A voice wake-up method, terminal and storage medium

Through the combination of microphone array and wake-up engine, the arrival angle and angle-time variation envelope of multiple audio are used to recognize wake-up words, which solves the recognition rate and false recognition rate problems under the influence of echo interference, and improves the accuracy of voice wake-up and efficiency.

CN114694638BActive Publication Date: 2024-11-26SHENZHEN WEIAI INTELLIGENT CO LTD
View PDF 9 Cites 0 Cited by

Patent Information

Application Number
CN202210410539.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-04-19
Publication Date
2024-11-26
Estimated Expiration
2042-04-19

AI Technical Summary

Technical Problem

When existing voice wake-up technologies face echo interference, it is difficult to improve the recognition rate and false recognition rate simultaneously. Especially in smart devices, the echo suppression ability is limited, resulting in a decrease in wake-up rate and an increase in false awake rate.

Method used

The audio source is collected in real time through the microphone array, and the arrival angle and angle-time variation envelope of the multiple audio are calculated. Combined with the echo cancellation, the wake-up words are identified to improve the recognition rate of the wake-up engine.

Benefits of technology

It significantly improves the recognition rate of the voice wake-up engine, reduces the false wake-up rate, effectively eliminates echo interference, and enhances the recognition accuracy of wake-up words.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114694638B_ABST
    Figure CN114694638B_ABST
Patent Text Reader

Abstract

The present application provides a voice wake-up method, which is applied to a terminal, and the terminal is provided with a microphone array and a wake-up engine, including: collecting audio sound sources in real time through the microphone array, performing echo cancellation on the audio sound sources, and determining the multi-channel audio after cancellation; calculating the arrival angle of the multi-channel audio; identifying the arrival angle angle-time variation envelope appearing in the arrival angle information of the multi-channel audio; the wake-up engine recognizes a wake-up word; and the wake-up engine wakes up the terminal. The present application also provides a terminal, including a memory and a processor, the memory is used to store at least one program instruction, and the processor is used to implement the voice wake-up method as described above by loading and executing the at least one program instruction. The present invention also provides a storage medium, on which program instructions are stored; when the program instructions are executed by the processor, the voice wake-up method as described above is implemented.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of voice wake-up technology, and in particular to a voice wake-up method, a terminal and a storage medium. Background Art

[0002] Wake-up words are widely used in smart devices for voice recognition. The factors that affect the performance of the wake-up word recognition engine are mainly the recognition rate and the false recognition rate. The two are interrelated. To achieve a higher recognition rate, the false recognition rate will also increase accordingly. The desired effect is a high recognition rate and a low false recognition rate.

[0003] When a smart device is playing music, news or other on-demand content, it is interrupted and woken up. At this time, there is a large echo interference, which seriously affects the recognition of the wake-up word. Currently, acoustic echo cancellation (AEC) is generally used to eliminate the interference of the echo. The performance of AEC greatly affects the effect of interruption and wake-up.

[0004] The suppression capability of AEC is limited. Even in a well-designed acoustic system, the adaptive linear filtering technology plus residual echo post-processing technology widely used in AEC can generally only provide 20-40dB suppression of acoustic echo. However, smart devices often use high-power speakers to achieve satisfactory loudness, and due to size limitations, the speakers are also very close to the microphone, and at the same time, far-field wake-up is often required. This results in a very small signal-to-echo ratio in the system, and the echo energy is much greater than the signal energy.

[0005] In actual equipment, due to cost and size constraints, the echo path often has serious nonlinearity, usually caused by low-cost speakers, poor microphone performance, device structure resonance, etc. Currently, AEC mainly eliminates linear echo, but is not ideal for eliminating nonlinear echo, which will have a large residual nonlinear echo.

[0006] Therefore, in the above situation, AEC sometimes cannot eliminate the echo well, resulting in strong residual echo after AEC. These residual echoes will cause the wake-up rate of the voice wake-up engine to decrease and the false wake-up rate to increase.

[0007] The preceding description is intended to provide general background information and does not necessarily constitute prior art. Summary of the invention

[0008] The purpose of the present application is to provide a voice wake-up method, terminal and storage medium for improving recognition rate.

[0009] The present invention provides a voice wake-up method, which is applied to a terminal, wherein the terminal is provided with a microphone array and a wake-up engine, comprising:

[0010] The microphone array is used to collect audio sources in real time, and echo cancellation is performed on the audio sources to determine the multi-channel audio after cancellation;

[0011] Calculating the arrival angles of the multi-channel audio;

[0012] Identifying the presence of an arrival angle angle-time variation envelope in the arrival angle information of the multi-channel audio;

[0013] The wake-up engine recognizes a wake-up word;

[0014] The wake-up engine wakes up the terminal.

