WO2021179854A1

WO2021179854A1 - Voiceprint wakeup method and apparatus, device, and storage medium

Info

Publication number: WO2021179854A1
Application number: PCT/CN2021/074833
Authority: WO
Inventors: 胡宁宁; 陈喆; 曹冰
Original assignee: Oppo广东移动通信有限公司
Priority date: 2020-03-12
Filing date: 2021-02-02
Publication date: 2021-09-16
Also published as: CN111223490A

Abstract

A voiceprint wakeup method and apparatus, a device, and a storage medium. The method comprises: determining, according to a preset condition, a preset wakeup parameter matching a current scene, wherein the preset wakeup parameter being used for characterizing a wakeup threshold and/or a voiceprint threshold meeting a wakeup requirement (S110a); and in response to a voiceprint wakeup operation, awakening, according to the preset wakeup parameter, an application to be awakened (S120a). In the present method, the current scene comprises a driving scene.

Description

Voiceprint wake-up method and device, equipment and storage medium

Cross-references to related applications

This application is filed based on the Chinese patent application with the application number 202010172688.7 and the filing date on March 12, 2020, and claims the priority of the Chinese patent application. The entire content of the Chinese patent application is hereby incorporated into this application in full .

Technical field

This application relates to the technical field of voice processing, and relates to a voiceprint wake-up method, device, device, and storage medium that are not limited to.

Background technique

The voiceprint feature is one of the important biological characteristics of the human body. It has strong individual specificity. It is often configured as a feature of identity authentication in areas such as voiceprint recognition and voiceprint authentication. With the rapid development of voice processing technology, voiceprint wake-up technology has been widely used in electronic devices with intelligent voice dialogue wake-up functions. For example, users can wake up voice interactive applications such as "voice assistant" by speaking a voice command when it is inconvenient to directly control the electronic device, and then realize the control of the electronic device through voice interaction with the voice interactive application.

Summary of the invention

The embodiments of the present application provide a voiceprint wake-up method, device, equipment, and storage medium.

The technical solutions of the embodiments of the present application are implemented as follows:

In the first aspect, an embodiment of the present application provides a voiceprint wake-up method, and the method includes:

Determine a preset wake-up parameter matching the current scene according to preset conditions; wherein the preset wake-up parameter is used to characterize a wake-up threshold and/or a voiceprint threshold that meets the wake-up requirement;

In response to the voiceprint wake-up operation, the application program to be awakened is awakened according to the preset wake-up parameter.

In a second aspect, an embodiment of the present application provides a voiceprint wake-up device. The device includes a first determination module and a first wake-up module, wherein:

The first determining module is configured to determine a preset wake-up parameter matching the current scene according to a preset condition; wherein the preset wake-up parameter is used to characterize a wake-up threshold and/or a voiceprint threshold that meets a wake-up requirement;

The first wake-up module is configured to wake up the application to be awakened according to the preset wake-up parameter in response to the voiceprint wake-up operation.

In a third aspect, an embodiment of the present application provides an electronic device, including a memory and a processor. The memory stores a computer program that can run on the processor. When the computer program is executed by the processor, the processing The device performs the following operations: obtains preset wake-up parameters that match the current scene; wherein, the preset wake-up parameters are used to characterize the wake-up threshold and/or voiceprint threshold that meet the wake-up requirements; in response to the voiceprint wake-up operation, follow the Preset wake-up parameters and wake up the application to be awakened.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps in the voiceprint wake-up method described above are realized.

The beneficial effects brought about by the technical solutions provided by the embodiments of the present invention include at least:

In the embodiment of the present application, first, a preset wake-up parameter that matches the current scene is determined according to preset conditions; wherein, the preset wake-up parameter is used to characterize the wake-up threshold and/or voiceprint threshold that meets the wake-up requirement; then, In response to the voiceprint wake-up operation, the application to be awakened is awakened according to the preset wake-up parameters; in this way, the wake-up and voiceprint thresholds can be automatically adjusted according to the current scene, which improves the user's wake-up rate and enhances the user experience.

Description of the drawings

In order to explain the technical solutions in the embodiments of the present invention more clearly, the following will briefly introduce the drawings needed in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative work, other drawings can be obtained based on these drawings, among which:

FIG. 1A is an optional flowchart of a voiceprint wake-up method provided by an embodiment of this application;

FIG. 1B is an optional flowchart of a voiceprint wake-up method provided by an embodiment of this application;

FIG. 2 is a schematic diagram of an optional process of the voiceprint wake-up method provided by an embodiment of the application;

FIG. 3 is an optional flowchart of the voiceprint wake-up method provided by an embodiment of the application;

FIG. 4A is a logical block diagram of improving the voiceprint awakening rate in a driving scenario provided by an embodiment of the application;

4B is a schematic diagram of a voiceprint monitoring process in a non-driving mode provided by an embodiment of the application;

4C is a schematic diagram of a voiceprint monitoring process in a driving mode provided by an embodiment of the application;

5A is a schematic diagram of the structure of the voiceprint wake-up device provided by an embodiment of the application;

5B is a schematic diagram of the composition structure of the voiceprint wake-up device provided by an embodiment of the application;

FIG. 6 is a schematic diagram of a hardware entity of an electronic device provided by an embodiment of the application.

Detailed ways

In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments It is a part of the embodiments of the present application, but not all of the embodiments. The following examples are used to illustrate the application, but not to limit the scope of the application. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

Before describing in detail the voiceprint wake-up method provided by the embodiments of the present application, a brief introduction to the terms and related technologies involved in the embodiments of the present application will be given first.

Voiceprint Recognition (VPR) is a type of biometric technology that converts acoustic signals into electrical signals and then uses a computer for recognition. Also known as Speaker Recognition, there are two types, namely Speaker Identification and Speaker Verification. The former is used to determine which one of several people said a certain speech, which is a "multiple choice" question; while the latter is used to confirm whether a certain speech is spoken by a designated person, which is a "one-to-one discrimination". "problem.

