WO2019041512A1

WO2019041512A1 - Method and device for enabling voice recognition function of terminal, earphone and terminal

Info

Publication number: WO2019041512A1
Application number: PCT/CN2017/108583
Authority: WO
Inventors: 陈大鹏
Original assignee: 歌尔科技有限公司
Priority date: 2017-08-29
Filing date: 2017-10-31
Publication date: 2019-03-07
Also published as: CN107393535A

Abstract

Disclosed is a method for enabling a voice recognition function of a terminal by means of an earphone, comprising: collecting voice; and when it is determined that a preset keyword is comprised in the voice, sending an enabling instruction for enabling the voice recognition function to the terminal so as to make the terminal perform voice recognition. Therefore, by adopting the method, the enabling instruction for enabling the voice recognition function can be sent to the terminal only by means of the voice comprising the preset keyword without manual operations to enable the voice recognition function of the terminal so as to perform voice recognition when the voice recognition function of the terminal is in a closed state, so that the power consumption of the terminal itself is reduced, the convenience of using the voice recognition function of a user is improved, and user experience is improved. In addition, also disclosed are a device for enabling the voice recognition function of the terminal by means of the earphone, the earphone, the method and the device for enabling the voice recognition function of the terminal, and the terminal. The advantages are stated as above.

Description

Method, device, earphone and terminal for opening terminal voice recognition function

cross reference

The present application is hereby incorporated by reference in its entirety in its entirety in its entirety in its entirety in its entirety in the the the the the the the the the the the the the the the the

Technical field

The present invention relates to the field of voice recognition technology, and in particular, to a method, device, earphone and terminal for enabling a voice recognition function of a terminal.

Background technique

With the development of electronic technology and speech recognition technology, more and more terminals have voice recognition functions, such as mobile phones.

Although the above terminal has a voice recognition function, the use convenience of the terminal can be improved to some extent. However, since the voice recognition function of the terminal is turned on, the terminal continues to actively acquire the voice in real time through the microphone regardless of whether the user is using the function. The sound in the surrounding environment, and when the intensity of the acquired sound is greater than the threshold, the acquired voice is recognized, so if the voice recognition function of the holding terminal is in the normally open state, a large amount of energy loss is caused. In addition, the terminal has its own energy limitation. Therefore, the existing terminal with voice recognition function mostly keeps the function in the normally closed state. Only after the user manually turns on the function through physical buttons or virtual buttons, the user can normally Use this feature.

The physical button not only occupies the space of the terminal, but also increases the terminal volume, which leads to the terminal not being carried, and it is easy to malfunction due to multiple physical pressing, which affects the user's use, thereby reducing the user's experience. Moreover, when the user's hands are occupied, they cannot pass physical buttons or virtual buttons. Manually turning on the voice recognition function of the terminal further affects the user's use. Of course, in order to prevent the voice recognition function of the terminal from being opened for the voice recognition when the two hands are occupied, the user may also choose to keep the voice recognition function of the terminal normally open. However, as described above, due to the limited energy of the terminal, the function is In the case of a large loss of the terminal's own energy, it is easy to cause the terminal to have insufficient power and affect the use of the terminal, further affecting the use of the function.

Therefore, how to improve the convenience of using the voice recognition function and further improve the user experience is a technical problem that a person skilled in the art needs to solve in the case of saving the power consumption of the terminal itself.

Summary of the invention

An object of the present invention is to provide a method, a device, an earphone and a terminal for enabling a voice recognition function of a terminal, which can improve the convenience of use of the voice recognition function and further improve the user experience.

In order to solve the above technical problem, the present invention provides a method for opening a voice recognition function of a terminal through a headset, and the method for enabling a voice recognition function of a terminal through a headset includes:

Collecting speech;

When it is determined that the preset keyword is included in the voice, an open command for turning on the voice recognition function is sent to the terminal to enable the terminal to perform voice recognition.

