Equipment awakening method and device, equipment and storage medium

Abstract

The invention discloses an equipment awakening method and device, equipment and a storage medium, and the method comprises the steps: obtaining first audio data received by a first audio receiver and second audio data received by a second audio receiver under the condition that a pre-awakening action is detected; determining the distance between the user and the electronic equipment based on the difference between the first audio data and the second audio data under the condition that the plosive sound is not detected based on the first audio data and / or the second audio data; and determining whether to wake up the electronic device based on the distance between the user and the electronic device. Therefore, under the condition that the plosive sound is not detected, the distance between the user and the electronic equipment can be determined by utilizing the difference between the first audio data and the second audio data, so that whether the electronic equipment is within the preset distance range of the user or not is judged, and whether the electronic equipment needs to be awakened or not is determined accordingly; therefore, accurate wakeup of the electronic equipment is realized.

Description

Technical Field

[0001] The present application relates to device wake-up technology, and in particular to a device wake-up method and apparatus, device, and storage medium. Background Art

[0002] Currently, there are two main ways to wake up a device. One is to detect and identify the presence of a pop noise waveform within a very close range to the mouth to determine whether to wake up the device. The other is to detect human voice frequency band speech within a fixed distance range to wake up the device. However, for the first method, after exceeding the very close range to the mouth, the presence of the pop noise cannot be detected, so the device cannot be woken up. For the second method, once the fixed distance range is exceeded, the human voice frequency band speech is weak and may not be able to accurately wake up the device. Summary of the invention

[0003] The present application provides a device wake-up method and apparatus, a device, and a storage medium.

[0004] The technical solution of this application is implemented as follows:

[0005] In a first aspect, a device wake-up method is provided, the method comprising:

[0006] When a pre-wake-up action is detected, obtaining first audio data received by the first audio receiver and second audio data received by the second audio receiver;

[0007] In a case where no plosive sound is detected in the first audio data and / or the second audio data, determining a distance between the user and the electronic device based on a difference between the first audio data and the second audio data;

[0008] Based on the distance between the user and the electronic device, it is determined whether to wake up the electronic device.

[0009] In a second aspect, a device waking up a device is provided, the device comprising:

[0010] An acquiring unit, configured to acquire, when a pre-wake-up action is detected, first audio data received by the first audio receiver and second audio data received by the second audio receiver;

[0011] a processing unit, configured to determine a distance between the user and the electronic device based on a difference between the first audio data and the second audio data, if no plosive sound is detected based on the first audio data and / or the second audio data;

[0012] The processing unit is further used to determine whether to wake up the electronic device based on the distance between the user and the electronic device.

[0013] According to a third aspect, an electronic device is provided, comprising: a processor and a memory configured to store a computer program that can be run on the processor, wherein the processor is configured to execute the steps of the method of the first aspect when running the computer program.

[0014] According to a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, wherein the computer program implements the steps of the method according to the first aspect when executed by a processor.

[0015] According to a fifth aspect, a computer program product is provided, comprising a computer program, wherein the computer program implements the steps of the method according to the first aspect when executed by a processor.

[0016] The present application provides a device wake-up method and apparatus, a device, and a storage medium, the method comprising: when a pre-wake-up action is detected, obtaining first audio data received by a first audio receiver and second audio data received by a second audio receiver; when no plosive sound is detected in the first audio data and / or the second audio data, determining the distance between the user and the electronic device based on the difference between the first audio data and the second audio data; and determining whether to wake up the electronic device based on the distance between the user and the electronic device. In this way, when no plosive sound is detected, the present application will use the difference between the first audio data and the second audio data to determine the distance between the user and the electronic device, so as to determine whether the electronic device is within the preset distance range of the user, and decide whether to wake up the electronic device accordingly, thereby achieving accurate wake-up of the electronic device. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 The process diagram of the device wake-up method in the embodiment of the present application is as follows Figure 1 ;

[0018] Figure 2 The process diagram of the device wake-up method in the embodiment of the present application is as follows Figure 2 ;