In the car scene, in the absence of the support of voiceprint recognition technology, the smart rearview mirror is easily awakened by accidental wake-up words in the broadcast, thereby affecting driving. Let the smart device understand "who" is giving the order when receiving the order, so that every user can enjoy the most suitable content and service for the first time with just one sentence, realizing the real naturalness of human-computer interaction And intelligent.

In the voice interaction scenario, the identity document (ID) of the voiceprint biological information becomes the best choice. By recording the voice, the system automatically extracts voiceprint features, which can quickly identify the speaker's identity without being affected by the language.

Voice wake-up: refers to the user waking up the electronic device by speaking the wake-up word, causing the electronic device to enter a state of waiting for a voice command or causing the electronic device to directly execute a predetermined voice command.

Wake-up word: A string used to wake up the electronic device to perform a voice wake-up operation. For example, the wake-up words are "Xiaoai classmate", "Xiaobu Xiaobu" and so on.

Voice instructions: instructions for voice-controlled electronic devices to perform predetermined operations. For example, the voice command can be "navigate home", "play music" and so on.

Wake-up threshold: used for the electronic device to determine whether to perform a voice wake-up operation based on the wake-up word. When the acoustic score of the wake-up word is greater than the wake-up threshold, the voice wake-up operation is performed; when the acoustic score of the wake-up word is less than the wake-up threshold, the voice wake-up operation is not performed. The wakeup threshold is set according to the number of false wakeups. The larger the wakeup threshold, the fewer the number of false wakeups. Usually, the actual application of the product must ensure that the number of false wakeups within 24 hours should be <= 1. It is necessary to prepare 100 hours of noise audio and adjust the wakeup threshold to meet the false wakeup requirements.

Voiceprint (Voiceprint) is a sound wave spectrum that carries verbal information displayed by an electro-acoustic instrument.

Voiceprint threshold: used to identify whether it is a voice wake-up operation performed by a specified user. It can be used to determine the similarity between the input voiceprint feature and the registered voiceprint features that have been stored by all registered users.

Awakening rate: refers to the success rate of user interaction, the technical term is the recall rate.

False wake-up: Voice wake-up caused by no specific wake-up word entered in the voice.

False awakening rate: the probability of false awakening within a certain period of time.

Increasing the wake-up rate, that is, the wake-up success rate, is mainly to lower the wake-up threshold. The simplest and fastest way is to lower the wake-up threshold to achieve the purpose of easy wake-up, but at the same time it will bring about the improvement of false wake-up. The wake-up threshold is obtained by weighting the posterior of the wake-up words according to the sequence of appearance of the words. The reduction of the wake-up threshold means that the requirements for some words in the wake-up words are reduced, resulting in an increase in deletion and replacement of false arousals. In other words, the lower the wake-up threshold, the higher the wake-up rate, and the higher the false wake-up rate; the higher the wake-up threshold, the lower the wake-up rate and the lower the false wake-up rate.

At present, electronic devices generally have voice interaction functions, that is, voice assistants. Voice assistants are a smart mobile phone application that helps users solve problems through intelligent interactions between intelligent dialogue and instant question and answer, which is mainly to help users solve their lives. Class problem. The user can perform part of the operation of the electronic device by inputting voice instructions, so that the user can release his hands when controlling the electronic device in some specific situations.

In the prior art, voiceprint awakening is generally performed by pre-setting wakeup and voiceprint thresholds. In the related art, a scene-based voice operation method and device are proposed. The method is to directly wake up according to the scene information after receiving the voice awakening instruction. For related applications, the voice assistant is not awakened during the wake-up process; another technology proposes a voice wake-up method, which is applied to the vehicle environment. The method proposes to activate the wake-up-free control logic when the user state meets the conditions, that is, without a wake-up word. The voice control logic can be awakened by voice; the related technology also proposes a method and device for adjusting the awakening sensitivity. This method is aimed at smart speaker devices and dynamically adjusts preset parameters by monitoring the noise of the surrounding environment or network traffic.

In summary, the existing methods for increasing the voiceprint wake-up rate have the following significant shortcomings: 1) Since users use electronic devices in various scenarios and are in a constantly changing process, a fixed preset threshold is adopted. , There is no way to meet the user's multi-scenario wake-up requirements; 2) Since the voice assistant is not awakened during the wake-up process, the usage scenarios are very limited and under current technical conditions, only very limited applications can be awakened; 3) Because The wake-up-free control logic is activated when the user status meets the conditions, which will cause frequent false wake-ups of the device; 4) Only monitoring environmental noise or network traffic cannot meet the needs of electronic devices for more diverse wake-up scenarios.

Based on at least one of the above-mentioned problems in related technologies, embodiments of the present application provide a voiceprint wake-up method, device, device, and storage medium, which can automatically adjust wake-up and voiceprint thresholds according to the current scene, improve user wake-up rate, and improve user experience .

FIG. 1A is an optional flowchart of the voiceprint wake-up method provided by an embodiment of this application, which is used for electronic devices with intelligent voice dialogue wake-up functions, such as in-vehicle voice devices, smart voice TVs, smart speakers, smart dialogue toys, and other modern devices. Some smart electronic devices that support voice wake-up, etc. As shown in Figure 1A, the method includes:

Step S110a: Determine a preset wake-up parameter matching the current scene according to a preset condition.

Here, the preset wake-up parameter is used to characterize the wake-up threshold and/or the voiceprint threshold that meets the wake-up requirement; wherein the wake-up threshold is used to set the threshold corresponding to the wake-up word in the preset scene, and the voiceprint threshold is used to set the preset The threshold corresponding to the user's voiceprint feature in the scene.

It should be noted that the voice signal can be collected in a preset scene, and the wake-up threshold in the preset scene can be obtained through model training, or voiceprint feature extraction can be performed on the voice signal input by a specific user, and the sample voiceprint feature can be stored or established. Voiceprint database to determine the preset voiceprint threshold.

