the voice data to be detected, including:

[0183] The speech data containing the key words is obtained from the target speech data to be detected.

[0184] In this embodiment, the voice data in the audio playback scene can be echo-cancelled first to filter the audio data played externally by the electronic device from the voice data, so that the voice data after echo cancellation no longer contains the audio data currently played by the electronic device. This method can avoid the interference of the audio data played externally by the electronic device on the voice data during the voice recognition process, which is beneficial to improving the accuracy of voice recognition.

[0185] When performing echo cancellation, the number of echo channels can be made consistent with the number of channels for playing audio data through the speaker, thereby facilitating the elimination of echoes related to audio data in voice data.

[0186] In some embodiments, if the current usage scenario is a driving scenario or a call scenario, before performing keyword detection on the voice data to be detected to obtain the keywords in the voice data to be detected, it also includes: performing noise reduction processing on the voice data to obtain the voice data after noise reduction processing; performing keyword detection on the voice data to be detected to obtain the keywords in the voice data to be detected, including: performing keyword detection on the voice data after noise reduction processing to obtain the keywords in the voice data after noise reduction processing; obtaining the voice data where the keywords are located from the voice data to be detected to obtain the voice data to be recognized, including: obtaining the voice data where the keywords are located from the voice data after noise reduction processing to obtain the voice data to be recognized.

[0187] In this embodiment, by performing noise reduction processing on the voice data, the external environmental noise in the voice data can be filtered, which is beneficial to improving the accuracy of the voice data when performing voice recognition.

[0188] The external environmental noise may be, for example, the sound of a car horn or a car engine in a driving scenario, or may be, for example, the noise of other users or environmental noise in a call scenario.

[0189] In an optional embodiment, if the current usage scenario changes, and the changed usage scenario is not the preset usage scenario, the wake-up-free function is turned off. The change in the current usage scenario may refer to the electronic device exiting the current usage scenario, or other applications of the electronic device being started. When the current usage scenario changes, it can also be determined whether the changed usage scenario is the preset usage scenario. If so, the wake-up-free function is kept enabled, and if not, the wake-up-free function is turned off.

[0190] In an optional embodiment, the user may also manually turn off the wake-up-free function.

[0191] It can be understood that when the wake-up-free function is turned off, the electronic device can turn off the audio collection function, local voice recognition engine, cloud voice recognition engine, semantic analysis engine, etc. The specific implementation method can be selected by technical personnel in this field according to actual needs and is not limited here.

[0192] Please also read Figure 2 and Figure 3 , Figure 2 is a second flow chart of the voice control method provided in the embodiment of the present application, Figure 3 : is a scene diagram of the voice control method provided in an embodiment of the present application, and the process may include:

[0193] In 201, the voice data to be detected is obtained, and the keyword detection is performed on the voice data to be detected by a keyword detection engine to obtain keywords in the voice data to be detected.

[0194] In 202, a target duration is determined according to the word count of the keyword, and the target duration is positively correlated with the word count.

[0195] In 203, the end time of the voice data where the last keyword in the keywords is located is determined.

[0196] In 204 , the speech data of the target duration before the end time in the speech data to be detected is determined as the speech data where the keyword is located, and the speech data to be recognized is obtained.

[0197] In 205 , a speech recognition engine performs speech recognition on the speech data to be recognized to obtain a first speech recognition result, where the first speech recognition result includes text and a first confidence level.

[0198] In 206, if the keyword matches the text and the first confidence is greater than the first confidence threshold, a speech recognition engine is used to perform speech recognition on the speech data to be detected to obtain a second speech recognition result, which includes the text to be analyzed.

[0199] In 207, a semantic analysis engine performs semantic analysis on the text to be analyzed to obtain a semantic analysis result.

[0200] In 208, a control instruction corresponding to the semantic analysis result is determined, a control instruction corresponding to the speech data to be detected is obtained, and the control instruction is executed.

[0201] The above process will be described below with a specific example.

[0202] For example, assume the user says to the electronic device: "Navigate to xx Restaurant", and the electronic device then obtains the voice data to be detected. Then, the electronic device performs keyword detection on the voice data to be detected through a keyword detection engine and obtains the keyword "daohangdao".

