A far-field voice wake-up method, system, terminal and storage medium of an application

Abstract

The application discloses an applied far-field voice wake-up method and system, a terminal and a storage medium. The method comprises the following steps: when it is detected that a user issues an application wake-up instruction, obtaining recording data collected by a target device according to the application wake-up instruction, and performing enhanced noise reduction processing on the recording data to obtain target recording data; confirming the type of the target device to obtain device type information, and performing architecture decision evaluation according to the device type information to obtain a target wake-up architecture; performing data processing on the target recording data according to the target wake-up architecture to obtain an application wake-up signal, and waking up a corresponding voice application according to the application wake-up signal. The application can quickly evaluate the best wake-up support structure by introducing a decision module, and realizes the reuse of a wake-up algorithm module by customizing a unified general interface.

Description

Technical Field

[0001] This invention relates to the field of voice wake-up processing technology, and in particular to an application of a far-field voice wake-up method, system, terminal, and computer-readable storage medium. Background Technology

[0002] With the rapid development of smart devices, far-field voice wake-up has become a standard feature. There are two existing architectures for far-field voice wake-up solutions: one follows the system's wake-up support architecture, and the other follows the app's wake-up support architecture. The system-following architecture obtains enhanced and noise-reduced recording data at the system's hardware abstraction layer. The wake-up signal, obtained after passing through the wake-up algorithm module, is transmitted to the voice app via a shared socket (network programming interface). If the algorithm is updated, a system upgrade is usually required, resulting in insufficient flexibility. However, because it's a low-level solution, it offers better real-time performance and generally better wake-up functionality. The app-following architecture obtains noise-reduced and enhanced data through a standard recording interface and then calls the wake-up algorithm module through a custom JNI interface. The wake-up signal is then given to the app through a custom callback interface. If the algorithm is updated, only the app needs to be updated. This solution allows for faster adaptation and quicker product iteration and deployment.

[0003] Currently, the two existing far-field voice wake-up solutions typically consist of two separate software packages, requiring customization based on the device and specific needs. This hinders solution evaluation, makes it difficult to quickly switch between solutions to verify effectiveness, and prevents the determination of the optimal adaptation method. Furthermore, due to the poor system-level support architecture for expansion capabilities, it is impossible to quickly and easily port solutions from one device to another. On the other hand, the APP-based solutions only include the wake-up algorithm, while the enhanced noise reduction algorithm relies on the device itself, which can easily lead to poor performance.

[0004] Therefore, existing technologies still need to be improved and developed. Summary of the Invention

[0005] The main objective of this invention is to provide a far-field voice wake-up method, system, terminal, and storage medium for applications, aiming to solve the problems in the prior art where the optimal adaptation method cannot be quickly determined and the wake-up effect is poor.

[0006] To achieve the above objectives, the present invention provides an application-based far-field voice wake-up method, which includes the following steps: When a user issues an application wake-up command, the recording data collected by the target device is obtained according to the application wake-up command, and the recording data is enhanced and noise-reduced to obtain the target recording data. The target device is identified by type to obtain device type information, and an architecture decision evaluation is performed based on the device type information to obtain the target wake-up architecture; The target recording data is processed according to the target wake-up architecture to obtain an application wake-up signal, and the corresponding voice application is woken up according to the application wake-up signal.

[0007] Optionally, the far-field voice wake-up method of the application, wherein when a user issues an application wake-up command, the recording data collected by the target device is obtained according to the application wake-up command, and the recording data is enhanced and noise-reduced to obtain target recording data, specifically includes: When a user issues an application wake-up command, the recording data collected by the array microphone of the target device is obtained according to the application wake-up command, wherein the recording data includes microphone data and back-collected data; Obtain the data processing format of the enhanced noise reduction algorithm, and adjust the data format of the recording data according to the data processing format to obtain the recording adjustment data; The signal-to-noise ratio of the recording adjustment data is optimized using the enhanced noise reduction algorithm to obtain the target recording data.