[0019] Figure 3 The process diagram of the device wake-up method in the embodiment of the present application is as follows Figure 3 ;

[0020] Figure 4 The process diagram of the device wake-up method in the embodiment of the present application is as follows Figure 4 ;

[0021] Figure 5 The process diagram of the device wake-up method in the embodiment of the present application is as follows Figure 5 ;

[0022] Figure 6 The process diagram of the device wake-up method in the embodiment of the present application is as follows Figure 6 ;

[0023] Figure 7 This is a schematic diagram of the position relationship between the user and the device in the embodiment of the present application;

[0024] Figure 8 The process diagram of the device wake-up method in the embodiment of the present application is as follows Figure 7 ;

[0025] Fig. 9 Schematic diagram of the detection process of the pre-wake-up action in the embodiment of the present application;

[0026] Fig.10 Schematic diagram of the waveform of the plosive sound at different distances in the embodiment of the present application;

[0027] Fig.11 A waveform diagram of a short-distance audio receiver and a long-distance audio receiver in an embodiment of the present application;

[0028] Fig.12 This is a schematic diagram of the structure of the device wake-up device in the embodiment of the present application;

[0029] Fig.13 It is a schematic diagram of the structure of the electronic device in the embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to enable a more detailed understanding of the features and technical contents of the embodiments of the present application, the implementation of the embodiments of the present application is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present application.

[0031] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing this embodiment and are not intended to limit this application.

[0032] In the following description, references to “some embodiments,” “this embodiment,” “this embodiment,” and examples, etc., describe a subset of all possible embodiments, but it can be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.

[0033] If similar descriptions of "first / second" appear in the application documents, the following instructions are added. In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged in a specific order or sequence where permitted, so that the present embodiment described here can be implemented in an order other than that illustrated or described here.

[0034] In this embodiment, the term "and / or" is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, object A and / or object B may represent three situations: object A exists alone, object A and object B exist at the same time, and object B exists alone.

[0035] The present application provides a device wake-up method. Figure 1 The process diagram of the device wake-up method in the embodiment of the present application is as follows Figure 1 , applied to electronic devices, which may be smart phones, tablet computers, wearable devices, etc. Figure 1 As shown, the device wake-up method includes the following steps:

[0036] Step S101: when a pre-wake-up action is detected, first audio data received by a first audio receiver and second audio data received by a second audio receiver are obtained.

[0037] In an embodiment of the present application, the electronic device includes a first audio receiver and a second audio receiver, and the first audio receiver and the second audio receiver are installed at different positions of the electronic device. Exemplarily, the first audio receiver is installed below the electronic device, and the second audio receiver is installed above the electronic device, so that the receiving distance of the first audio receiver is less than the receiving distance of the second audio receiver. Alternatively, the first audio receiver is installed above the electronic device, and the second audio receiver is installed below the electronic device, so that the receiving distance of the first audio receiver is greater than the receiving distance of the second audio receiver.

[0038] In an embodiment of the present application, when an electronic device detects a pre-wake-up action, it indicates that the electronic device may need to be woken up. To further determine whether the electronic device needs to be woken up, the first audio data received by the first audio receiver and the second audio data received by the second audio receiver are obtained, and then based on the first audio data and the second audio data, it is determined whether the electronic device needs to be woken up.

[0039] Step S102: if no plosive sound is detected based on the first audio data and / or the second audio data, determine the distance between the user and the electronic device based on the difference between the first audio data and the second audio data.

[0040] It should be noted that both the first audio receiver and the second audio receiver are installed in the electronic device, but the installation positions are different. Therefore, it can be determined whether the plosive sound is detected based on the first audio data and / or the second audio data. Specifically, feature extraction is performed on the first audio data to obtain a first feature extraction result. If the first feature extraction result does not include the plosive sound feature, it means that the plosive sound is not detected. Alternatively, feature extraction is performed on the second audio data to obtain a second feature extraction result. If the second feature extraction result does not include the plosive sound feature, it means that the plosive sound is not detected. Alternatively, feature extraction is performed on the first audio data to obtain a first feature extraction result, and feature extraction is performed on the second audio data to obtain a second feature extraction result. If the first feature extraction result does not include the plosive sound feature, and the second feature extraction result does not include the plosive sound feature, it means that the plosive sound is not detected.