[0203] Assume the duration of the voice data to be detected is 3 seconds, the end time of the last keyword "dao" in the keyword "Navigate to" is the 1.5th second of the voice data to be detected, and the target duration is 1.2 seconds. Then, 1.2 seconds of voice data before the 1.5th second in the voice data to be detected can be obtained as the voice data to be recognized. After obtaining the voice data to be recognized, the electronic device performs voice recognition on the voice data to be recognized through a voice recognition engine and obtains a first voice recognition result. The first voice recognition result includes text and a first confidence level. Assume the text is "daohangdao", the first confidence level is 0.9, and the first confidence level threshold is 0.85. It can be determined that the keyword matches the text and the first confidence level is greater than the first confidence level threshold. Then, the electronic device can perform voice recognition on the voice data to be detected through the voice recognition engine and obtain a second voice recognition result. The second voice recognition result includes the text to be analyzed.

[0204] Assume the text to be analyzed is "Navigate to xx Restaurant". Then, the electronic device performs voice analysis on the text to be analyzed through a semantic analysis engine and obtains a semantic analysis result. It can be determined that the semantic analysis result indicates navigating to xx Restaurant. Then, the electronic device can determine that the control instruction is "Navigate to xx Restaurant". Then, the electronic device can navigate to xx Restaurant through the installed navigation application and display the navigation route.

[0205] Please refer to Figure 4 , Figure 4 which is a schematic structural diagram of the voice control device provided by an embodiment of the present application. The voice control device 300 includes: a keyword detection module 301, a data acquisition module 302, a voice recognition module 303, and an instruction execution module 304.

[0206] The keyword detection module 301 is configured to obtain the voice data to be detected and perform keyword detection on the voice data to be detected to obtain the keyword in the voice data to be detected.

[0207] The data acquisition module 302 is configured to obtain the voice data where the keyword is located from the voice data to be detected to obtain the voice data to be recognized.

[0208] The voice recognition module 303 is configured to perform voice recognition on the voice data to be recognized to obtain a first voice recognition result.

[0209] The instruction execution module 304 is used to determine the control instruction corresponding to the voice data to be detected if the keyword matches the first voice recognition result, and execute the control instruction.

[0210] In an optional embodiment, the data acquisition module 302 may be used to: determine the end time of the voice data containing the last keyword in the keywords; and acquire the voice data to be recognized from the voice data to be detected according to the end time.

[0211] In an optional embodiment, the data acquisition module 302 can be used to: determine the target duration based on the number of words in the keyword, and the target duration is positively correlated with the number of words; and obtain the voice data of the target duration from the voice data to be detected as the voice data to be recognized based on the end time.

[0212] In an optional embodiment, the data acquisition module 302 can be used to: perform speech rate detection on the voice data to be detected to obtain the speech rate corresponding to the voice data to be detected; determine the target duration based on the number of words and the speech rate, and the target duration is inversely correlated with the speech rate.

[0213] In an optional embodiment, the data acquisition module 302 may be configured to: determine corresponding voice data before the end time in the voice data to be detected as the voice data to be recognized.

[0214] In an optional embodiment, the data acquisition module 302 may be used to: determine the corresponding voice data before the end time and the corresponding voice data after the end time in the voice data to be detected as the voice data to be recognized.

[0215] In an optional embodiment, the first speech recognition result includes text, and the instruction execution module 304 can be used to: if the keyword matches the text and the confidence is greater than a confidence threshold, determine the control instruction corresponding to the speech data to be detected.

[0216] In an optional embodiment, the first speech recognition result also includes a first confidence level, and the instruction execution module 304 can be used to: if the keyword matches the text and the first confidence level is greater than a first confidence level threshold, determine a control instruction corresponding to the speech data to be detected.

[0217] In an optional embodiment, the voice control device 300 may also include a threshold adjustment module, which may be used to: if the keyword matches the text, the first confidence is greater than a first confidence threshold, and the difference between the first confidence and the first confidence threshold is greater than a difference threshold, then obtain the historical confidence corresponding to each of the historical voice data to be recognized in the historical voice data to be recognized acquired within the first historical period; determine a target historical confidence from the historical confidences, the target historical confidence is a historical confidence greater than the first confidence threshold, and the difference between the target historical confidence and the first confidence threshold is greater than the difference threshold; determine a first quantity of the first confidence and the target historical confidence, and determine a second quantity of the first confidence and the historical confidence; if the first quantity is not less than a first quantity threshold, and the ratio of the first quantity to the second quantity is not less than a ratio threshold, then increase the first confidence threshold.