[0008] Optionally, the far-field voice wake-up method of the application, wherein the step of confirming the type of the target device to obtain device type information, and performing an architecture decision evaluation based on the device type information to obtain the target wake-up architecture, specifically includes: The target device is type-confirmed to obtain device type information. Based on the device type information, it is determined whether the target device provides system source code, and a first determination result is obtained. If the first determination result is that the target device provides system source code, then the target device is determined to have an enhanced noise reduction algorithm based on the first determination result, and a second determination result is obtained; If the second determination result indicates that the target device has an enhanced noise reduction algorithm, then based on the second determination result, it is determined whether the target device has high sound quality requirements, and a third determination result is obtained; If the third determination result indicates that the target device has high sound quality requirements, then the fourth determination result is obtained by determining whether the target device supports system upgrades based on the third determination result. If the fourth determination result is that the target device supports system upgrade, then determine whether the target device needs lightweight adaptation based on the fourth determination result to obtain the fifth determination result; If the fifth determination result is that the target device does not require lightweight adaptation, then the target wake-up architecture is determined to be a wake-up support architecture that follows the system.

[0009] Optionally, the far-field voice wake-up method of the application, wherein the step of confirming the type of the target device to obtain device type information, and performing an architecture decision evaluation based on the device type information to obtain a target wake-up architecture, further includes: If the first determination result is that the target device does not provide system source code, or the second determination result is that the target device does not have an enhanced noise reduction algorithm, or the third determination result is that the target device does not have high sound quality requirements, or the fourth determination result is that the target device does not support system upgrades, or if the fifth determination result is that the target device needs lightweight adaptation, then the target wake-up architecture is determined to be the wake-up support architecture that follows the APP.

[0010] Optionally, the far-field voice wake-up method for the application, wherein the step of processing the target recording data according to the target wake-up architecture to obtain an application wake-up signal, and waking up the corresponding voice application according to the application wake-up signal, specifically includes: If the target wake-up architecture is a wake-up support architecture that follows the system, feature analysis is performed on the target recording data according to the wake-up algorithm; If the target recording data matches the wake word feature, then an application wake-up signal is generated based on the target recording data; The transmission interface of the application wake-up signal is determined according to the target wake-up architecture to obtain the network programming interface, and the application wake-up signal is sent to the corresponding voice application according to the network programming interface to wake up the voice application.

[0011] Optionally, the far-field voice wake-up method for the application, wherein the step of processing the target recording data according to the target wake-up architecture to obtain an application wake-up signal, and waking up the corresponding voice application according to the application wake-up signal, specifically includes: If the target wake-up architecture is a wake-up support architecture that follows the APP, then a corresponding data filling interface is defined according to the target wake-up architecture, and a wake-up algorithm is extracted according to the data filling interface; The target recording data is analyzed for features according to the wake-up algorithm. If the target recording data matches the wake-up word features, an application wake-up signal is generated based on the target recording data. Based on the application wake-up signal, a corresponding wake-up callback interface is defined, and the application wake-up signal is sent to the corresponding voice application according to the wake-up callback interface to wake up the voice application.

[0012] Optionally, the far-field voice wake-up method for the application further includes, after processing the target recording data according to the target wake-up architecture to obtain an application wake-up signal, and waking up the corresponding voice application according to the application wake-up signal: If no wake-up feedback is received from the voice application within a preset time, the voice application is determined to have failed to wake up, and a wake-up command is generated to re-wake up the voice application according to the wake-up command.

[0013] Optionally, the far-field voice wake-up method of the application, wherein the far-field voice wake-up system of the application includes: The data processing module is used to obtain the recording data collected by the target device according to the application wake-up command when the user issues an application wake-up command, and to perform enhancement and noise reduction processing on the recording data to obtain the target recording data. The architecture evaluation module is used to confirm the type of the target device, obtain device type information, and perform architecture decision evaluation based on the device type information to obtain the target wake-up architecture. The application wake-up module is used to process the target recording data according to the target wake-up architecture to obtain the application wake-up signal, and wake up the corresponding voice application according to the application wake-up signal.

[0014] Furthermore, to achieve the above objectives, the present invention also provides a terminal, wherein the terminal includes: a memory, a processor, and a far-field voice wake-up program for an application stored in the memory and executable on the processor, wherein when the far-field voice wake-up program for the application is executed by the processor, it implements the steps of the far-field voice wake-up method for the application as described above.

[0015] Furthermore, to achieve the above objectives, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a far-field voice wake-up program for an application, which, when executed by a processor, implements the steps of the far-field voice wake-up method for the application as described above.