[0041] In the embodiment of the present application, the first audio data and the second audio data are quite different. Therefore, the distance between the user and the electronic device can be obtained by analyzing the difference.

[0042] Based on this, when no plosive sound is detected, the distance between the user currently using the electronic device and the electronic device is determined based on the audio difference between the first audio data and the second audio data. Here, the user currently using the electronic device can be the user of the electronic device or a non-user of the electronic device.

[0043] Step S103: Determine whether to wake up the electronic device based on the distance between the user and the electronic device.

[0044] In some embodiments, determining whether to wake up the electronic device is based on the distance between the user and the electronic device, including: determining to wake up the electronic device when the distance between the user and the electronic device is less than or equal to a distance threshold; determining not to wake up the electronic device when the distance between the user and the electronic device is greater than the distance threshold.

[0045] In the embodiment of the present application, when the distance between the user and the electronic device is less than or equal to the distance threshold, it means that the user is very close to the electronic device, and it is determined that the user wants to wake up the electronic device, that is, the electronic device enters the working state from the sleep state. When the distance between the user and the electronic device is greater than the distance threshold, it means that the user is far away from the electronic device, and there is no need to wake up the electronic device at this time, that is, the electronic device remains in the sleep state. Among them, the distance threshold refers to the critical value for waking up the electronic device, which can be set according to the developer's experiments or experience.

[0046] In an embodiment of the present application, when no plosive sound is detected, the present application uses the difference between the first audio data and the second audio data to determine the distance between the user and the electronic device, so as to determine whether the electronic device is within the preset distance range of the user, and decide whether the electronic device needs to be woken up accordingly, thereby achieving accurate wake-up of the electronic device.

[0047] In some embodiments of the present application, determining the distance between the user and the electronic device based on the difference between the first audio data and the second audio data includes the following steps S201 to S203:

[0048] Step S201: performing differential processing based on the first audio data and the second audio data to obtain differential data.

[0049] In the embodiment of the present application, differential processing refers to determining the difference between two audio data. Here, one way is to directly calculate the difference between the first audio data and the second audio data. Another way is to first process the first audio data and the second audio data separately, and then calculate the difference between the two audio data after processing. It should be noted that before differential processing is performed on the two audio data, it is necessary to ensure that the sampling points of the two audio data are aligned, which means that the two audio data need to have the same sampling rate and time length, or the two audio data need to be preprocessed to match these parameters.

[0050] Step S202: extract features from the differential data to obtain corresponding feature vectors.

[0051] In the embodiment of the present application, feature extraction technology is used to extract features from differential data to obtain a feature vector representing the differential data. Exemplarily, the feature extraction technology includes but is not limited to Mel-Frequency Cepstral Coefficients (MFCC), Linear Predictive Cepstral Coefficients (LPCC), Root Mean Square (RMS) and spectrum center.

[0052] Step S203: using the feature vector as input of a sound source distance measurement model to obtain the distance between the user and the electronic device.

[0053] In the embodiment of the present application, the sound source distance measurement model is used to measure the distance between the sound source and the electronic device. Therefore, by using the feature vector as the input of the sound source distance measurement model, the distance between the user using the electronic device and the electronic device can be obtained.

[0054] In the embodiment of the present application, the difference between the first audio data and the second audio data can be highlighted through differential processing, and the difference is closely related to the change in the position of the sound source. The feature extraction process can extract key information related to the distance of the sound source from the differential data, such as the intensity and frequency distribution of the audio. Based on this, the sound source distance determination model uses this key information to more accurately estimate the distance between the user and the electronic device.

[0055] In some embodiments of the present application, performing differential processing based on the first audio data and the second audio data to obtain differential data includes the following steps S301:

[0056] Step S301: When it is detected that the current environment is a quiet environment, differential processing is performed on the first audio data and the second audio data to obtain differential data.