[0015] Further, the wake-up engine wakes up the terminal, including:

[0016] When the arrival angle information of the multi-channel audio is identified to contain an arrival angle angle-time variation envelope, the wake-up engine identifies the wake-up word in the multi-channel audio received within the time interval, and the wake-up engine wakes up the terminal after identifying the wake-up word.

[0017] Further, the wake-up engine wakes up the terminal, including:

[0018] When the wake-up engine recognizes the wake-up word and confirms that an arrival angle angle-time variation envelope appears in the arrival angle information of the multi-channel audio, the wake-up engine wakes up the terminal.

[0019] Furthermore, it also includes:

[0020] The arrival angle confidence differences of the multi-channel audios before and after echo cancellation are compared.

[0021] Further, the wake-up engine wakes up the terminal, including:

[0022] After the wake-up engine recognizes the wake-up word, it compares the arrival angle confidence difference of the multi-channel audio before and after echo cancellation. When the arrival angle confidence difference envelope appears, it confirms that the arrival angle angle-time change envelope appears in the arrival angle information of the multi-channel audio and then wakes up the terminal.

[0023] Furthermore, it also includes:

[0024] After calculating the arrival angles of the multi-channel audio, smoothing is performed on the arrival angles of the multi-channel audio.

[0025] Furthermore, the angle-time variation envelope of the arrival angle is: in the arrival angle sequence, after detecting that the angle change of the arrival angle exceeds the first preset value and lasts for the first preset time, the arrival angle returns to the first preset value, and the time period of this angle change-maintenance-return is extracted, which is called the angle-time variation envelope of the arrival angle.

[0026] Furthermore, the arrival angle confidence difference envelope is: in the arrival angle confidence sequence, after detecting that the change of the arrival angle confidence exceeds the second preset value and lasts for the second preset time, the arrival angle confidence returns to the second preset value, and the time period of this confidence change-maintenance-return is extracted, which is called the arrival angle confidence difference envelope.

[0027] The present invention also provides a terminal, comprising a memory and a processor, wherein the memory is used to store at least one program instruction, and the processor is used to implement the voice wake-up method as described above by loading and executing the at least one program instruction.

[0028] The present invention also provides a storage medium, on which program instructions are stored; when the program instructions are executed by a processor, the voice wake-up method as described above is implemented.

[0029] The voice wake-up method provided by the present invention improves the recognition rate of the wake-up engine by identifying the arrival angle angle-time variation envelope. Since the angle of the echo is determined by the position of the speaker relative to the microphone and the acoustic characteristics of the room, it is often relatively fixed or changes slowly over time and is relatively stable. The angle of the wake-up word is inconsistent with the angle of the echo most of the time and appears and disappears with the wake-up word. When the wake-up word appears, the voice arrival angle can see a relatively obvious short-term arrival angle angle-time variation envelope, which transitions from the angle of the echo to the angle of the wake-up word, lasts for a short time, and then returns to the residual echo angle. When the echo and voice angles are similar or the same, the arrival angle of the wake-up word is similar to the arrival angle of the echo. By comparing the difference in the arrival angle confidence before and after echo elimination, the echo and voice are distinguished. The echo component is reduced after the echo is eliminated, and the corresponding arrival angle confidence before and after the echo elimination will be significantly reduced, while the voice component of the wake-up word will not be eliminated, and the confidence will not change significantly.

[0030] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the following specifically cites the preferred embodiments and describes them in detail with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application. In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor.

[0032] Figure 1is a flow chart of a voice wake-up method provided by the first embodiment of the present invention;

[0033] Figure 2 is a flow chart of a voice wake-up method provided by the second embodiment of the present invention;

[0034] Figure 3 This is a flow chart of a voice wake-up method provided in the third embodiment of the present invention. DETAILED DESCRIPTION

[0035] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0036] It should be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context of the specific embodiment.

[0037] It should be understood that, although the terms first, second, third, etc. may be used to describe various information in this article, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this article, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination". Furthermore, as used in this article, the singular forms "one", "one" and "the" are intended to also include plural forms, unless there is an opposite indication in the context. It should be further understood that the terms "comprising", "including" indicate the existence of features, steps, operations, elements, components, projects, kinds, and / or groups, but do not exclude the existence, occurrence or addition of one or more other features, steps, operations, elements, components, projects, kinds, and / or groups. The terms "or" and "and / or" used herein are interpreted as inclusive, or mean any one or any combination. Thus, “A, B, or C” or “A, B and / or C” means “any of the following: A; B; C; A and B; A and C; B and C; A, B, and C.” An exception to this definition will occur only when a combination of elements, functions, steps, or operations are inherently mutually exclusive in some manner.