[0218] In an optional embodiment, the threshold adjustment module can be used to: if the keyword matches the text and the first confidence is not greater than the first confidence threshold, then obtain the historical text corresponding to each of the historical voice data to be recognized obtained in the second historical period; if there is a target historical text matching the text in the historical text, and the number of the target historical text is not less than the second number threshold, then reduce the first confidence threshold.

[0219] In an optional embodiment, the keyword detection module 301 may be used to: perform keyword detection on the to-be-detected voice data through a keyword detection engine to obtain a keyword detection result, wherein the keyword detection result includes a keyword and a second confidence level;

[0220] The data acquisition module 302 may be configured to: if the second confidence is not less than a second confidence threshold and not greater than a third confidence threshold, acquire the voice data containing the keyword from the voice data to be detected to obtain the voice data to be recognized.

[0221] In an optional embodiment, the instruction execution module 304 can be used to: perform speech recognition on the voice data to be detected to obtain a second speech recognition result, wherein the second speech recognition result includes a text to be analyzed; perform semantic analysis on the text to be analyzed to obtain a semantic analysis result; determine a control instruction corresponding to the semantic analysis result to obtain a control instruction corresponding to the voice data to be detected.

[0222] In an optional embodiment, the instruction execution module 304 may be used to: if the keyword is a keyword of a target category, perform speech recognition on the speech data to be detected by a local speech recognition engine to obtain a second speech recognition result.

[0223] In an optional embodiment, the instruction execution module 304 can be used to: if the keyword is not a keyword of the target category, perform speech recognition on the voice data to be detected through a local speech recognition engine and a cloud speech recognition engine; if a first candidate speech recognition result output by the cloud speech recognition engine is obtained within a preset time period, the first candidate speech recognition result is determined as the second speech recognition result; if the first candidate speech recognition result is not obtained within the preset time period, the second candidate speech recognition result output by the local speech recognition engine is determined as the second speech recognition result.

[0224] In an optional embodiment, the instruction execution module 304 can be used to: if the keyword is not a keyword of the target category, determine whether the current network quality is lower than a quality threshold; if the current network quality is lower than the quality threshold, perform speech recognition on the voice data to be detected by a local speech recognition engine to obtain a second speech recognition result; if the current network quality is not lower than the quality threshold, perform speech recognition on the voice data to be detected by a cloud-based speech recognition engine to obtain a second speech recognition result.

[0225] In an optional embodiment, the keyword detection module 301 can be used to: determine the current usage scenario; if the current usage scenario is a preset usage scenario, start the wake-up-free function and obtain the voice data to be detected, and the preset usage scenario includes at least one of a driving scenario, an audio playback scenario, a call scenario and a shooting scenario.

[0226] In an optional embodiment, if the current usage scenario is an audio playback scenario, the keyword detection module 301 can be used to: obtain the played audio data; perform echo cancellation on the voice data to be detected according to the audio data to obtain the target voice data to be detected; perform keyword detection on the target voice data to be detected to obtain the keywords in the target voice data to be detected;

[0227] The data acquisition module 302 may be used to acquire the speech data containing the keyword from the target speech data to be detected.

[0228] An embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed on a computer, the computer executes the voice control method provided in this embodiment.

[0229] An embodiment of the present application also provides an electronic device, including a memory and a processor, wherein the processor is used to execute the voice control method provided in the present embodiment by calling a computer program stored in the memory.

[0230] For example, the electronic device may be a mobile terminal such as a tablet computer or a smart phone. Figure 5 , Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0231] The electronic device 400 may include components such as a processor 401 and a memory 402. Those skilled in the art will appreciate that Figure 5 The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. For example, the electronic device 400 may also include a microphone.

[0232] The processor 401 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. It executes various functions of the electronic device and processes data by running or executing applications stored in the memory 402 and calling data stored in the memory 402, thereby monitoring the electronic device as a whole.