[0057] It should be noted that if the first audio receiver is installed below the electronic device and the second audio receiver is installed above the electronic device, then the first audio receiver is referred to as a short-range audio receiver and the second audio receiver is referred to as a long-range audio receiver. In a relatively quiet environment, the waveform of the first audio data received by the short-range audio receiver is quite different from the waveform of the second audio data received by the long-range audio receiver. Therefore, the distance between the user and the electronic device can be finally obtained by analyzing this difference.

[0058] In an embodiment of the present application, when it is detected that the current environment is a quiet environment, there is no difficulty in locating the sound source. Therefore, the first audio data and the second audio data are directly differentially processed. In this way, based on the obtained differential data, the distance between the user and the electronic device can be accurately and efficiently determined.

[0059] In some embodiments of the present application, performing differential processing based on the first audio data and the second audio data to obtain differential data includes the following steps S401 to S402:

[0060] Step S401: when it is detected that the current environment is a noisy environment, voiceprint feature extraction is performed on the first audio data and / or the second audio data to obtain at least one voiceprint feature.

[0061] In the embodiment of the present application, when it is detected that the current environment is noisy, it is difficult to locate the sound source. Therefore, it is necessary to first identify whether the received audio data includes pre-recorded (i.e., already recorded) voiceprint audio. If the pre-recorded voiceprint audio is not identified, the subsequent distance measurement is not performed to avoid interference from environmental human voices. If the pre-recorded voiceprint audio is identified, the corresponding voiceprint audio in the received audio data is used to perform subsequent distance measurement between the human voice and the electronic device.

[0062] In an embodiment of the present application, whether the received audio data includes pre-recorded (i.e., already recorded) voiceprint audio is identified by first performing voiceprint feature extraction on the first audio data and / or the second audio data to obtain at least one voiceprint feature, which is then compared with the pre-recorded voiceprint feature. If at least one voiceprint feature includes a voiceprint feature of an already recorded user, then based on the difference between the audio data of the already recorded user in the first audio data and the audio data of the already recorded user in the second audio data, the distance between the already recorded user and the electronic device is determined.

[0063] Step S402: When at least one voiceprint feature includes a voiceprint feature of a recorded user, differential processing is performed on the audio data of the recorded user in the first audio data and the audio data of the recorded user in the second audio data to obtain differential data.

[0064] In an embodiment of the present application, based on the voiceprint features of the recorded user, the audio data of the recorded user is segmented from the first audio data, and the audio data of the recorded user is segmented from the second audio data, so that interference from other sounds can be avoided, and then the audio data of the recorded user in the first audio data and the audio data of the recorded user in the second audio data are differentially processed, so that based on the obtained differential data, the distance between the user and the electronic device can be accurately and efficiently determined.

[0065] In some embodiments of the present application, the method further includes: detecting whether the current environment is a quiet environment based on the first audio data and / or the second audio data.

[0066] In an embodiment of the present application, feature extraction is performed on the first audio data and / or the second audio data, and the extracted features are input into a trained classification model to obtain a classification result of whether the current environment is quiet or noisy. Alternatively, the first audio data and / or the second audio data are processed to obtain a corresponding decibel value; a decibel threshold is set, and if the decibel value is less than or equal to the decibel threshold, the current environment is considered to be a quiet environment; if the decibel value is greater than the decibel threshold, the current environment is considered to be a noisy environment. The decibel threshold can be set to 30dB. Other possible implementation methods are all possible and are not specifically limited.

[0067] In some embodiments of the present application, performing differential processing on the audio data of the user recorded in the first audio data and the audio data of the user recorded in the second audio data to obtain the differential data includes the following steps S501 to S503:

[0068] Step S501: performing noise reduction processing on the audio data of the user recorded in the first audio data to obtain first noise reduction data.

[0069] Step S502: performing noise reduction processing on the audio data of the user recorded in the second audio data to obtain second noise reduction data.

[0070] Step S503: performing differential processing on the first denoised data and the second denoised data to obtain differential data.