[0038] It should be understood that, although the various steps in the flowchart in the embodiment of the present application are displayed in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and it can be performed in other orders. Moreover, at least a portion of the steps in the figure may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and their execution order is not necessarily performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0039] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0040] In the subsequent description, the suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present application, and have no specific meanings. Therefore, "module", "component" or "unit" can be used in a mixed manner.

[0041] The following description will be made by taking a terminal as an example, and those skilled in the art will understand that, in addition to components specifically used for mobile purposes, the construction according to the embodiments of the present application can also be applied to fixed-type terminals.

[0042] First embodiment

[0043] Please refer to Figure 1 A first embodiment of the present invention provides a voice wake-up method, which is applied to a terminal, and the terminal is provided with a microphone array and a wake-up engine.

[0044] The voice wake-up method comprises the following steps:

[0045] S11: collecting audio sound sources in real time through the microphone array, performing echo cancellation on the audio sound sources, and determining the multi-channel audio after cancellation;

[0046] S12: calculating the arrival angles of the multi-channel audios and performing smoothing processing on the arrival angles of the multi-channel audios;

[0047] S13: Identify whether an arrival angle angle-time variation envelope appears in the arrival angle information of the multi-channel audio;

[0048] S14: When an arrival angle-time variation envelope appears in the arrival angle information of the multi-channel audio, the wake-up engine recognizes a wake-up word in the multi-channel audio received within the time interval;

[0049] S15: The wake-up engine wakes up the terminal after recognizing the wake-up word.

[0050] For step S11, echo cancellation is performed on the audio source to determine the multi-channel audio after cancellation. For acoustic echo cancellation, there are two types of cancellation algorithms, including echo suppression and acoustic echo cancellation. The echo suppression algorithm is an earlier echo control algorithm. Echo suppression is a nonlinear echo cancellation. It compares the sound to be played by the speaker with the level of the sound currently picked up by the microphone through a simple comparator. If the former is higher than a certain threshold, it is allowed to be transmitted to the speaker, and the microphone is turned off to prevent it from picking up the sound played by the speaker and causing a far-end echo. If the sound level picked up by the microphone is higher than a certain threshold, the speaker is disabled to achieve the purpose of eliminating the echo. Since echo suppression is a nonlinear echo control method, it will cause discontinuity in speaker playback and affect the effect of echo cancellation. With the emergence of high-performance echo cancellers. The acoustic echo cancellation algorithm is based on the correlation between the speaker signal and the multipath echo generated by it, establishes a speech model of the far-end signal, uses it to estimate the echo, and continuously modifies the coefficients of the filter so that the estimated value is closer to the real echo. The echo estimate is then subtracted from the microphone input signal, thereby achieving the purpose of echo cancellation.

[0051] For step S12, calculating the arrival angle of multi-channel audio is to calculate the arrival angle of multi-channel audio frame by frame to obtain an arrival angle sequence. Since the angle of the echo is determined by the position of the speaker relative to the microphone and the acoustic characteristics of the room, it is often relatively fixed or changes slowly over time and is relatively stable, and the angle of the wake-up word is inconsistent with the angle of the echo most of the time and appears and disappears with the wake-up word. After the voice arrival angle is smoothed, when the wake-up word appears, the voice arrival angle can see a relatively obvious short-term arrival angle angle-time change envelope, which transitions from the angle of the echo to the angle of the wake-up word, and after a short period of time, returns to the residual echo angle. Among them, smoothing the arrival angle of multi-channel audio refers to a temporal averaging operation that can reduce the impact of outliers and can be implemented using an infinite impulse response filter.

[0052] For steps S13 and S14, an equation is established with the value of the arrival angle of each frame of multi-channel audio as the vertical coordinate and the time as the horizontal coordinate. In the absence of a wake-up word, the equation curve basically swings slightly at a specific angle, such as around 30 degrees. In the arrival angle sequence, after detecting that the angle change of the arrival angle exceeds the first preset value and lasts for the first preset time, the arrival angle returns to the first preset value, and the time period of this angle change-maintenance-return is extracted, which is called the arrival angle angle-time change envelope. In this embodiment, the first preset value can be set to 90 degrees, and the first preset time can be set to 1 second, and the time period of reaching 90 degrees for one second is called the arrival angle angle-time change envelope. Of course, in other embodiments, the preset value can also be set according to actual conditions.