[0016] In this invention, when a user issues an application wake-up command, the system acquires recording data from the target device based on the command, performs noise reduction and enhancement processing on the recording data to obtain target recording data, confirms the target device type to obtain device type information, and evaluates the architecture based on the device type information to obtain a target wake-up architecture. The system then processes the target recording data according to the target wake-up architecture to obtain an application wake-up signal, and wakes up the corresponding voice application based on the application wake-up signal. This invention, by introducing a decision module, can quickly evaluate the optimal wake-up support structure, and by customizing a unified universal interface, it achieves the reuse of the wake-up algorithm module. Attached Figure Description

[0017] Figure 1 This is a flowchart of a preferred embodiment of the far-field voice wake-up method applied in this invention; Figure 2 This is a schematic diagram of the overall architecture of the far-field voice wake-up method applied in this invention; Figure 3 This is a flowchart illustrating the architecture evaluation process of the decision module in a preferred embodiment of the far-field voice wake-up method applied in this invention. Figure 4 This is a structural diagram of a preferred embodiment of the far-field voice wake-up system used in this invention; Figure 5 This is a schematic diagram of the operating environment of a preferred embodiment of the terminal of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this invention clearer and more explicit, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0019] It should be noted that if the embodiments of the present invention involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of the components in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0020] Furthermore, if the embodiments of this invention involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention.

[0021] The preferred embodiment of the present invention describes a far-field voice wake-up method, such as... Figure 1 As shown, the far-field voice wake-up method of the application includes the following steps: Step S10: When a user issues an application wake-up command, the recording data collected by the target device is obtained according to the application wake-up command, and the recording data is enhanced and noise-reduced to obtain the target recording data.

[0022] Step S10 includes: Step S11: When a user issues an application wake-up command, the recording data collected by the array microphone of the target device is obtained according to the application wake-up command, wherein the recording data includes microphone data and back-collected data; Step S12: Obtain the data processing format of the enhanced noise reduction algorithm, and adjust the data format of the recording data according to the data processing format to obtain the recording adjustment data; Step S13: Optimize the signal-to-noise ratio of the recording adjustment data according to the enhanced noise reduction algorithm to obtain the target recording data.

[0023] Specifically, existing far-field voice wake-up solutions typically use two separate software packages, requiring customization based on device and requirements. This hinders solution evaluation, prevents rapid switching to verify effectiveness, and makes it difficult to determine the optimal adaptation method. Furthermore, due to poor system-level support architecture expansion capabilities, lightweight and rapid porting from one device to another is impossible. App-based solutions, which only include the wake-up algorithm while relying on the device itself for enhanced noise reduction algorithms, are prone to poor performance. This invention proposes an application-based far-field voice wake-up method to address these problems. The specific processing steps are as follows: Figure 2 As shown, when a user issues an application wake-up command, the recording data collected by the array microphones (e.g., 2 mics and 4 mics) of the target device is obtained according to the application wake-up command. The recording data includes microphone data and retrieval data.

[0024] Next, the recording data is packaged into the data format required by the enhancement and noise reduction algorithm using ALSA (i.e., the sound card driver). Specifically, the data processing format of the enhancement and noise reduction algorithm is obtained, and the data format of the recording data is adjusted according to the data processing format to obtain the recording adjustment data. Taking a 2-mic array microphone as an example, the recording adjustment data usually includes two microphone data and two backtracking data, and the microphone data and backtracking data are consistent in time. Then, the signal-to-noise ratio of the recording adjustment data is optimized according to the enhancement and noise reduction algorithm to obtain the target recording data. After processing by the enhancement and noise reduction algorithm, the effective voice data is highlighted, while other noise from the outside and noise from the audio and video resources played by the device itself are mostly eliminated. The signal-to-noise ratio of the obtained target recording data is usually less than 10dB. The purpose of the enhancement and noise reduction algorithm is to meet the requirements of the subsequent wake-up algorithm.

[0025] Step S20: Confirm the type of the target device to obtain device type information, and perform architecture decision evaluation based on the device type information to obtain the target wake-up architecture.

[0026] Step S20 includes: Step S21: Confirm the type of the target device to obtain device type information, and determine whether the target device provides system source code based on the device type information to obtain a first determination result; Step S22: If the first determination result is that the target device provides system source code, then determine whether the target device has an enhanced noise reduction algorithm based on the first determination result, and obtain the second determination result; Step S23: If the second determination result is that the target device has an enhanced noise reduction algorithm, then determine whether the target device has high sound quality requirements based on the second determination result, and obtain a third determination result; Step S24: If the third determination result indicates that the target device has high sound quality requirements, then determine whether the target device supports system upgrade based on the third determination result to obtain the fourth determination result; Step S25: If the fourth determination result is that the target device supports system upgrade, then determine whether the target device needs lightweight adaptation based on the fourth determination result to obtain the fifth determination result; Step S26: If the fifth determination result is that the target device does not require lightweight adaptation, then the target wake-up architecture is determined to be a wake-up support architecture that follows the system.