[0071] In an embodiment of the present application, a noise reduction algorithm is used to perform noise reduction processing on the ambient noise in the audio data of the user recorded in the first audio data and the audio data of the user recorded in the second audio data, and only the audio with human voice frequency is retained. Then, the first noise reduction data and the second noise reduction data after the noise reduction processing are differentially processed. In this way, based on the obtained differential data, the accuracy of determining the distance between the recorded user and the electronic device can be improved.

[0072] In some embodiments of the present application, the method further includes the following steps S601:

[0073] Step S601: When a plosive sound is detected based on the first audio data and / or the second audio data, the electronic device is woken up.

[0074] In an embodiment of the present application, when a plosive sound is detected based on the first audio data and / or the second audio data, it means that the user who makes the plosive sound is extremely close to the electronic device, and the user wants to wake up the electronic device. Therefore, the electronic device is woken up (for example, it can be a voice assistant that wakes up the electronic device), so that the electronic device enters the working state from the sleep state.

[0075] In some embodiments of the present application, the method also includes: obtaining a first angle between the screen of the electronic device and a vertical direction, and a second angle between the screen of the electronic device and a horizontal direction; when the first angle is greater than or equal to a first angle threshold and the second angle is less than or equal to a second angle threshold, a pre-wake-up action is detected.

[0076] In an embodiment of the present application, the electronic device has a built-in inertial measurement unit (IMU), and the IMU is used to measure a first angle between the plane of the electronic device and the vertical direction, and a second angle between the plane of the electronic device and the horizontal direction. When the first angle is greater than or equal to the first angle threshold, it indicates that the user may have lifted the electronic device. When the second angle is less than or equal to the second angle threshold, it indicates that the electronic device is in a relatively horizontal holding state, which further indicates that the user may want to use the electronic device, that is, the user has a pre-wake-up action. Here, the first angle threshold and the second angle threshold are set by the developer based on experiments or experience.

[0077] like Figure 7 As shown in (a), (b), and (c), in daily use, users may use the device at different distances, such as on a desk, in front of the chest, near the mouth, etc. There may also be situations where the device is at a longer distance from the user, such as more than half a meter, one meter, or two meters.

[0078] Based on this, the present application provides a method for identifying two types of human voice audio, breathing sounds and speaking voices, to determine whether to wake up an electronic device. It can be mainly used in the field of wake-up without a wake-up word and distance measurement and direction measurement of audio in the human voice frequency band.

[0079] Furthermore, the present application embodiment specifically provides a process of a device wake-up method, Figure 8 The process diagram of the device wake-up method in the embodiment of the present application is as follows Figure 7 ,like Figure 8 As shown, the device wake-up method includes the following steps:

[0080] start.

[0081] Step S801: Detect whether there is a pre-wake-up action.

[0082] If yes, execute step S802; if no, execute step S801.

[0083] Step S802: Ultra-close range respiratory plosive sound detection.

[0084] Step S803: Whether respiratory plosives are detected.

[0085] If yes, go to step S804; if no, go to step S805.

[0086] Step S804: Wake up the electronic device.

[0087] Step S805: calling the sound source distance measurement model.

[0088] Step S806: Output the distance between the user and the electronic device.

[0089] Step S807: Determine whether to wake up the electronic device based on the distance between the user and the electronic device.

[0090] Finish.

[0091] Step S807: Specifically, when the distance between the user and the electronic device is less than or equal to the distance threshold, it means that the user is very close to the electronic device, and it is determined that the user wants to wake up the electronic device, that is, the electronic device enters the working state from the sleep state. When the distance between the user and the electronic device is greater than the distance threshold, it means that the user is far away from the electronic device, and there is no need to wake up the electronic device at this time, that is, the electronic device remains in the sleep state. Among them, the distance threshold refers to the critical value for waking up the electronic device, which can be set according to the developer's experiments or experience.

[0092] Regarding step S801, detecting whether there is a pre-wake-up action may include the following steps:

[0093] start.