[0053] For step S14, when the arrival angle angle-time variation envelope appears, it means that the microphone array has recognized the voice information. In this situation, the wake-up engine recognizes the wake-up word from the audio, avoiding the echo from waking up the terminal by mistake and significantly reducing the false wake-up rate.

[0054] This embodiment also provides a terminal, including a memory and a processor, the memory is used to store at least one program instruction, and the processor is used to load and execute the at least one program instruction to implement the voice wake-up method as described above. The terminal can be implemented in various forms. For example, the terminal described in this application may include smart terminals such as mobile phones, tablet computers, laptop computers, PDAs, portable media players (PMPs), navigation devices, wearable devices, smart bracelets, pedometers, and fixed terminals such as digital TVs and desktop computers.

[0055] This embodiment also provides a storage medium, on which program instructions are stored. When the program instructions are executed by a processor, the voice wake-up method as described above is implemented.

[0056] Second embodiment

[0057] Please refer to Figure 2 A second embodiment of the present invention provides a voice wake-up method, which is applied to a terminal, and the terminal is provided with a microphone array and a wake-up engine.

[0058] The voice wake-up method comprises the following steps:

[0059] S21: collecting audio sound sources in real time through a microphone array, performing echo cancellation on the audio sound sources, and determining multi-channel audio after cancellation;

[0060] S22: The wake-up engine recognizes the wake-up word in the multi-channel audio;

[0061] S23: When the wake-up engine recognizes the wake-up word, the arrival angles of the multi-channel audio are calculated and the arrival angles of the multi-channel audio are smoothed;

[0062] S24: When an arrival angle-time variation envelope is identified in the arrival angle information of the multi-channel audio, the wake-up engine wakes up the terminal.

[0063] For steps S22 to S24, the wake-up engine first identifies the wake-up word, and then identifies the arrival angle angle-time change envelope to determine whether it is a false wake-up, thereby improving the recognition rate of voice wake-up.

[0064] Third embodiment

[0065] Please refer to Figure 3 A third embodiment of the present invention provides a voice wake-up method, which is applied to a terminal, and the terminal is provided with a microphone array and a wake-up engine.

[0066] The voice wake-up method comprises the following steps:

[0067] S31: collecting audio sources in real time through a microphone array, performing echo cancellation on the audio sources, and determining multi-channel audio after cancellation;

[0068] S32: The wake-up engine recognizes the wake-up word in the multi-channel audio;

[0069] S33: when the wake-up word is recognized, the wake-up engine compares the difference in arrival angle confidence before and after the multi-channel audio word echo cancellation;

[0070] S341: When the arrival angle confidence difference envelope appears, the wake-up engine wakes up the terminal;

[0071] S342: When the arrival angle confidence difference envelope does not appear, the arrival angles of the multi-channel audio are calculated and the arrival angles of the multi-channel audio are smoothed. When it is identified that the fluctuation of the arrival angle angle-time change envelope in the arrival angle information of the multi-channel audio exceeds the preset value, the wake-up engine wakes up the terminal.

[0072] For steps S33 and S341, the difference in the arrival angle confidence before and after echo cancellation can be used to assist in distinguishing echo from speech. The echo component is reduced after echo cancellation, and accordingly, its arrival angle confidence will be significantly reduced before and after echo cancellation. The wake-up word speech component will not be eliminated, and the confidence will not change significantly. This feature can detect the wake-up word speech when the echo and speech angles are similar or the same.

[0073] The arrival angle confidence is calculated frame by frame. In the arrival angle confidence sequence, it is detected that the change of the arrival angle confidence exceeds the second preset value and lasts for the second preset time until the arrival angle confidence returns to the second preset value. The time period of this confidence change-maintenance-return is extracted and called the arrival angle confidence difference envelope. The critical value of the confidence difference can be set according to the actual scenario. For example, the second preset value is 0.3, and the second preset time is 1 second. That is, before and after the echo cancellation, the critical value is reduced by more than 0.3, that is, more than 30%, and it lasts for one second. Then the audio segment is most likely not a wake-up word.

[0074] For voice terminals that contain both wake-up words and echoes, the arrival angle confidence may increase after echo cancellation. Therefore, the arrival angle confidence change in the arrival angle confidence difference envelope in the above method refers to the situation where the arrival angle confidence decreases.