[0027] Specifically, after obtaining the target recording data, it is necessary to determine the optimal wake-up support architecture. In this embodiment of the invention, a suitable wake-up support architecture is quickly evaluated by combining factors such as device type, quality requirements, and product iteration needs. The specific processing procedure is as follows: Figure 3 As shown, the decision module confirms the type of the target device to obtain device type information (e.g., TV, mobile phone, and tablet). Based on the device type information, it determines whether the target device provides system source code, resulting in a first determination result. If the first determination result indicates that the target device provides system source code, it determines whether the target device has an enhanced noise reduction algorithm, resulting in a second determination result. If the second determination result indicates that the target device has an enhanced noise reduction algorithm, it determines whether the target device requires high-quality audio, resulting in a third determination result. If the third determination result indicates that the target device requires high-quality audio, it determines whether the target device supports system upgrades, resulting in a fourth determination result. If the fourth determination result indicates that the target device supports system upgrades, it determines whether the target device requires lightweight adaptation, resulting in a fifth determination result. If the fifth determination result indicates that the target device does not require lightweight adaptation, the target wake-up architecture is determined to be a wake-up support architecture that follows the system.

[0028] Furthermore, if the first determination result is that the target device does not provide system source code, or the second determination result is that the target device does not have an enhanced noise reduction algorithm, or the third determination result is that the target device does not have high sound quality requirements, or the fourth determination result is that the target device does not support system upgrades, or if the fifth determination result is that the target device needs lightweight adaptation, then the target wake-up architecture is determined to be the wake-up support architecture that follows the APP.

[0029] Step S30: Process the target recording data according to the target wake-up architecture to obtain the application wake-up signal, and wake up the corresponding voice application according to the application wake-up signal.

[0030] Specifically, after determining the target wake-up architecture, the target recording data is processed according to the target wake-up architecture. In this embodiment of the invention, different processing methods are used for different target wake-up architectures, such as... Figure 2As shown, if the target wake-up architecture is a wake-up support architecture following the system, the target recording data is processed directly at the bottom layer according to the wake-up algorithm. Specifically, the target recording data is subjected to feature analysis according to the wake-up algorithm. By comparing the features of a specific wake-up word, if the target recording data matches the wake-up word features, an application wake-up signal is generated based on the target recording data. Then, the transmission method of the wake-up signal is determined through the result cached by the decision module, avoiding the functional redundancy of repeatedly sending the wake-up signal. The result cached by the decision module is a state. For example, if the state is STATUS_APP, it indicates that the current wake-up signal will be sent by a customized wake-up callback interface; if the state is STATUS_SYS, it indicates that the wake-up signal will be sent by a socket interface (i.e., a network programming interface). Specifically, the transmission interface of the application wake-up signal is determined according to the target wake-up architecture to obtain the socket interface, and the application wake-up signal is sent to the corresponding voice application according to the network programming interface to wake up the voice application.

[0031] If the target wake-up architecture is a wake-up support architecture that follows the APP, then the corresponding target recording data is in a voice application. Before processing the target recording data, it is necessary to extract the target recording data. Specifically, a corresponding data filling interface is defined according to the target wake-up architecture, and a wake-up algorithm is extracted according to the data filling interface. The target recording data is then subjected to feature analysis according to the wake-up algorithm. If the target recording data matches the wake-up word feature, an application wake-up signal is generated based on the target recording data. Afterward, a corresponding wake-up callback interface is defined according to the application wake-up signal, and the application wake-up signal is sent to the corresponding voice application according to the wake-up callback interface to wake up the voice application.

[0032] Furthermore, after sending the application wake-up signal to the corresponding voice application, it is necessary to determine whether the voice application has been successfully woken up. If a wake-up response is received from the voice application within a preset time, for example, the voice application will respond with a human voice, such as "Yes," or render a specific animation, such as the appearance of a "Yes" text prompt box, then the voice application is determined to have been successfully woken up. If no wake-up response is received from the voice application within the preset time, then the voice application is determined to have failed to wake up, and a re-wake-up command is generated to re-wake up the voice application according to the re-wake-up command.