[0233] The memory 402 may be used to store applications and data. The applications stored in the memory 402 include executable codes. The applications may be composed of various functional modules. The processor 401 executes various functional applications and data processing by running the applications stored in the memory 402.

[0234] In this embodiment, the processor 401 in the electronic device will load the executable code corresponding to the process of one or more application programs into the memory 402 according to the following instructions, and the processor 401 will run the application program stored in the memory 402, thereby achieving:

[0235] Acquire voice data to be detected, and perform keyword detection on the voice data to be detected to obtain keywords in the voice data to be detected;

[0236] Acquire the voice data containing the keyword from the voice data to be detected to obtain the voice data to be recognized;

[0237] Performing speech recognition on the speech data to be recognized to obtain a first speech recognition result;

[0238] If the keyword matches the first speech recognition result, a control instruction corresponding to the speech data to be detected is determined and the control instruction is executed.

[0239] In an optional embodiment, when the processor 401 executes the step of obtaining the voice data containing the keyword from the voice data to be detected and obtains the voice data to be recognized, it can execute: determining the end time of the voice data containing the last keyword among the keywords; and obtaining the voice data to be recognized from the voice data to be detected according to the end time.

[0240] In an optional embodiment, before the processor 401 executes the step of obtaining the voice data to be recognized from the voice data to be detected according to the end time, it may also execute: determining a target duration according to the number of words in the keyword, wherein the target duration is positively correlated with the number of words; when the processor 401 executes the step of obtaining the voice data to be recognized from the voice data to be detected according to the end time, it may execute: obtaining voice data of the target duration from the voice data to be detected as the voice data to be recognized according to the end time.

[0241] In an optional embodiment, before the processor 401 executes the step of determining the target duration based on the number of words of the keyword, it may also execute: performing speech rate detection on the voice data to be detected to obtain the speech rate corresponding to the voice data to be detected; when the processor 401 executes the step of determining the target duration based on the number of words of the keyword, it may execute: determining the target duration based on the number of words and the speech rate, wherein the target duration is inversely correlated with the speech rate.

[0242] In an optional embodiment, when the processor 401 executes the step of obtaining the voice data to be recognized from the voice data to be detected according to the end time, it may execute: determining the corresponding voice data in the voice data to be detected before the end time as the voice data to be recognized.

[0243] In an optional embodiment, when the processor 401 executes the acquisition of the voice data to be recognized from the voice data to be detected according to the end time, it can execute: determining the corresponding voice data before the end time and the corresponding voice data after the end time in the voice data to be detected as the voice data to be recognized.

[0244] In an optional embodiment, the first voice recognition result includes text. When the processor 401 executes the step of determining the control instruction corresponding to the voice data to be detected if the keyword matches the first voice recognition result, it may execute: if the keyword matches the text, determining the control instruction corresponding to the voice data to be detected.

[0245] In an optional embodiment, the first speech recognition result also includes a first confidence level. When the processor 401 executes the step of determining the control instruction corresponding to the speech data to be detected if the keyword matches the text, it may execute: if the keyword matches the text and the first confidence level is greater than a first confidence level threshold, determining the control instruction corresponding to the speech data to be detected.

[0246] In an optional embodiment, the processor 401 may also execute: if the keyword matches the text, the first confidence is greater than a first confidence threshold, and the difference between the first confidence and the first confidence threshold is greater than a difference threshold, then obtaining the historical confidence corresponding to each of the historical voice data to be recognized in the historical voice data to be recognized obtained within the first historical period; determining a target historical confidence from the historical confidences, the target historical confidence being a historical confidence greater than the first confidence threshold, and the difference between the target historical confidence and the first confidence threshold is greater than the difference threshold; determining a first quantity of the first confidence and the target historical confidence, and determining a second quantity of the first confidence and the historical confidence; if the first quantity is not less than a first quantity threshold, and the ratio of the first quantity to the second quantity is not less than a ratio threshold, then increasing the first confidence threshold.

[0247] In an optional embodiment, the processor 401 can also execute: if the keyword matches the text and the first confidence is not greater than the first confidence threshold, then obtain the historical text corresponding to each of the historical voice data to be recognized obtained in the second historical period; if there is a target historical text matching the text in the historical text, and the number of the target historical text is not less than the second number threshold, then reduce the first confidence threshold.