[0075] For steps S342, only when the wake-up word engine detects the wake-up word and the wake-up word confidence is lower than a certain threshold (i.e., the wake-up word is in doubt), is it further calculated whether there is a wake-up word angle-time envelope that matches the wake-up word? If not, it is judged as a false wake-up. In other embodiments, the confidence can also be replaced by other parameters, such as an acoustic score (indicating the acoustic fit between the detected wake-up word and the model).

[0076] It is understood that the above scenarios are only examples and do not constitute a limitation on the application scenarios of the technical solutions provided in the embodiments of the present application. The technical solutions of the present application can also be applied to other scenarios. For example, it is known to those skilled in the art that with the evolution of the system architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0077] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0078] The steps in the method of the embodiment of the present application can be adjusted in order, combined and deleted according to actual needs.

[0079] The units in the device of the embodiment of the present application can be merged, divided and deleted according to actual needs.

[0080] In the present application, the same or similar terminology concepts, technical solutions and / or application scenario descriptions are generally described in detail only the first time they appear. When they appear again later, they are generally not repeated for the sake of brevity. When understanding the technical solutions and other contents of the present application, for the same or similar terminology concepts, technical solutions and / or application scenario descriptions that are not described in detail later, reference can be made to the previous related detailed descriptions.

[0081] In the present application, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0082] The various technical features of the technical solution of the present application can be arbitrarily combined. In order to make the description concise, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of the present application.

[0083] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as above, and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, a controlled terminal, or a network device, etc.) to execute the method of each embodiment of the present application.

[0084] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loading and executing computer program instructions on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server, a data center, etc. that contains one or more available media integrated. The available medium can be a magnetic medium, (e.g., a floppy disk, a storage disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state storage disk Solid State Disk (SSD)), etc.

[0085] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A voice wake-up method, applied to a terminal, wherein the terminal is provided with a microphone array and a wake-up engine, characterized in that: include: The microphone array is used to collect audio sources in real time, and echo cancellation is performed on the audio sources to determine the multi-channel audio after cancellation; Calculating the arrival angles of the multi-channel audio; Identifying the presence of an arrival angle angle-time variation envelope in the arrival angle information of the multi-channel audio; In the arrival angle sequence, after detecting that the angle change of the arrival angle exceeds the first preset value and lasts for the first preset time, the arrival angle returns to the first preset value, and the time period of this angle change-maintenance-return is extracted, which is called the arrival angle angle-time change envelope; The wake-up engine recognizes a wake-up word; The wake-up engine wakes up the terminal.

2. The voice wake-up method according to claim 1, characterized in that: The wake-up engine wakes up the terminal, including: When the arrival angle information of the multi-channel audio is identified to contain an arrival angle angle-time variation envelope, the wake-up engine identifies the wake-up word in the multi-channel audio received within the time interval, and the wake-up engine wakes up the terminal after identifying the wake-up word.

3. A voice wake-up method, applied to a terminal, wherein the terminal is provided with a microphone array and a wake-up engine, characterized in that: include: The microphone array is used to collect audio sources in real time, and echo cancellation is performed on the audio sources to determine the multi-channel audio after cancellation; The wake-up engine recognizes the wake-up word in the multi-channel audio; Calculating the arrival angles of the multi-channel audio; When the arrival angle information of the multi-channel audio is identified to contain an arrival angle angle-time variation envelope, the wake-up engine wakes up the terminal; wherein, in the arrival angle sequence, after detecting that the angle change of the arrival angle exceeds a first preset value and lasts for a first preset time, the arrival angle returns to the first preset value, and the time period of this angle change-maintenance-return is extracted, which is called the arrival angle angle-time variation envelope.

4. The voice wake-up method according to claim 1, characterized in that: Also includes: After calculating the arrival angles of the multi-channel audio, smoothing is performed on the arrival angles of the multi-channel audio.

5. A terminal, characterized in that: It comprises a memory and a processor, wherein the memory is used to store at least one program instruction, and the processor is used to implement the voice wake-up method as claimed in claim 1 by loading and executing the at least one program instruction.

6. A storage medium, characterized in that: The storage medium stores program instructions; when the program instructions are executed by the processor, the voice wake-up method as claimed in claim 1 is implemented.

Citation Information

Patent Citations

  • Voice wake-up method and system for intelligent equipment

    CN109461449A

  • Sound source localization tracking device and method based on microphone cross ring array

    CN109669159A

  • Voice arrival direction estimation method and device

    CN110261816A

  • Sound event detection and positioning method and device, equipment and readable storage medium

    CN112581978A

  • Creating an audio envelope based on angular information

    US20170280235A1