Preferably, after the sending the opening instruction of the voice recognition function to the terminal, the method for opening the voice recognition function of the terminal through the earphone further includes:

Responding to a request initiated by the terminal to establish a voice transmission link;

When it is detected that the voice transmission link is turned on, voice can be transmitted to the terminal through the voice transmission link.

Preferably, the method for enabling the terminal voice recognition function by using the earphone further includes:

When detecting that the terminal closes the voice transmission link, stopping transmission of voice to the terminal through the voice transmission link.

Preferably, the opening instruction for sending the voice recognition function to the terminal is specifically:

The open command is sent to the terminal through an instruction channel based on the BLE protocol.

In order to solve the above technical problem, the present invention further provides an apparatus for enabling a voice recognition function of a terminal through a headset, and the apparatus for enabling a voice recognition function of a terminal by using a headset includes:

An acquisition module for collecting voices;

The opening module is configured to, when determining that the voice includes a preset keyword, send an open command to enable the voice recognition function to enable the terminal to perform voice recognition.

In order to solve the above technical problem, the present invention also provides an earphone, the earphone including a memory and a processor, the processor performing voice recording by using an instruction stored in the memory to perform any of the above-mentioned voice-opening through the earphone Functional method.

In order to solve the above technical problem, the present invention further provides a method for enabling a voice recognition function of a terminal, where the method for enabling a voice recognition function of the terminal includes:

Receiving an open command for turning on the voice recognition function sent by the earphone;

The speech recognition function is turned on for speech recognition.

Preferably, after the opening the voice recognition function, the method for enabling the voice recognition function of the terminal further includes:

Initiating a request to establish a voice transmission link to the headset to establish the voice transmission link;

Receiving voice transmitted by the earphone through the voice transmission link, and performing voice recognition.

Preferably, after the voice sent by the headset is received by the voice transmission link, the method for enabling the voice recognition function of the terminal further includes:

When the preset shutdown condition is reached, disconnecting the voice transmission link and turning off the voice recognition function;

The preset shutdown condition specifically includes:

The signal strength of the voice is lower than the first preset value and the duration is up to the second preset value;

Or the signal strength of the voice is higher than the third preset value, and the duration is up to the fourth preset value;

Or get a speech recognition result;

The first preset value is smaller than the third preset value.

In order to solve the above technical problem, the present invention also provides a voice recognition function for opening a terminal. The device, the device for enabling the voice recognition function of the terminal includes:

a receiving module, configured to receive an open instruction for turning on the voice recognition function sent by the earphone;

The module is turned on for turning on the voice recognition function for voice recognition.

In order to solve the above technical problem, the present invention also provides a terminal, the terminal comprising a memory and a processor, the processor performing the above-mentioned voice recognition function of the open terminal by calling an instruction stored in the memory method.

With respect to the above prior art, the method for enabling a voice recognition function of a terminal through a headset includes collecting voice, and when determining that the voice includes a preset keyword, sending an open command for turning on the voice recognition function to the terminal Make the terminal perform speech recognition. It can be seen that the method can be used in the state that the voice recognition function of the terminal is off, without manual operation, and only the voice containing the preset keyword can be used to send an open command for turning on the voice recognition function to open the voice of the terminal. The recognition function performs voice recognition. Therefore, the method provided by the present invention can perform voice recognition through the earphone and automatically turn on the voice recognition function of the terminal, so that the terminal does not need to open the voice recognition function for a long time, which can not only reduce the power consumption of the terminal, but also improve the performance. Users use the convenience of voice recognition to further enhance the user experience. In addition, the present invention also provides a device for opening a terminal voice recognition function through a headphone and an earphone, the effect is as above.

In addition, the present invention also provides a method for turning on the voice recognition function of the terminal, comprising: receiving an opening instruction of the voice recognition function sent by the earphone; and opening the voice recognition function to perform voice recognition. It can be seen that the method provided by the present invention can be used in the state that the voice recognition function of the terminal is off, without manual operation, and the terminal can open its own voice recognition function for voice recognition only by receiving an open command sent by the earphone. Compared with the prior art, the method can not only reduce the power consumption of the terminal, but also improve the convenience of the user using the voice recognition function, thereby further improving the user experience. In addition, the present invention also provides an apparatus for opening a voice recognition function of a terminal and a terminal, the effect is as above.