[0033] Furthermore, such as Figure 3 As shown, based on the far-field voice wake-up method described above, this invention also provides a corresponding far-field voice wake-up system, wherein the far-field voice wake-up system includes: The data processing module 51 is used to obtain the recording data collected by the target device according to the application wake-up command when the user issues an application wake-up command, and to perform enhancement and noise reduction processing on the recording data to obtain the target recording data. Architecture evaluation module 52 is used to confirm the type of the target device, obtain device type information, and perform architecture decision evaluation based on the device type information to obtain the target wake-up architecture; The application wake-up module 53 is used to process the target recording data according to the target wake-up architecture to obtain the application wake-up signal, and wake up the corresponding voice application according to the application wake-up signal.

[0034] Furthermore, such as Figure 4 As shown, based on the far-field voice wake-up method described above, the present invention also provides a terminal, which includes a processor 10, a memory 20, and a display 30. Figure 4 Only some of the terminal components are shown; however, it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0035] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory. In other embodiments, the memory 20 may be an external storage device of the terminal, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc. Further, the memory 20 may include both internal and external storage devices. The memory 20 is used to store application software and various types of data installed on the terminal, such as the program code installed on the terminal. The memory 20 can also be used to temporarily store data that has been output or will be output. In one embodiment, the memory 20 stores a far-field voice wake-up program 40 for an application, which can be executed by the processor 10 to implement the far-field voice wake-up method applied in this application.

[0036] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor, or other data processing chip, used to run program code stored in the memory 20 or process data, such as executing the far-field voice wake-up method of the application.

[0037] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display 30 is used to display information on the terminal and to display a visual user interface. The components of the terminal communicate with each other via a system bus.

[0038] In one embodiment, when the processor 10 executes the far-field voice wake-up program 40 applied in the memory 20, the following steps are performed: When a user issues an application wake-up command, the recording data collected by the target device is obtained according to the application wake-up command, and the recording data is enhanced and noise-reduced to obtain the target recording data. The target device is identified by type to obtain device type information, and an architecture decision evaluation is performed based on the device type information to obtain the target wake-up architecture; The target recording data is processed according to the target wake-up architecture to obtain an application wake-up signal, and the corresponding voice application is woken up according to the application wake-up signal.

[0039] Specifically, when a user issues an application wake-up command, the process of acquiring the recording data collected by the target device according to the application wake-up command, and performing enhancement and noise reduction processing on the recording data to obtain the target recording data includes: When a user issues an application wake-up command, the recording data collected by the array microphone of the target device is obtained according to the application wake-up command, wherein the recording data includes microphone data and back-collected data; Obtain the data processing format of the enhanced noise reduction algorithm, and adjust the data format of the recording data according to the data processing format to obtain the recording adjustment data; The signal-to-noise ratio of the recording adjustment data is optimized using the enhanced noise reduction algorithm to obtain the target recording data.

[0040] Specifically, the step of confirming the type of the target device to obtain device type information, and then performing an architecture decision evaluation based on the device type information to obtain the target wake-up architecture, includes: The target device is type-confirmed to obtain device type information. Based on the device type information, it is determined whether the target device provides system source code, and a first determination result is obtained. If the first determination result is that the target device provides system source code, then the target device is determined to have an enhanced noise reduction algorithm based on the first determination result, and a second determination result is obtained; If the second determination result indicates that the target device has an enhanced noise reduction algorithm, then based on the second determination result, it is determined whether the target device has high sound quality requirements, and a third determination result is obtained; If the third determination result indicates that the target device has high sound quality requirements, then the fourth determination result is obtained by determining whether the target device supports system upgrades based on the third determination result. If the fourth determination result is that the target device supports system upgrade, then determine whether the target device needs lightweight adaptation based on the fourth determination result to obtain the fifth determination result; If the fifth determination result is that the target device does not require lightweight adaptation, then the target wake-up architecture is determined to be a wake-up support architecture that follows the system.