It is understandable that as the user enters a driving scene or a quiet indoor scene, there is relatively little interference from other people around the user at this time, which means that there are very few accidental wake-ups by others. Therefore, the preset wakeup threshold and the preset voiceprint threshold can be determined according to different usage scenarios, so as to strike a balance between the false wakeup rate and the wakeup success rate.

In some embodiments, the preset wake-up threshold and preset sound that match the current scene can be determined based on the surrounding environment information where the electronic device is located, such as the environmental noise extracted from the collected voice signal or the environmental state collected by the camera. Pattern threshold. For example, when the electronic device is in a relatively quiet environment such as a bedroom or an office, there is less noise in the surrounding environment and relatively less interference from other users. The wakeup threshold and voiceprint threshold can be reduced, thereby increasing the wakeup rate.

In some embodiments, it is also possible to determine whether the electronic device enters a specific usage scenario through a specific operation of the user on the electronic device, such as an interface switch, a specific voice command, or whether to connect a specific Bluetooth device, so as to determine whether the electronic device enters a specific usage scenario. Scene matching preset wake-up threshold and preset voiceprint threshold. For example, when the user turns on the driving mode switch, or inputs the voice command "turn on (or enter) the driving mode", or connects to the car's Bluetooth, it means that the electronic device is currently in a driving situation and the voice assistant is only used in the driving position. Interference from other users It is also relatively small, which can reduce the wake-up threshold and the voiceprint threshold, thereby increasing the wake-up rate.

Step S120a, in response to the voiceprint wake-up operation, wake up the application to be awakened according to the preset wake-up parameter.

Here, the voiceprint wake-up operation may be a voice instruction including a wake-up word. For example, the voice instruction may be "navigate home", "xiaobuxiaobu, play music", and so on.

Here, by presetting the wake-up threshold and/or voiceprint threshold in the electronic device or software, when a designated user who meets the voiceprint threshold gives a voice command or when the acoustic score of the wake-up word included in the voice command is greater than the wake-up threshold, The application program to be awakened on the electronic device can be awakened from the dormant state to respond to other voice commands of the user.

Here, the application program to be awakened is an application program installed on the electronic device in a state to be activated, and the application program to be awakened is awakened, that is, the application program in the state to be activated or in a dormant state directly enters the state of waiting for instructions. For example, the application program to be awakened may be a voice assistant. By waking up the voice assistant, the voice command is further recognized and the user operation is responded to.

It is understandable that after the electronic device is turned on, the voice assistant is in a standby state and occupies a small amount of memory. When the user’s voiceprint feature matches the voiceprint feature pre-stored in the electronic device, the user inputs a voice command containing a preset wake-up word. Or when the wake-up value of the voice command is greater than the preset wake-up threshold, the voice assistant is activated by waking up the voice assistant. At this point, the user can say what he wants to do, such as "play music" or "call XXX", so that the electronic device can automatically complete the operation.

In the embodiment of the present application, firstly, a preset wake-up parameter matching the current scene is determined according to preset conditions; wherein the preset wake-up parameter includes a preset wake-up threshold and a preset voiceprint threshold; and an input voice signal is received; Determine the wake-up value and voiceprint feature of the voice signal; in the case that the wake-up value is greater than the preset wake-up threshold, and the voiceprint feature is greater than the preset voiceprint threshold, the application to be awakened is performed Wake up; in this way, the wake-up and voiceprint thresholds can be automatically adjusted according to the current scene, which improves the user's wake-up rate and enhances the user experience.

Figure 1B is an optional flowchart of the voiceprint wake-up method provided by an embodiment of the application, which is used for electronic devices with intelligent voice dialogue wake-up functions, such as car voice devices, smart voice TVs, smart speakers, smart dialogue toys, and others Existing smart electronic devices that support voice wake-up, etc. As shown in Figure 1B, the method includes:

Step S110b, in response to the received preset operation, it is determined that the electronic device enters the driving scenario;

Here, the preset operation includes at least one of the following: turning on the interface switch, inputting a first preset voice command, connecting to the car Bluetooth and connecting to a specific Bluetooth device, wherein the first preset voice command includes turning on the driving mode or Enter driving mode.

In the implementation, a voiceprint monitoring module can be set to monitor whether the electronic device receives these preset operations in real time, so as to quickly determine that the electronic device enters the driving situation.

Step S120b, in the driving scenario, determine a preset wake-up parameter matching the driving scenario;

Here, the preset wake-up parameter is used to characterize the wake-up threshold and the voiceprint threshold that meet the wake-up requirement.

When the electronic device is in a driving situation, the core demand of the user at this time is that the wake-up response is more sensitive, that is, the wake-up rate is high. Therefore, when the system recognizes that it is in a driving situation, a lower wake-up threshold and voiceprint threshold can be set as the preset wake-up parameters, thereby greatly improving the wake-up rate.

Step S130b, in response to the voiceprint wake-up operation, wake up the voice assistant of the electronic device according to the preset wake-up parameter.

Here, by waking up the voice assistant of the electronic device, the voice assistant can perform voice interaction with the user, so that the user can make the electronic device perform corresponding operations through voice commands in a driving situation.

In the embodiment of the present application, firstly, in response to the received preset operation, it is determined that the electronic device enters the driving scenario; in the driving scenario, the preset wake-up parameter matching the driving scenario is determined; and the wake-up operation in response to the voiceprint , According to the preset wake-up parameters, wake up the voice assistant of the electronic device; in this way, when the system recognizes that it is in a driving situation, the preset wake-up threshold and voiceprint threshold can be adjusted to greatly increase the wake-up rate.

FIG. 2 is an optional flowchart of the voiceprint wake-up method provided by an embodiment of the application. As shown in FIG. 2, the method includes at least the following steps:

Step S210: Determine that the electronic device enters a preset scene mode according to the surrounding environment information where the electronic device is located.

Here, the surrounding environment information includes information such as multi-user interaction status, moving speed, background music, and environmental noise.