[0094] Step S901: Detecting a first angle between a screen and a vertical direction by using an inertial measurement unit built into the electronic device.

[0095] Step S902: whether it is greater than or equal to a first angle threshold.

[0096] If yes, execute step S901; if no, execute step S903.

[0097] Step S903: There is a lifting action.

[0098] Step S904: Detecting a second angle between the screen and the horizontal direction by using an inertial measurement unit.

[0099] Step S905: whether it is less than or equal to the second angle threshold.

[0100] If yes, execute step S904; if no, execute step S906.

[0101] Step S906: There is a pre-wake-up action.

[0102] Finish.

[0103] In other words, detect whether the electronic device has vertical acceleration and deceleration changes on the z-axis of the inertial measurement unit to determine the vertical movement distance. If there is a significant movement distance, it means that the user may have lifted the electronic device. Further, detect whether the inertial measurement unit of the electronic device maintains a relatively stable angle change in the horizontal direction. If there is no obvious horizontal (x-axis, y-axis) angle change, it means that the electronic device is in a relatively horizontal holding state. This process can be used to determine whether there is a pre-wake-up action.

[0104] Regarding step S802, ultra-close range respiratory blast detection, the details are as follows:

[0105] Pop noise detection is an important waveform marker for ultra-close distance detection. By detecting pop noise, it can be effectively detected that the distance between the device and the user is at the mouth.

[0106] like Fig.10 As shown, from the waveform, it can be clearly found that the amplitude of the plosive sound at a close distance to the mouth, i.e. 2 cm, is much higher than the amplitude of the plosive sound at other distances (i.e. 5 cm, 10 cm, 20 cm, 30 cm, 50 cm).

[0107] The present application uses signal processing features including but not limited to Short Time Fourier Transform (STFT), MFCC, amplitude, wavelet, etc., and identifies the plosive sound features through a sliding window by framing and windowing the received first audio data and / or second audio data.

[0108] Regarding step S805, the sound source distance determination model is called, as follows:

[0109] When the plosive sound cannot be detected, the distance can still be measured by the human voice with audible frequency. At the same time, the non-directional distance positioning method used in this application can avoid the amplitude and energy influence caused by the volume, and the volume of the sound emitted by the user does not affect the distance measurement.

[0110] This application uses a dual-channel method in which two upper and lower audio receivers simultaneously receive human voice audio, combined with feature engineering, to detect the distance between the user's sound source and the device.

[0111] like Fig.11 As shown in (a) and (b), in a relatively quiet environment, the short-range audio receiver (i.e. Fig.11 (b)) The waveform under dual channel and the long-distance audio receiver (i.e. Fig.11 (a)) The waveforms under dual channels are very different, so the distance between the sound source and the electronic device can be obtained by analyzing this difference.

[0112] Specifically, by performing differential calculations on the upper and lower channel waveforms, the differential data is obtained, and then feature extraction technology (including but not limited to MFCC, LPCC, RMS, and spectrum center) is used to perform feature engineering on the differential data to solve the feature vector. Use a machine learning model or a deep learning model to perform multi-distance classification modeling on the feature vector and establish a sound source distance measurement model. After the human voice audio is actually collected, the distance between the sound source and the electronic device is identified through the sound source distance measurement model.

[0113] In a relatively noisy environment, it is difficult to locate the sound source, so the human voice audio needs to be further processed. Specifically, the user first records a personal voiceprint audio and uses the voiceprint recognition model to build a model. In actual recognition, first identify whether it is a recorded user voiceprint. If the audio does not contain a slice of the recorded user voiceprint audio, no subsequent distance measurement is performed to avoid interference from environmental human voices. If a slice of the recorded user voiceprint audio is identified in the audio, the slice is used for subsequent human voice sound measurement. The environmental noise is reduced by the noise reduction algorithm, and only the audio with the human voice frequency is retained, and the above-mentioned distance measurement can be performed on the audio.