[0041] The process of confirming the type of the target device to obtain device type information, and then performing an architecture decision evaluation based on the device type information to obtain the target wake-up architecture, further includes: If the first determination result is that the target device does not provide system source code, or the second determination result is that the target device does not have an enhanced noise reduction algorithm, or the third determination result is that the target device does not have high sound quality requirements, or the fourth determination result is that the target device does not support system upgrades, or if the fifth determination result is that the target device needs lightweight adaptation, then the target wake-up architecture is determined to be the wake-up support architecture that follows the APP.

[0042] Specifically, the step of processing the target recording data according to the target wake-up architecture to obtain an application wake-up signal, and waking up the corresponding voice application according to the application wake-up signal, includes: If the target wake-up architecture is a wake-up support architecture that follows the system, feature analysis is performed on the target recording data according to the wake-up algorithm; If the target recording data matches the wake word feature, then an application wake-up signal is generated based on the target recording data; The transmission interface of the application wake-up signal is determined according to the target wake-up architecture to obtain the network programming interface, and the application wake-up signal is sent to the corresponding voice application according to the network programming interface to wake up the voice application.

[0043] Specifically, the step of processing the target recording data according to the target wake-up architecture to obtain an application wake-up signal, and waking up the corresponding voice application according to the application wake-up signal, includes: If the target wake-up architecture is a wake-up support architecture that follows the APP, then a corresponding data filling interface is defined according to the target wake-up architecture, and a wake-up algorithm is extracted according to the data filling interface; The target recording data is analyzed for features according to the wake-up algorithm. If the target recording data matches the wake-up word features, an application wake-up signal is generated based on the target recording data. Based on the application wake-up signal, a corresponding wake-up callback interface is defined, and the application wake-up signal is sent to the corresponding voice application according to the wake-up callback interface to wake up the voice application.

[0044] The step of processing the target recording data according to the target wake-up architecture to obtain an application wake-up signal, and then waking up the corresponding voice application according to the application wake-up signal, further includes: If no wake-up feedback is received from the voice application within a preset time, the voice application is determined to have failed to wake up, and a wake-up command is generated to re-wake up the voice application according to the wake-up command.

[0045] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a far-field voice wake-up program for an application, which, when executed by a processor, implements the steps of the far-field voice wake-up method for the application as described above.

[0046] In summary, this invention provides a far-field voice wake-up method, system, terminal, and storage medium for an application. The method includes: when a user issues an application wake-up command, acquiring recording data collected by a target device according to the application wake-up command, and performing enhancement and noise reduction processing on the recording data to obtain target recording data; confirming the type of the target device to obtain device type information, and performing architecture decision evaluation based on the device type information to obtain a target wake-up architecture; processing the target recording data according to the target wake-up architecture to obtain an application wake-up signal, and waking up the corresponding voice application according to the application wake-up signal. This invention can quickly evaluate the optimal wake-up support structure by introducing a decision module, and achieves the reuse of the wake-up algorithm module through a customized unified general interface.

[0047] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal that includes that element.

[0048] Of course, those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.). The program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The computer-readable storage medium can be a memory, magnetic disk, optical disk, etc.

[0049] It should be understood that the application of the present invention is not limited to the examples above. Those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. A method for far-field voice wake-up in application, characterized in that, The far-field voice wake-up method of the application includes: When a user issues an application wake-up command, the recording data collected by the target device is obtained according to the application wake-up command, and the recording data is enhanced and noise-reduced to obtain the target recording data. The target device is identified by type to obtain device type information, and an architecture decision evaluation is performed based on the device type information to obtain the target wake-up architecture; The step of confirming the type of the target device to obtain device type information, and then performing an architecture decision evaluation based on the device type information to obtain the target wake-up architecture, specifically includes: The target device is type-confirmed to obtain device type information. Based on the device type information, it is determined whether the target device provides system source code, and a first determination result is obtained. If the first determination result is that the target device provides system source code, then the target device is determined to have an enhanced noise reduction algorithm based on the first determination result, and a second determination result is obtained; If the second determination result indicates that the target device has an enhanced noise reduction algorithm, then based on the second determination result, it is determined whether the target device has high sound quality requirements, and a third determination result is obtained; If the third determination result indicates that the target device has high sound quality requirements, then the fourth determination result is obtained by determining whether the target device supports system upgrades based on the third determination result. If the fourth determination result is that the target device supports system upgrade, then determine whether the target device needs lightweight adaptation based on the fourth determination result to obtain the fifth determination result; If the fifth determination result is that the target device does not require lightweight adaptation, then the target wake-up architecture is determined to be a wake-up support architecture that follows the system. The target recording data is processed according to the target wake-up architecture to obtain an application wake-up signal, and the corresponding voice application is woken up according to the application wake-up signal.