Here, the preset scene modes include driving mode, audio and video mode, conference mode, game entertainment mode, and so on. It is understandable that electronic devices such as mobile phones and tablet computers are generally pre-set with multiple scene modes. Different scene modes provide functions, human-computer interaction, and displayed interfaces corresponding to the scene, so as to facilitate electronic device users in the Various operations of electronic equipment can still be performed in the scene.

In some embodiments, an application program may be provided in the electronic device to detect the current scene mode. For example, after the electronic device detects the current scene mode by using the application program, it can determine whether the current scene mode is a driving mode. Alternatively, it can also be set directly in the application layer of the driving mode. When the electronic device enters the driving mode, the application layer of the driving mode sends out a notification to enter the mode, which is not limited here.

Step S220: Adjust the default wake-up parameter of the electronic device to a preset wake-up parameter matching the preset scene mode.

Here, when the electronic device enables the preset scene mode, the application layer of the preset scene mode can send a notification to the module that performs the voiceprint wake-up operation, and the voiceprint wake-up module can automatically adjust the default wake-up parameters to the preset scene mode. Matching preset wake-up parameters.

In some embodiments, a mapping relationship between different preset scene modes and wake-up parameters can be established. When it is determined that the electronic device enters a certain preset scene mode, the preset scene mode and the corresponding preset can be obtained from the mapping relationship. Set the wake-up parameters and automatically adjust the default wake-up parameters to the preset wake-up parameters that match the preset scene mode.

Step S230: Receive the input voice signal.

Here, the voice signal is a voice command including a wake-up word, and the voice signal input by the user can be collected through the recording function on the electronic device.

Step S240: Determine the wake-up value and voiceprint characteristics of the voice signal.

Here, the wake-up value may be the similarity between the wake-up word input by the user's voice and the set fixed wake-up word; the voiceprint feature is the personality information in the voice signal, which may characterize the personal identity of the user.

In some embodiments, the voice signal may be converted to obtain the corresponding text information, and then semantic recognition is performed on the text information to determine the wake-up word of the voice signal, and compare the wake-up word with the set fixed wake-up The similarity between words is used to obtain the wake-up value of the voice signal.

In some embodiments, voiceprint recognition may be used to extract feature parameters of the voice signal to obtain the voiceprint feature, which can be further compared with the sample voiceprint feature stored in the electronic device to determine whether it is a wake-up of a specific user.

Step S250, in the case that the wake-up value is greater than the preset wake-up threshold, and the voiceprint feature is greater than the preset voiceprint threshold, wake up the application to be awakened.

Here, the voice signal input by the user through voice needs to meet the preset wakeup threshold and the preset voiceprint threshold to wake up the application to be awakened. For example, the wake-up value of the voice signal is greater than the preset wake-up threshold, and the voiceprint feature of the voice signal is greater than the preset voiceprint threshold. Therefore, when the default wake-up threshold is reduced, the user can wake up applications such as the voice assistant more accurately, and the wake-up interaction efficiency between the user and the electronic device is improved.

In some embodiments, the voiceprint feature may be extracted from the voice signal input by the user first, and the extracted voiceprint feature may be matched with a preset voiceprint feature to determine whether the user currently inputting the voice signal has a specific user with wake-up authority If yes, then determine whether there is a word with a wake-up value of voice recognition higher than the wake-up threshold in the current input voice signal, which is the wake-up word of the specific user; if yes, trigger the voiceprint wake-up module to wake up the application to be waked up, otherwise it will not wake up Wait to wake up the application. In this way, the user is identified in combination with voiceprint characteristics, and the wakeup threshold is adjusted to optimize the user's wakeup success rate and false wakeup rate.

In some embodiments, the above step S240 "determine the wake-up value and voiceprint characteristics of the voice signal" can be implemented through the following process:

Step S2401: Determine the similarity between the voice signal and a preset wake-up word, and use the similarity as the wake-up value of the voice signal.

Here, the preset wake-up words can be stored in the electronic device in advance. When the voice signal input by the user is received, the voice signal can be converted to obtain the corresponding text information, and then semantic recognition can be performed to obtain the wake-up word input by the user , And match the wake-up word with the preset wake-up word, and obtain the matching similarity as the wake-up value corresponding to the voice signal.

Step S2403: Perform voiceprint recognition on the input voice signal to obtain voiceprint features.

Here, the voiceprint recognition is performed on the voice signal input by the user, and the voiceprint feature is extracted to further match the extracted voiceprint feature with a preset voiceprint threshold to determine whether the user currently inputting the voice signal has a specific user with wake-up authority .

In the embodiment of the present application, the electronic device is determined to enter the preset scene mode based on the surrounding environment information where the electronic device is located, and the current wake-up threshold and voiceprint threshold of the electronic device are adjusted to a preset matching the preset scene mode The wake-up threshold and voiceprint threshold can automatically adjust the wake-up and voiceprint thresholds according to the current scene, increase the user's wake-up rate, and enhance the user experience.

FIG. 3 is an optional flowchart of the voiceprint wake-up method provided by the embodiment of the present application. As shown in FIG. 3, in the above step S110, "determine the preset wake-up parameter matching the current scene according to the preset condition", and it can also Through the following steps:

Step S310: Monitor current operation information.

Step S320, in a case where the current operation information satisfies a preset operation, determine the current scene in which the electronic device is located.

Here, the implementation process can include at least the following steps:

Step S3201: When the current operation information satisfies the first preset operation, it is determined that the electronic device enters the driving scenario.

Here, the first preset operation includes at least one of the following operations: turning on the interface switch, inputting a first preset voice command, connecting to the car Bluetooth and connecting to a specific Bluetooth device, wherein the first preset voice command includes turning on Driving mode or enter driving mode.

Step S3202: In a case where the current operation information satisfies a second preset operation, it is determined that the electronic device exits the driving scenario.