[0248] In an optional embodiment, when the processor 401 performs the keyword detection on the voice data to be detected and obtains the keywords in the voice data to be detected, it can execute: performing keyword detection on the voice data to be detected by a keyword detection engine to obtain a keyword detection result, and the keyword detection result includes the keyword and a second confidence level; when the processor 401 performs the acquisition of the voice data where the keyword is located from the voice data to be detected and obtains the voice data to be recognized, it can execute: if the second confidence level is not less than the second confidence level threshold and not greater than the third confidence level threshold, then acquiring the voice data where the keyword is located from the voice data to be detected to obtain the voice data to be recognized.

[0249] In an optional embodiment, when the processor 401 executes the determination of the control instruction corresponding to the voice data to be detected, it can execute: performing voice recognition on the voice data to be detected to obtain a second voice recognition result, the second voice recognition result includes a text to be analyzed; performing semantic analysis on the text to be analyzed to obtain a semantic analysis result; determining the control instruction corresponding to the semantic analysis result, and obtaining a control instruction corresponding to the voice data to be detected.

[0250] In an optional embodiment, when the processor 401 performs the speech recognition on the speech data to be detected and obtains the second speech recognition result, it can execute: if the keyword is a keyword of the target category, then the speech recognition is performed on the speech data to be detected by a local speech recognition engine to obtain a second speech recognition result.

[0251] In an optional embodiment, when the processor 401 performs the speech recognition on the speech data to be detected and obtains the second speech recognition result, it can execute: if the keyword is not a keyword of the target category, then speech recognition is performed on the speech data to be detected by a local speech recognition engine and a cloud speech recognition engine; if a first candidate speech recognition result output by the cloud speech recognition engine is obtained within a preset time period, then the first candidate speech recognition result is determined as the second speech recognition result; if the first candidate speech recognition result is not obtained within the preset time period, then the second candidate speech recognition result output by the local speech recognition engine is determined as the second speech recognition result.

[0252] In an optional embodiment, when the processor 401 performs the speech recognition on the voice data to be detected and obtains the second speech recognition result, it can execute: if the keyword is not a keyword of the target category, determining whether the current network quality is lower than the quality threshold; if the current network quality is lower than the quality threshold, performing speech recognition on the voice data to be detected by a local speech recognition engine to obtain a second speech recognition result; if the current network quality is not lower than the quality threshold, performing speech recognition on the voice data to be detected by a cloud-based speech recognition engine to obtain a second speech recognition result.

[0253] In an optional embodiment, when the processor 401 executes the acquisition of the voice data to be detected, it can execute: determining the current usage scenario; if the current usage scenario is a preset usage scenario, starting the wake-up-free function and acquiring the voice data to be detected, and the preset usage scenario includes at least one of a driving scenario, an audio playback scenario, a call scenario, and a shooting scenario.

[0254] In an optional embodiment, if the current usage scenario is an audio playback scenario, before the processor 401 executes the keyword detection on the voice data to be detected and obtains the keywords in the voice data to be detected, it can also execute: obtaining the played audio data; performing echo elimination on the voice data to be detected according to the audio data to obtain the target voice data to be detected; when the processor 401 executes the keyword detection on the voice data to be detected and obtains the keywords in the voice data to be detected, it can execute: performing keyword detection on the target voice data to be detected and obtains the keywords in the target voice data to be detected; when the processor 401 executes the acquisition of the voice data where the keywords are located from the voice data to be detected, it can execute: acquiring the voice data where the keywords are located from the target voice data to be detected.

[0255] In the above embodiments, the description of each embodiment has its own focus. For the part that is not described in detail in a certain embodiment, please refer to the detailed description of the voice control method above, and will not be repeated here.

[0256] The voice control device provided in the embodiment of the present application belongs to the same concept as the voice control method in the above embodiment. Any method provided in the voice control method embodiment can be run on the voice control device. The specific implementation process is detailed in the voice control method embodiment, which will not be repeated here.

[0257] It should be noted that, for the voice control method of the embodiment of the present application, a person of ordinary skill in the art can understand that all or part of the process of implementing the voice control method of the embodiment of the present application can be completed by controlling the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, such as a memory, and executed by at least one processor, and the execution process may include the process of the embodiment of the voice control method. Among them, the computer-readable storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), etc.