2. The far-field voice wake-up method according to claim 1, characterized in that, When a user issues an application wake-up command, the system acquires the recording data collected by the target device based on the application wake-up command, and performs enhancement and noise reduction processing on the recording data to obtain the target recording data. Specifically, this includes: When a user issues an application wake-up command, the recording data collected by the array microphone of the target device is obtained according to the application wake-up command, wherein the recording data includes microphone data and back-collected data; Obtain the data processing format of the enhanced noise reduction algorithm, and adjust the data format of the recording data according to the data processing format to obtain the recording adjustment data; The signal-to-noise ratio of the recording adjustment data is optimized using the enhanced noise reduction algorithm to obtain the target recording data.

3. The far-field voice wake-up method according to claim 1, characterized in that, The process of confirming the type of the target device to obtain device type information, and then performing an architecture decision evaluation based on the device type information to obtain the target wake-up architecture, further includes: If the first determination result is that the target device does not provide system source code, or the second determination result is that the target device does not have an enhanced noise reduction algorithm, or the third determination result is that the target device does not have high sound quality requirements, or the fourth determination result is that the target device does not support system upgrades, or if the fifth determination result is that the target device needs lightweight adaptation, then the target wake-up architecture is determined to be the wake-up support architecture that follows the APP.

4. The far-field voice wake-up method according to claim 3, characterized in that, The step of processing the target recording data according to the target wake-up architecture to obtain an application wake-up signal, and waking up the corresponding voice application according to the application wake-up signal, specifically includes: If the target wake-up architecture is a wake-up support architecture that follows the system, feature analysis is performed on the target recording data according to the wake-up algorithm; If the target recording data matches the wake word feature, then an application wake-up signal is generated based on the target recording data; The transmission interface of the application wake-up signal is determined according to the target wake-up architecture to obtain the network programming interface, and the application wake-up signal is sent to the corresponding voice application according to the network programming interface to wake up the voice application.

5. The far-field voice wake-up method according to claim 3, characterized in that, The step of processing the target recording data according to the target wake-up architecture to obtain an application wake-up signal, and waking up the corresponding voice application according to the application wake-up signal, specifically includes: If the target wake-up architecture is a wake-up support architecture that follows the APP, then a corresponding data filling interface is defined according to the target wake-up architecture, and a wake-up algorithm is extracted according to the data filling interface; The target recording data is analyzed for features according to the wake-up algorithm. If the target recording data matches the wake-up word features, an application wake-up signal is generated based on the target recording data. A corresponding wake-up callback interface is defined based on the application wake-up signal, and the application wake-up signal is sent to the corresponding voice application according to the wake-up callback interface to wake up the voice application.

6. The far-field voice wake-up method according to claim 1, characterized in that, The step of processing the target recording data according to the target wake-up architecture to obtain an application wake-up signal, and then waking up the corresponding voice application according to the application wake-up signal, further includes: If no wake-up feedback is received from the voice application within a preset time, the voice application is determined to have failed to wake up, and a wake-up command is generated to re-wake up the voice application according to the wake-up command.

7. A far-field voice wake-up system for an application, characterized in that, The far-field voice wake-up system of the application is used to implement the far-field voice wake-up method of the application according to any one of claims 1-6, and the far-field voice wake-up system of the application includes: The data processing module is used to obtain the recording data collected by the target device according to the application wake-up command when the user issues an application wake-up command, and to perform enhancement and noise reduction processing on the recording data to obtain the target recording data. The architecture evaluation module is used to confirm the type of the target device, obtain device type information, and perform architecture decision evaluation based on the device type information to obtain the target wake-up architecture. The application wake-up module is used to process the target recording data according to the target wake-up architecture to obtain the application wake-up signal, and wake up the corresponding voice application according to the application wake-up signal.

8. A terminal, characterized in that, The terminal includes: a memory, a processor, and a far-field voice wake-up program for an application stored in the memory and executable on the processor. When the far-field voice wake-up program for the application is executed by the processor, it implements the steps of the far-field voice wake-up method for the application as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a far-field voice wake-up program for an application, which, when executed by a processor, implements the steps of the far-field voice wake-up method for an application as described in any one of claims 1-6.

Images