[0114] In order to implement the method of the embodiment of the present application, based on the same inventive concept, the embodiment of the present application also provides a device waking up the device, Fig.12 FIG. 1 is a schematic diagram of the structure of the device wake-up device in the embodiment of the present application. Fig.12 As shown, the device waking up device 120 includes:

[0115] An acquiring unit 1201 is configured to acquire, when a pre-wake-up action is detected, first audio data received by the first audio receiver and second audio data received by the second audio receiver;

[0116] The processing unit 1202 is configured to determine the distance between the user and the electronic device based on the difference between the first audio data and the second audio data when no plosive sound is detected based on the first audio data and / or the second audio data;

[0117] The processing unit 1202 is further configured to determine whether to wake up the electronic device based on the distance between the user and the electronic device.

[0118] In an embodiment of the present application, when no plosive sound is detected, the present application uses the difference between the first audio data and the second audio data to determine the distance between the user and the electronic device, so as to determine whether the electronic device is within the preset distance range of the user, and decide whether the electronic device needs to be woken up accordingly, thereby achieving accurate wake-up of the electronic device.

[0119] In some embodiments of the present application, the processing unit 1202 is further used to perform differential processing based on the first audio data and the second audio data to obtain differential data; perform feature extraction on the differential data to obtain a corresponding feature vector; and use the feature vector as an input of a sound source distance measurement model to obtain the distance between the user and the electronic device.

[0120] In some embodiments of the present application, the processing unit 1202 is further configured to perform differential processing on the first audio data and the second audio data to obtain the differential data when it is detected that the current environment is a quiet environment.

[0121] In some embodiments of the present application, the processing unit 1202 is further configured to extract voiceprint features from the first audio data and / or the second audio data to obtain at least one voiceprint feature when detecting that the current environment is a noisy environment;

[0122] In a case where the at least one voiceprint feature includes a voiceprint feature of a recorded user, differential processing is performed on the audio data of the recorded user in the first audio data and the audio data of the recorded user in the second audio data to obtain the differential data.

[0123] In some embodiments of the present application, the processing unit 1202 is further used to perform noise reduction processing on the audio data recorded by the user in the first audio data to obtain first noise reduction data; perform noise reduction processing on the audio data recorded by the user in the second audio data to obtain second noise reduction data; and perform differential processing on the first noise reduction data and the second noise reduction data to obtain the differential data.

[0124] In some embodiments of the present application, the processing unit 1202 is further configured to wake up the electronic device when the plosive sound is detected based on the first audio data and / or the second audio data.

[0125] In some embodiments of the present application, the acquisition unit 1201 is also used to acquire a first angle between the screen of the electronic device and the vertical direction, and a second angle between the screen of the electronic device and the horizontal direction; when the first angle is greater than or equal to a first angle threshold and the second angle is less than or equal to a second angle threshold, a pre-wake-up action is detected.

[0126] The present application also provides another electronic device, Fig.13 Schematic diagram of the structure of the electronic device in the embodiment of the present application. Fig.13 As shown, the electronic device 130 includes: a processor 1301 and a memory 1302 configured to store a computer program that can be run on the processor;

[0127] The processor 1301 is configured to execute the method steps in the aforementioned embodiment when running a computer program.

[0128] Of course, in practical applications, Fig.13As shown, the various components in the electronic device 130 are coupled together via a bus system 1303. It is understood that the bus system 1303 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 1303 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, Fig.13 Various buses are labeled as bus system 1303.

[0129] In practical applications, the processor may be at least one of an application-specific integrated circuit (ASIC), a digital signal processing device (DSPD), a programmable logic device (PLD), a field-programmable gate array (FPGA), a controller, a microcontroller, and a microprocessor. It is understandable that for different devices, the electronic device used to implement the functions of the processor may also be other, and the embodiments of the present application do not specifically limit this.

[0130] The above-mentioned memory can be a volatile memory (volatile memory), such as a random access memory (RAM); or a non-volatile memory (non-volatile memory), such as a read-only memory (ROM), a flash memory, a hard disk (HDD) or a solid-state drive (SSD); or a combination of the above-mentioned types of memory, and provide instructions and data to the processor.