Here, the second preset operation includes at least one of the following operations: turning off the interface switch, inputting a second preset voice command, disconnecting the car Bluetooth, and disconnecting the specific Bluetooth device, wherein the The second preset voice command includes turning off the driving mode or exiting the driving mode.

Step S330: Adjust the default wake-up parameter of the electronic device to a preset wake-up parameter matching the current scene.

Further, in the case that the electronic device enters the driving scenario, wake up the application to be awakened according to the preset wake-up parameter, or, in the case that the electronic device exits the driving scenario, According to the default wake-up parameter, wake up the application to be waked up.

In the following, an exemplary application of the embodiment of the present application in an actual application scenario will be described.

The embodiment of the present application provides a method for improving the voiceprint awakening rate in a driving scenario, which is applied to an electronic device. FIG. 4A is a logical block diagram of improving the voiceprint awakening rate in a driving scenario provided by an embodiment of the present application, as shown in FIG. 4A. The method includes four modules: an interactive interface module 41, a voice assistant module 42, a Bluetooth module 43, and a voiceprint wake-up module 44. The first three modules provide services for the voiceprint wake-up module 44 to comprehensively determine whether the electronic device enters the driving situation. Then in the driving situation, the voiceprint wake-up module 44 is triggered to enter the driving mode, and the voiceprint wake-up module 44 automatically adjusts the wake-up threshold of the voiceprint wake-up algorithm and the voiceprint threshold to the preset value of the driving mode, and according to the preset value of the driving mode Value, wake up the voice assistant module 42; similarly, after detecting that the electronic device exits the driving scenario, the wake-up threshold of the voiceprint wake-up algorithm and the voiceprint threshold are automatically restored to the original preset values, thereby increasing the wake-up rate of the user's voiceprint wake-up. Improve user experience.

FIG. 4B is a schematic diagram of a voiceprint monitoring process in a non-driving mode provided by an embodiment of the application. As shown in FIG. 4B, it includes the following steps:

In step S410, it is judged whether the electronic device enters the driving scene.

Here, the interactive interface module, voice assistant module or Bluetooth module can be used to determine whether the electronic device enters the driving scenario.

For example, in response to the user's interface switch, or voice command, such as "open driving mode" or "enter driving mode", or connect the car Bluetooth or connect to the user-specified Bluetooth device, it is determined that the electronic device has entered the driving situation; otherwise, it is determined as The electronic device does not enter the driving situation.

In step S420, the voiceprint wake-up module is adjusted to enter the driving mode.

Here, after the voiceprint wake-up module detects that the electronic device enters the driving scenario, it automatically enters the driving mode;

In step S430, the voiceprint wake-up module is adjusted to maintain the default mode.

Here, when the voiceprint wake-up module detects that the electronic device has not entered the driving situation, the voiceprint wake-up module remains in the default mode, that is, the original non-driving mode, and does not enter the driving mode.

Step S440: Adjust the wake-up threshold and the voiceprint threshold to the preset values of the driving mode.

After the voiceprint wake-up module enters the driving mode, it automatically adjusts the wakeup threshold and the voiceprint threshold to the preset values of the driving mode.

Here, the wake-up threshold and voiceprint threshold of the voiceprint wake-up algorithm are fixed original preset values in non-driving mode. After entering the driving mode, the wake-up threshold and voiceprint threshold are automatically adjusted to the preset values of the driving mode.

Under normal circumstances, when the electronic device enters the driving situation, it means that the voice assistant is basically used in the driving position. At this time, the user who uses the electronic device has relatively little interference from other people around, which means that the false wake-up rate of others is very high. few. At this time, the user's core demand is that the wake-up response is more sensitive, that is, the wake-up rate is high. Therefore, when the system recognizes that the electronic device is in a driving situation, the wakeup threshold and the voiceprint threshold can be reduced, thereby greatly improving the wakeup rate.

Further, the electronic device performs a voiceprint wake-up operation in the driving mode, the voiceprint wake-up module wakes up the voice assistant according to the preset value of the driving mode, and then the voice assistant interacts with the user according to the received voice command.

For example, the following shows the objective test data before and after the voiceprint wakeup module adjusts the wakeup threshold and the voiceprint threshold after detecting that the electronic device enters the driving situation. Since it is a test for a specific driver, the voiceprint threshold can be fixed as relative For lower values, Table 1 is the test data before lowering the wake-up threshold, and Table 2 is the test data after lowering the wake-up threshold, where the lower the wake-up threshold is 0.05:

Table 1 Test data before lowering the wake-up threshold

驾驶情景Driving situation	声纹唤醒率Voiceprint awakening rate
车速80km/hSpeed 80km/h	83.80％83.80%
车速80km/h且开启音乐模式Speed 80km/h and turn on music mode	77.20％77.20%

Table 2 Test data after lowering the wake-up threshold

驾驶情景Driving situation	声纹唤醒率Voiceprint awakening rate
车速80km/hSpeed 80km/h	96.04％96.04%
车速80km/h且开启音乐模式Speed 80km/h and turn on music mode	97.08％97.08%

According to Table 1 and Table 2, it can be seen that for a specific user, the voiceprint threshold is fixed to a very low value, and then the wakeup threshold is reduced by 0.05 on the basis of the original wakeup threshold, which can increase the voiceprint wakeup rate in driving scenarios by more than a dozen Percentage points: For example, in a driving scenario with a vehicle speed of 80km/h, the voiceprint wake-up rate can be increased from 83.80% to 96.04%; in a driving scenario with a vehicle speed of 80km/h and the music mode is turned on, the voiceprint wake-up rate can be increased from 77.20 % Increased to 97.08%. That is to say, after detecting that the electronic device enters the driving mode, the wake-up threshold of the voiceprint wake-up algorithm and the voiceprint threshold are automatically adjusted to the preset values of the driving mode, which can significantly improve the user's voiceprint wake-up rate in the driving mode. Improve user experience.

FIG. 4C is a schematic diagram of the voiceprint monitoring process in the driving mode provided by an embodiment of the application. As shown in FIG. 4C, it includes the following steps:

In step S450, it is determined whether the electronic device exits the driving scenario.