[0258] It is understandable that in the specific implementation of this application, user information is involved, such as application usage behavior data, logs and other related data. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0259] For the voice control device of the embodiment of the present application, each functional module can be integrated into a processing chip, or each module can exist physically separately, or two or more modules can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium, such as a read-only memory, a disk or an optical disk.

[0260] The above is a detailed introduction to a voice control method, device, storage medium and electronic device provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A voice control method, characterized in that: include: Acquire voice data to be detected, and perform keyword detection on the voice data to be detected to obtain keywords in the voice data to be detected; Acquire the voice data containing the keyword from the voice data to be detected to obtain the voice data to be recognized; Performing speech recognition on the speech data to be recognized to obtain a first speech recognition result; If the keyword matches the first speech recognition result, a control instruction corresponding to the speech data to be detected is determined and the control instruction is executed.

2. The voice control method according to claim 1, characterized in that: The acquiring the voice data containing the keyword from the voice data to be detected to obtain the voice data to be recognized includes: Determine the end time of the voice data where the last keyword in the keywords is located; The voice data to be recognized is obtained from the voice data to be detected according to the end time.

3. The voice control method according to claim 2, characterized in that: Before acquiring the voice data to be recognized from the voice data to be detected according to the end time, the method further includes: Determine a target duration according to the word count of the keyword, wherein the target duration is positively correlated with the word count; The acquiring the to-be-recognized voice data from the to-be-detected voice data according to the end time includes: According to the end time, voice data of the target duration is acquired from the voice data to be detected as the voice data to be recognized.

4. The voice control method according to claim 3, characterized in that: Before determining the target duration according to the word count of the keyword, the method further includes: Performing speech rate detection on the speech data to be detected to obtain the speech rate corresponding to the speech data to be detected; Determining the target duration according to the word count of the keyword includes: The target duration is determined according to the number of words and the speaking speed, and the target duration is inversely correlated with the speaking speed.

5. The voice control method according to claim 2, characterized in that: The acquiring the to-be-recognized voice data from the to-be-detected voice data according to the end time includes: The corresponding voice data before the end time in the voice data to be detected is determined as the voice data to be recognized.

6. The voice control method according to claim 2, characterized in that: The acquiring the to-be-recognized voice data from the to-be-detected voice data according to the end time includes: The corresponding voice data before the end time and the corresponding voice data after the end time in the voice data to be detected are determined as the voice data to be recognized.

7. The voice control method according to claim 1, characterized in that: The first voice recognition result includes text, and if the keyword matches the first voice recognition result, determining a control instruction corresponding to the voice data to be detected includes: If the keyword matches the text, a control instruction corresponding to the voice data to be detected is determined.

8. The voice control method according to claim 7, characterized in that: The first speech recognition result also includes a first confidence level, and if the keyword matches the text, determining a control instruction corresponding to the speech data to be detected includes: If the keyword matches the text and the first confidence level is greater than a first confidence level threshold, a control instruction corresponding to the voice data to be detected is determined.

9. The voice control method according to claim 8, characterized in that: The method further comprises: If the keyword matches the text, the first confidence is greater than a first confidence threshold, and the difference between the first confidence and the first confidence threshold is greater than a difference threshold, then obtaining a historical confidence corresponding to each of the historical voice data to be recognized in the historical voice data to be recognized acquired within a first historical period; Determining a target historical confidence from the historical confidences, the target historical confidence being a historical confidence that is greater than the first confidence threshold and whose difference from the first confidence threshold is greater than the difference threshold; determining a first quantity of the first confidence and the target historical confidence, and determining a second quantity of the first confidence and the historical confidence; If the first number is not less than a first number threshold, and the ratio of the first number to the second number is not less than a ratio threshold, the first confidence threshold is increased.

10. The voice control method according to claim 8, characterized in that: The method further comprises: If the keyword matches the text, and the first confidence is not greater than a first confidence threshold, obtaining a historical text corresponding to each of the historical voice data to be recognized in the historical voice data to be recognized acquired in a second historical period; If there are target historical texts matching the text in the historical texts, and the number of the target historical texts is not less than a second number threshold, the first confidence threshold is reduced.