DRAWINGS

In order to explain the embodiments of the present invention more clearly, the drawings, which are used in the embodiments, will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the present invention. In terms of personnel, other drawings can be obtained based on these drawings without any creative work.

FIG. 1 is a flowchart of a method for enabling a voice recognition function of a terminal through a headset according to an embodiment of the present invention;

2 is a flowchart of another method for enabling a voice recognition function of a terminal through a headset according to an embodiment of the present invention;

FIG. 3 is a flowchart of another method for enabling a voice recognition function of a terminal through a headset according to an embodiment of the present invention;

FIG. 4 is a structural diagram of an apparatus for enabling a voice recognition function of a terminal through a headset according to an embodiment of the present invention;

FIG. 5 is a flowchart of a method for enabling a voice recognition function of a terminal according to an embodiment of the present invention;

FIG. 6 is a flowchart of another method for enabling a voice recognition function of a terminal according to an embodiment of the present invention;

FIG. 7 is a flowchart of another method for enabling a voice recognition function of a terminal according to an embodiment of the present invention;

FIG. 8 is a structural diagram of an apparatus for enabling a voice recognition function of a terminal according to an embodiment of the present invention;

FIG. 9 is a schematic diagram of an application scenario of a headset and a terminal according to an embodiment of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present invention. It is obvious that the described embodiments are only a part of the embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, those of ordinary skill in the art are not paying All other embodiments obtained under the premise of creative labor are within the scope of the present invention.

An object of the present invention is to provide a method for voice recognition, which can improve the convenience of a user using a voice recognition function, thereby improving the user experience.

The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

It should be noted that the earphone mentioned in the present invention needs to establish a communication connection with the terminal, and the communication module required for establishing the communication connection may be a Bluetooth module or another type of communication module, as long as the communication module of the earphone and the terminal matches. . In addition, the terminal can be other types of electronic products such as mobile phones.

FIG. 1 is a flowchart of a method for enabling a voice recognition function of a terminal through a headset according to an embodiment of the present invention. As shown in Figure 1, the method includes:

S10: Collecting voice.

S11: When it is determined that the preset keyword is included in the voice, the terminal sends an open command for turning on the voice recognition function to enable the terminal to perform voice recognition.

In a specific implementation, the voice collection module of the earphone collects the voice input by the user in real time, and then the local voice recognition module identifies whether the collected voice includes a preset keyword, and if yes, sends an open command to the terminal.

It should be noted that the specific process of the headset recognizing the preset keyword is: converting the collected voice into text, and then comparing the text with the text of the preset keyword in the database, if the text includes If the text of the preset keyword has the same text, it is determined that the voice collected by the earphone includes a preset keyword. If there is no text in the text that is the same as the preset keyword, it is determined that there is no preset key in the voice collected by the earphone. word.

The preset keyword mentioned in step S11 refers to a keyword that turns on the voice recognition function of the terminal. Moreover, it can be understood that the content of the preset keyword is not limited, and may be letters, numbers, Chinese, etc. The more content included in the preset keyword, the slower the recognition process, but the error can be effectively prevented. The operation can be selected according to the actual situation, and the invention is not limited.

For example, if the default keyword is "turn on speech recognition", then when the user says "I am to the headset" When the voice recognition function is turned on (the voice includes the preset keyword "turn on the voice recognition function"), the first voice collection module of the earphone collects the voice spoken by the user to the earphone, and is performed by the earphone. The local voice recognition module identifies the voice, and finally determines that the voice includes a preset keyword (the preset keyword is “turning on the voice recognition function”), and sends an open command for turning on the voice recognition function to the terminal, then the terminal receives the voice. After the command is turned on, the voice recognition function is turned on for voice recognition.