Here, the user interaction interface module, voice assistant module, or Bluetooth module on the electronic device can be used to determine whether the electronic device exits the driving scenario.

For example, in response to the interface switch receiving operation instructions, or voice instructions, such as "turn off driving mode" or "exit driving mode", or disconnect the car Bluetooth or disconnect the Bluetooth device designated by the user, it is determined that the electronic device has exited the driving scenario.

In step S460, the voiceprint wake-up module is adjusted to exit the driving mode.

Here, after the voiceprint wake-up module detects that the electronic device exits the driving scenario, it automatically exits the driving mode;

In step S470, the voiceprint wake-up module is adjusted to maintain the driving mode.

Here, in the case that the voiceprint wakeup module detects that the electronic device has not exited the driving scenario, the voiceprint wakeup module remains in the driving mode without exiting.

Step S480, adjusting the wake-up threshold and the voiceprint threshold to the original preset values.

Here, after the voiceprint wake-up module exits the driving mode, the wake-up threshold and the voiceprint threshold of the voiceprint wake-up algorithm are automatically restored to the original preset values.

The voiceprint wake-up method provided by the embodiments of the application automatically enters the driving mode according to the user's voice command or interface operation or when connecting to the car Bluetooth or connecting to the user-specified Bluetooth device, and then automatically adjusts the voiceprint after detecting that the electronic device enters the driving mode The wake-up threshold and voiceprint threshold of the wake-up algorithm are the preset values of the driving mode, which improves the wake-up rate of the user's voiceprint wake-up; after detecting that the electronic device exits the driving mode, the wake-up threshold and voiceprint threshold of the voiceprint wake-up algorithm are automatically restored The original preset value can accurately determine the state of the user's driving situation. In the driving situation, it will automatically enter the driving mode; and after entering the driving mode, the wake-up and voiceprint thresholds will be automatically adjusted to increase the user's wake-up rate and enhance the user experience.

The embodiment of the present application provides a voiceprint wake-up device, which includes each module included and each unit included in each module, which can be implemented by a processor in an electronic device; of course, it can also be implemented by a logic circuit; In the implementation process, the processor can be a central processing unit (CPU), a microprocessor (Micro Processing Unit, MPU), a digital signal processor (Digital Signal Processor, DSP), or a field programmable gate array ( Field Programmable Gate Array, FPGA), etc.

FIG. 5A is a schematic diagram of the composition structure of a voiceprint wake-up device provided by an embodiment of the application. As shown in FIG. 5A, the device 500a includes a first determination module 501a and a first wake-up module 502a, wherein:

The first determining module 501a is configured to determine a preset wake-up parameter matching the current scene according to preset conditions;

The first wake-up module 502a is configured to wake up the application to be awakened according to the preset wake-up parameter in response to the voiceprint wake-up operation.

In some embodiments, the first determining module 501a includes a first determining unit and a first adjusting unit, wherein: the first determining unit is configured to determine the The electronic device enters a preset scene mode; the first adjustment unit is configured to adjust the current wake-up parameter of the electronic device to a preset wake-up parameter matching the preset scene mode.

In some embodiments, the first determining module 501a includes a monitoring unit, a second determining unit, and a second adjusting unit, wherein: the monitoring unit is configured to monitor current operation information; the second determining unit is configured to When the current operation information satisfies the preset operation, determine the current scene in which the electronic device is located; the second adjustment unit is configured to adjust the default wake-up parameter of the electronic device to match the current scene The preset wake-up parameters.

In some embodiments, the second determining unit is further configured to determine that the electronic device enters the driving scenario when the current operation information satisfies a first preset operation; wherein, the first preset operation is at least It includes one of the following operations: turning on an interface switch, inputting a first preset voice command, connecting a car Bluetooth and connecting a specific Bluetooth device, and the first preset voice command includes turning on the driving mode or entering the driving mode.

In some embodiments, the second determining unit is further configured to determine that the electronic device exits the driving scenario when the current operation information satisfies a second preset operation; wherein, the second preset The operation includes at least one of the following operations: turning off the interface switch, inputting a second preset voice command, disconnecting the car Bluetooth and disconnecting the specific Bluetooth device, the second preset voice command including turning off the driving mode Or exit driving mode.

In some embodiments, the device 500a further includes a second wake-up module configured to wake up the application to be awakened according to the preset wake-up parameter when the electronic device enters the driving scenario; Or when the electronic device exits the driving scenario, wake up the application to be awakened according to the default wake-up parameter.

In some embodiments, the first wake-up module 502a includes a receiving unit, a third determining unit, and a wake-up unit, wherein: the receiving unit is configured to receive an input voice signal; the third determining unit is configured to determine The wake-up value and voiceprint feature of the voice signal; the voiceprint recognition unit is configured to be in the case where the wake-up value is greater than the preset wake-up threshold, and the voiceprint feature is greater than the preset voiceprint threshold Next, wake up the application to be awakened.

In some embodiments, the third determining unit is further configured to determine the similarity between the voice signal and a preset wake-up word, and use the similarity as the wake-up value of the voice signal; Perform voiceprint recognition on the voice signal to obtain voiceprint features.

It should be pointed out here that the description of the above device embodiment is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the device embodiments of the present application, please refer to the description of the method embodiments of the present application for understanding.

The embodiment of the present application provides a voiceprint wake-up device, which includes each module included and each unit included in each module, which can be implemented by a processor in an electronic device; of course, it can also be implemented by a logic circuit; In the implementation process, the processor may be a central processing unit, a microprocessor, a digital signal processor, or a field programmable gate array.