11. The voice control method according to claim 1, characterized in that: The performing keyword detection on the voice data to be detected to obtain keywords in the voice data to be detected includes: Performing keyword detection on the to-be-detected voice data by a keyword detection engine to obtain a keyword detection result, wherein the keyword detection result includes a keyword and a second confidence level; The acquiring the voice data containing the keyword from the voice data to be detected to obtain the voice data to be recognized includes: If the second confidence level is not less than the second confidence level threshold and not greater than the third confidence level threshold, the voice data containing the keyword is obtained from the voice data to be detected to obtain the voice data to be recognized.

12. The voice control method according to claim 1, characterized in that: The determining of the control instruction corresponding to the voice data to be detected includes: Performing speech recognition on the speech data to be detected to obtain a second speech recognition result, wherein the second speech recognition result includes a text to be analyzed; Performing semantic analysis on the text to be analyzed to obtain a semantic analysis result; Determine a control instruction corresponding to the semantic analysis result, and obtain a control instruction corresponding to the voice data to be detected.

13. The voice control method according to claim 12, characterized in that: The performing speech recognition on the speech data to be detected to obtain a second speech recognition result includes: If the keyword is a keyword of the target category, speech recognition is performed on the speech data to be detected by a local speech recognition engine to obtain a second speech recognition result.

14. The voice control method according to claim 12, characterized in that: The performing speech recognition on the speech data to be detected to obtain a second speech recognition result includes: If the keyword is not a keyword of the target category, performing speech recognition on the speech data to be detected by using a local speech recognition engine and a cloud speech recognition engine; If a first candidate voice recognition result output by the cloud voice recognition engine is obtained within a preset period of time, the first candidate voice recognition result is determined as the second voice recognition result; If the first candidate voice recognition result is not obtained within a preset period of time, the second candidate voice recognition result output by the local voice recognition engine is determined as the second voice recognition result.

15. The voice control method according to claim 12, characterized in that: The performing speech recognition on the speech data to be detected to obtain a second speech recognition result includes: If the keyword is not a keyword of the target category, determining whether the current network quality is lower than a quality threshold; If the current network quality is lower than the quality threshold, performing speech recognition on the speech data to be detected by a local speech recognition engine to obtain a second speech recognition result; If the current network quality is not lower than the quality threshold, the cloud-based speech recognition engine performs speech recognition on the speech data to be detected to obtain a second speech recognition result.

16. The voice control method according to any one of claims 1 to 15, characterized in that: The step of obtaining the voice data to be detected includes: Determine the current usage scenario; If the current usage scenario is a preset usage scenario, the wake-up-free function is started and the voice data to be detected is obtained. The preset usage scenario includes at least one of a driving scenario, an audio playback scenario, a call scenario, and a shooting scenario.

17. The voice control method according to claim 16, characterized in that: If the current usage scenario is the audio playback scenario, before performing keyword detection on the voice data to be detected to obtain the keywords in the voice data to be detected, the method further includes: Get the audio data to be played; Performing echo cancellation on the voice data to be detected according to the audio data to obtain target voice data to be detected; The performing keyword detection on the voice data to be detected to obtain keywords in the voice data to be detected includes: Performing keyword detection on the target voice data to be detected to obtain keywords in the target voice data to be detected; The acquiring the voice data containing the keyword from the voice data to be detected includes: The voice data where the keyword is located is obtained from the target voice data to be detected.

18. A voice control device, characterized in that: include: A keyword detection module, used to obtain the voice data to be detected, and perform keyword detection on the voice data to be detected to obtain the keywords in the voice data to be detected; A data acquisition module, used to acquire the voice data containing the keyword from the voice data to be detected, so as to obtain the voice data to be recognized; A speech recognition module, used for performing speech recognition on the speech data to be recognized to obtain a first speech recognition result; An instruction execution module is used to determine a control instruction corresponding to the voice data to be detected and execute the control instruction if the keyword matches the first voice recognition result.

19. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed on a computer, the computer executes the voice control method according to any one of claims 1 to 17.

20. An electronic device, characterized in that: The electronic device includes a processor and a memory, wherein a computer program is stored in the memory, and the processor is used to execute the voice control method according to any one of claims 1 to 17 by calling the computer program stored in the memory.

Images