[0131] In an exemplary embodiment, the present application also provides a computer-readable storage medium for storing a computer program.

[0132] Optionally, the computer-readable storage medium can be applied to any one of the methods in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the processor in each method in the embodiments of the present application. For the sake of brevity, they are not repeated here.

[0133] Illustratively, an embodiment of the present application further provides a computer program product, including a computer program, which can be executed by a processor of an electronic device to complete the steps of any of the aforementioned methods.

[0134] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0135] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0136] In addition, all functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may be a separate unit, or two or more units may be integrated into one unit; the above integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units. A person of ordinary skill in the art may understand that all or part of the steps of implementing the above method embodiments may be completed by hardware related to program instructions, and the above program may be stored in a computer-readable storage medium, which, when executed, executes the steps of the above method embodiments; and the above storage medium includes various media that can store program codes, such as mobile storage devices, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0137] The methods disclosed in several method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0138] The features disclosed in several product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0139] The features disclosed in several method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0140] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A device wake-up method, characterized in that: The method comprises: When a pre-wake-up action is detected, obtaining first audio data received by the first audio receiver and second audio data received by the second audio receiver; In a case where no plosive sound is detected in the first audio data and / or the second audio data, determining a distance between the user and the electronic device based on a difference between the first audio data and the second audio data; Based on the distance between the user and the electronic device, it is determined whether to wake up the electronic device.

2. The method according to claim 1, characterized in that The determining the distance between the user and the electronic device based on the difference between the first audio data and the second audio data includes: Performing differential processing based on the first audio data and the second audio data to obtain differential data; Performing feature extraction on the differential data to obtain a corresponding feature vector; The feature vector is used as an input of a sound source distance measurement model to obtain the distance between the user and the electronic device.

3. The method according to claim 2, characterized in that The performing differential processing based on the first audio data and the second audio data to obtain differential data includes: When it is detected that the current environment is a quiet environment, the first audio data and the second audio data are differentially processed to obtain the differential data.

4. The method according to claim 2, characterized in that: The performing differential processing based on the first audio data and the second audio data to obtain differential data includes: When it is detected that the current environment is a noisy environment, extracting voiceprint features from the first audio data and / or the second audio data to obtain at least one voiceprint feature; In a case where the at least one voiceprint feature includes a voiceprint feature of a recorded user, differential processing is performed on the audio data of the recorded user in the first audio data and the audio data of the recorded user in the second audio data to obtain the differential data.

5. The method according to claim 4, characterized in that The performing differential processing on the audio data of the user recorded in the first audio data and the audio data of the user recorded in the second audio data to obtain the differential data includes: Performing noise reduction processing on the audio data recorded by the user in the first audio data to obtain first noise reduction data; Performing noise reduction processing on the audio data recorded by the user in the second audio data to obtain second noise reduction data; The first denoised data and the second denoised data are differentially processed to obtain the differential data.

6. The method according to claim 1 or 2, characterized in that: The method further comprises: When the plosive sound is detected based on the first audio data and / or the second audio data, the electronic device is woken up.

7. The method according to claim 1 or 2, characterized in that: The method further comprises: Acquire a first angle between the screen of the electronic device and a vertical direction, and a second angle between the screen of the electronic device and a horizontal direction; When the first angle is greater than or equal to a first angle threshold and the second angle is less than or equal to a second angle threshold, a pre-wake-up action is detected.

8. A device waking up a device, characterized in that: The device comprises: An acquiring unit, configured to acquire, when a pre-wake-up action is detected, first audio data received by the first audio receiver and second audio data received by the second audio receiver; a processing unit, configured to determine a distance between the user and the electronic device based on a difference between the first audio data and the second audio data, if no plosive sound is detected based on the first audio data and / or the second audio data; The processing unit is further used to determine whether to wake up the electronic device based on the distance between the user and the electronic device.

9. An electronic device, characterized in that: The electronic device comprises: a processor and a memory configured to store a computer program capable of running on the processor, Wherein, the processor is configured to execute the steps of the method according to any one of claims 1 to 7 when running the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images