FIG. 5B is a schematic diagram of the composition structure of a voiceprint wake-up device provided by an embodiment of the application. As shown in FIG. 5B, the device 500b includes a second determination module 501b, a third determination module 502b, and a third wake-up module 503b. :

The second determining module 501b is configured to determine that the electronic device enters the driving scenario in response to receiving a preset operation of waking up the application to be awakened;

The third determining module 502b is configured to determine a preset wake-up parameter matching the driving scenario under the driving scenario;

The third wake-up module 503b is configured to wake up the voice assistant of the electronic device according to the preset wake-up parameter in response to the voiceprint wake-up operation.

The preset operation includes at least one of the following: turning on an interface switch, inputting a first preset voice command, connecting a car Bluetooth and connecting a specific Bluetooth device, wherein the first preset voice command includes turning on driving mode or entering driving model.

It should be noted that, in the embodiments of the present application, if the above voiceprint wake-up method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application can be embodied in the form of software products in essence or the parts that contribute to related technologies. The computer software products are stored in a storage medium and include several instructions to enable The automatic test line of the device containing the storage medium executes all or part of the method described in each embodiment of the present application. The aforementioned storage media include: U disk, mobile hard disk, read only memory (Read Only Memory, ROM), magnetic disk or optical disk and other media that can store program codes.

Correspondingly, an embodiment of the present application provides an electronic device. FIG. 6 is a schematic diagram of the hardware entity of the electronic device provided by an embodiment of the application. As shown in FIG. 6, the hardware entity of the device 600 includes: a processor 601 and a communication interface 602 And memory 603, where

The processor 601 generally controls the overall operation of the device 600.

The communication interface 602 can enable the device 600 to communicate with other electronic devices or servers through a network.

The memory 603 is configured to store instructions and applications executable by the processor 601, and can also cache data to be processed or processed by the processor 601 and each module in the device 600 (for example, image data, audio data, voice communication data, and video data). Communication data) can be realized by flash memory (FLASH) or random access memory (Random Access Memory, RAM).

Correspondingly, an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps in the voiceprint wake-up method provided in the above-mentioned embodiments are implemented.

It should be pointed out here that the description of the above storage medium and device embodiments is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the storage medium and device embodiments of this application, please refer to the description of the method embodiments of this application for understanding.

It should be understood that “one embodiment” or “an embodiment” mentioned throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of the present application. Therefore, the appearances of "in one embodiment" or "in an embodiment" in various places throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in the various embodiments of the present application, the size of the sequence number of the above-mentioned processes does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not correspond to the embodiments of the present application. The implementation process constitutes any limitation. The serial numbers of the foregoing embodiments of the present application are for description only, and do not represent the superiority or inferiority of the embodiments.

It should be noted that in this article, the terms "include", "include" 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 not only includes those elements, It also includes other elements that are not explicitly listed, or elements inherent to the process, method, article, or device. If there are no more restrictions, the element defined by the sentence "including a..." does not exclude the existence of other identical elements in the process, method, article, or device that includes the element.

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

The units described above as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units; 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 objectives of the solutions of the embodiments of the present application. In addition, the functional units in the embodiments of the present application can be all integrated into one processing unit, or each unit can be individually used as a unit, or two or more units can be integrated into one unit; The unit can be implemented in the form of hardware, or in the form of hardware plus software functional units.

Alternatively, if the aforementioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it may also be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application can be embodied in the form of software products in essence or the parts that contribute to related technologies. The computer software products are stored in a storage medium and include several instructions to enable The equipment automatic test line executes all or part of the methods described in the various embodiments of the present application. The aforementioned storage media include: removable storage devices, ROMs, magnetic disks, or optical disks and other media that can store program codes.

The methods disclosed in the several method embodiments provided in this application can be combined arbitrarily without conflict to obtain new method embodiments. The features disclosed in the several method or device embodiments provided in this application can be combined arbitrarily without conflict to obtain a new method embodiment or device embodiment.

The above are only the implementation manners of this application, but the protection scope of this application is not limited to this. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application. Covered in the scope of protection of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Industrial applicability

In the embodiment of the present application, the preset wake-up parameters that match the current scene are first determined according to preset conditions; wherein the preset wake-up parameters include a preset wake-up threshold and a preset voiceprint threshold; then, in response to the voiceprint wake-up operation, The application program to be awakened is awakened according to the preset wake-up parameters; in this way, the wake-up and voiceprint thresholds can be automatically adjusted according to the current scene, which improves the user's wake-up rate and enhances the user experience.

Claims

A voiceprint wake-up method, applied to an electronic device, and the method includes:

Determine a preset wake-up parameter matching the current scene according to preset conditions; wherein the preset wake-up parameter is used to characterize the wake-up threshold and the voiceprint threshold that meet the wake-up requirements;

In response to the voiceprint wake-up operation, the application program to be awakened is awakened according to the preset wake-up parameter.
The method of claim 1, wherein the determining a preset wake-up parameter matching the current scene according to a preset condition comprises:

Determining that the electronic device enters a preset scene mode according to the surrounding environment information where the electronic device is located;

The default wake-up parameter of the electronic device is adjusted to a preset wake-up parameter matching the preset scene mode.
The method of claim 1, wherein the determining a preset wake-up parameter matching the current scene according to a preset condition comprises:

Monitor current operation information;

If the current operation information satisfies a preset operation, determine the current scene where the electronic device is located;

The default wake-up parameter of the electronic device is adjusted to a preset wake-up parameter matching the current scene.
The method according to claim 3, wherein the determining the current scene where the electronic device is located when the current operation information satisfies a preset operation comprises:

In a case where the current operation information satisfies the first preset operation, determining that the electronic device enters the driving scenario;

Wherein, the first preset operation includes at least one of the following operations: turning on the interface switch, inputting a first preset voice command, connecting the car Bluetooth and connecting a specific Bluetooth device, and the first preset voice command includes turning on the driving mode Or enter driving mode.
The method of claim 4, wherein the method further comprises:

In a case where the current operation information satisfies the second preset operation, determining that the electronic device exits the driving scenario;