Certainly, in a specific implementation, the preset keyword for enabling the voice recognition function may be one or more, and if there are multiple preset keywords, the database includes texts of multiple preset keywords. Then, the user inputs a voice containing any preset keyword to achieve the purpose of turning on the terminal voice recognition function. In addition, in a specific implementation, two preset keywords may be set to respectively represent keywords of the local voice recognition function of the terminal and keywords of the network voice recognition function of the terminal. Correspondingly, the open command carries corresponding information, for example, the head of the data corresponding to the open command is set to 1, indicating that the terminal local voice recognition function is adopted; the head of the data corresponding to the open command is set to 0, and the network is adopted. Speech recognition. Specifically, when the headset receives the keyword that includes the local voice recognition function of the terminal, the terminal sends an open command for opening the local voice recognition function of the terminal; when the headset receives the key of the network voice recognition function including the enabled terminal In the case of a word, an open command to turn on the network voice recognition function of the terminal is sent to the terminal.

It can be seen that the method for enabling the voice recognition function of the terminal through the earphone provided by the embodiment of the present invention can be performed in the state that the voice recognition function of the terminal is off, without manual operation, and can only be transmitted to the terminal through the voice containing the preset keyword. Sending the open command of the voice recognition function to enable the voice recognition function of the terminal for voice recognition. Therefore, the method can not only reduce the power consumption of the terminal, but also improve the convenience of the user using the voice recognition function, thereby further improving the user experience.

In a specific implementation, when the user speaks the voice to be recognized far away from the terminal, the quality of the voice to be recognized obtained by the microphone of the terminal itself is poor, which may result in a decrease in the success rate of voice recognition and affect the user. Experience. Of course, the user can move the terminal to a place with a small distance from itself so that the terminal can obtain a better-quality voice to be recognized, but because of the terminal The portability is poor. When the user's hands are occupied, it is difficult for the user to ensure the distance between the user and the terminal. In view of this, the present invention considers that the earphone has better portability. As long as the user wears the earphone, even if the user speaks the voice to be recognized far away from the terminal, the terminal can collect the higher-quality voice to be recognized through the earphone. Therefore, after the headset sends an open command to the terminal, the terminal can also establish a voice transmission link with the earphone, so that the terminal can acquire the high quality to be recognized by the portable headset through the voice transmission link. voice.

FIG. 2 is a flowchart of another method for enabling a voice recognition function of a terminal through a headset according to an embodiment of the present invention. In this embodiment, the headset voice transmission link transmits the high-quality to-be-identified voice collected by the headset to the terminal, as shown in FIG. 2 . As a preferred implementation manner, after performing step S11 on the basis of FIG. :

S20: Respond to the request initiated by the terminal to establish a voice transmission link.

S21: When it is detected that the voice transmission link is connected, the voice can be transmitted to the terminal through the voice transmission link.

It should be noted that the voice transmission link refers to a transmission link between the terminal and the earphone for transmitting the voice to be recognized, and the voice mentioned in step S21 is after the voice transmission link is detected by the earphone after the opening command is sent. The voice collected at the time of the connection is the voice at the different time from the voice mentioned in the step S10. Specifically, the voice mentioned in the step S10 is the voice spoken by the user before the voice transmission link is turned on; step S21 The voice mentioned in the voice is the voice spoken by the user after the voice transmission link is connected. For example, at the current moment, the headset does not detect that the voice transmission link is turned on, and the voice collected by the headset in real time is the voice in step S10. If, at the next moment, the headset detects that the voice transmission link has been turned on, the voice collected by the headset in real time is the voice in step S21.

In a specific implementation, when the headset receives the request for the terminal to initiate a voice transmission link, the headset immediately responds to the request initiated by the terminal to establish a voice transmission link, so that the terminal establishes a voice transmission link between the two as soon as possible. And when the headset detects that the voice transmission link between itself and the terminal is connected, the headset starts to collect the voice in real time and the voice is transmitted to the terminal in real time through the voice transmission link.