Wherein, the second preset operation includes at least one of the following operations: turning off the interface switch, inputting a second preset voice command, disconnecting the car Bluetooth and disconnecting the specific Bluetooth device, the second The preset voice commands include turning off the driving mode or exiting the driving mode.
The method according to claims 3 to 5, wherein the method further comprises:

When the electronic device enters the driving scenario, wake up the application to be awakened according to the preset wake-up parameter; or

When the electronic device exits the driving scenario, wake up the application to be awakened according to the default wake-up parameter.
The method according to any one of claims 1 to 5, wherein the preset wake-up parameters include a preset wake-up threshold and a preset voiceprint threshold,

The waking up the application program to be awakened in response to the voiceprint wake-up operation according to the preset wake-up parameter includes:

Receive input voice signal;

Determining the wake-up value and voiceprint characteristics of the voice signal;

In a case where the wake-up value is greater than the preset wake-up threshold, and the voiceprint feature is greater than the preset voiceprint threshold, wake up the application to be awakened.
The method according to claim 7, wherein the determining the wake-up value and voiceprint characteristics of the voice signal comprises:

Determine the similarity between the voice signal and a preset wake-up word, and use the similarity as the wake-up value of the voice signal;

Perform voiceprint recognition on the input voice signal to obtain voiceprint features.
A voiceprint wake-up method, the method includes:

In response to the received preset operation, it is determined that the electronic device enters the driving scenario;

In the driving scenario, determining a preset wake-up parameter matching the driving scenario; wherein the preset wake-up parameter is used to characterize the wake-up threshold and the voiceprint threshold that meet the wake-up requirements;

In response to the voiceprint wake-up operation, wake up the voice assistant of the electronic device according to the preset wake-up parameter.
9. The method of claim 9, wherein the preset operation includes at least one of the following:

Turn on the interface switch, input the first preset voice instruction, connect the car Bluetooth and connect to a specific Bluetooth device, wherein the first preset voice instruction includes turning on the driving mode or entering the driving mode.
A voiceprint wake-up device, the device includes a first determination module and a first wake-up module, wherein:

The first determining module is configured to determine a preset wake-up parameter matching the current scene according to a preset condition; wherein the preset wake-up parameter is used to characterize a wake-up threshold and/or a voiceprint threshold that meets a wake-up requirement;

The first wake-up module is configured to, in response to the voiceprint wake-up operation, wake up the application to be awakened according to the preset wake-up parameter. In response to the voiceprint wake-up operation, the application to be woken up according to the preset wake-up parameter The program wakes up.
The apparatus of claim 11, wherein the first determining module comprises:

The first determining unit is configured to determine that the electronic device enters a preset scene mode according to the surrounding environment information where the electronic device is located;

The first adjustment unit is configured to adjust the current wake-up parameter of the electronic device to a preset wake-up parameter matching the preset scene mode.
The apparatus of claim 11, wherein the first determining module comprises:

The monitoring unit is configured to monitor current operation information;

The second determining unit is configured to determine the current scene where the electronic device is located when the current operation information satisfies a preset operation;

The second adjustment unit is configured to adjust the default wake-up parameter of the electronic device to a preset wake-up parameter matching the current scene.
The apparatus according to claim 13, wherein the second determining unit is further configured to determine that the electronic device enters the driving scenario when the current operation information satisfies the first preset operation;

The first preset operation includes at least one of the following operations: turning on the interface switch, inputting a first preset voice command, connecting to the car Bluetooth and connecting to a specific Bluetooth device, and the first preset voice command includes turning on the driving mode or entering Driving mode.
The apparatus of claim 14, wherein the second determining unit is further configured to determine that the electronic device exits the driving scenario when the current operation information satisfies a second preset operation;

The second preset operation includes at least one of the following operations: turning off the interface switch, inputting a second preset voice command, disconnecting the car Bluetooth and disconnecting the specific Bluetooth device, the second preset Voice commands include turning off driving mode or exiting driving mode.
The device according to claims 13-15, wherein the device further comprises:

The second wake-up module is configured to wake up the application to be awakened according to the preset wake-up parameters when the electronic device enters the driving scenario; or when the electronic device exits the driving scenario In this case, the application program to be awakened is awakened according to the default awakening parameter.
The device according to any one of claims 11 to 15, wherein the first wake-up module comprises:

A receiving unit, configured to receive an input voice signal;

The third determining unit is configured to determine the wake-up value and voiceprint characteristics of the voice signal;

The voiceprint recognition unit is configured to wake up the application to be awakened when the wakeup value is greater than the preset wakeup threshold and the voiceprint feature is greater than the preset voiceprint threshold.
17. The apparatus of claim 17, wherein the third determining unit is further configured to determine the similarity between the voice signal and a preset wake-up word, and use the similarity as the wake-up value of the voice signal ; Perform voiceprint recognition on the input voice signal to obtain voiceprint features.
A voiceprint wake-up device, the device includes a second determination module, a third determination module, and a third wake-up module, wherein:

The second determining module is configured to determine that the electronic device enters the driving scenario in response to receiving a preset operation of waking up the application to be awakened;

The third determination module is configured to determine a preset wake-up parameter matching the driving scenario under the driving scenario; wherein the preset wake-up parameter is used to characterize a wake-up threshold and/or sound that meets the wake-up requirement. Pattern threshold

The third wake-up module is configured to wake up the voice assistant of the electronic device according to the preset wake-up parameter in response to the voiceprint wake-up operation.
An electronic device includes a memory and a processor, the memory stores a computer program that can run on the processor, and when the computer program is executed by the processor, the processor performs the following operations:

Acquiring a preset wake-up parameter matching the current scene; wherein the preset wake-up parameter is used to characterize the wake-up threshold and/or the voiceprint threshold that meets the wake-up requirement;

In response to the voiceprint wake-up operation, the application program to be awakened is awakened according to the preset wake-up parameter.
A computer-readable storage medium with a computer program stored thereon, which, when executed by a processor, implements the steps in the method described in any one of claims 1 to 8, or implements the steps described in claim 9 or 10 Steps in the method.