However, it is worth noting that, for step S21, when the user inputs the speech to be recognized If the machine is not correct, it may cause speech recognition to fail. For example, when the user inputs the voice containing the preset keyword and immediately outputs the voice to be recognized, it is likely that the terminal has not fully turned on the voice recognition function or has not been established yet. The voice transmission link is good, and the terminal cannot obtain the voice to be recognized when the user turns on the voice recognition function and the voice transmission link is established when the terminal establishes the voice transmission link, so that the voice recognition fails. Therefore, in order to enable the user to accurately input the timing of the voice to be recognized, thereby improving the success rate of the voice recognition, thereby improving the user experience, the following manner may also be adopted in other embodiments.

As a preferred implementation manner, when the headset detects that the voice transmission link is turned on and receives the prompt command sent by the terminal, the headset plays a prompt signal to the user to start inputting the voice to be recognized to help the user accurately grasp the timing of inputting the voice to be recognized. And the earphone can transmit the voice collected by the earphone to the terminal through the voice transmission link, so that the terminal can obtain all the voices to be recognized to improve the success rate of the voice recognition, thereby improving the user experience.

It can be seen that the method provided by the embodiment can respond to the request initiated by the terminal to establish a voice transmission link by using a headset with better portability, and when the voice transmission link is detected to be connected, the earphone can be real-time through the voice transmission link. The voice collected by the user is transmitted to the terminal, so that the terminal can obtain the high-quality to-be-recognized voice through the better-capable earphone, and the terminal cannot successfully identify the user because the terminal cannot obtain the high-quality to-be-recognized voice through the microphone. The voice you want to recognize is the impact of the user experience. Therefore, the method can improve the success rate of voice recognition, thereby improving the user experience.

In a specific implementation, after the terminal successfully obtains the to-be-recognized voice or successfully obtains the recognition result, the terminal closes the voice transmission link. At this time, the earphone may stop transmitting the collected voice to the terminal to reduce the power consumption of the earphone itself. Therefore, the embodiment of the present invention provides another method for opening the voice recognition function of the terminal through the earphone, which is further improved on the basis of FIG. 2, and is described in detail below with reference to the accompanying drawings.

FIG. 3 is a flowchart of another method for enabling a voice recognition function of a terminal through a headset according to an embodiment of the present invention. As shown in FIG. 3, in order to reduce the power consumption of the earphone itself, as a preferred embodiment, On the basis of FIG. 2, after performing step S21, the method further includes:

S30: When detecting that the terminal closes the voice transmission link, stop transmitting the voice to the terminal through the voice transmission link.

It should be noted that although the voice is transmitted to the terminal through the voice transmission link in step S30, the earphone still collects voice in real time. At this time, for the earphone, the collected voice is used to determine whether or not the voice is included. Set keywords so that the user can turn on the voice recognition function of the terminal again through the voice recognition function. In addition, it should be noted that during the operation of the earphone, although the voice is collected in real time, the used voice is used for different purposes, that is, the voice collected before the open command is sent to the terminal in a complete cycle. It is used to judge whether the preset keyword is included, and after the opening command is sent to the terminal, the collected voice is used for transmission to the terminal for voice recognition. Therefore, in a specific implementation, the earphone includes two acquisition modules, which are a first acquisition module and a second collection module, and the two acquisition modules do not work at the same time.

Moreover, in order to further improve the method for the voice recognition function of the terminal to be opened by the earphone provided by the embodiment, the user's experience is improved, and after performing step S30, the earphone can also receive the audio in the recognition result sent by the terminal, and play The audio.

Of course, it can be understood that the method for opening the voice recognition function of the terminal through the earphone provided by the embodiment of the present invention can be further improved on the basis of FIG. 1 , that is, after step S11 is performed, step S30 is continued, More details will be described.

In order to reduce the power consumption of the earphone itself, as a preferred embodiment, the opening command for transmitting the voice recognition function to the terminal is specifically: sending an open command to the terminal through the command channel based on the BLE protocol. Other communication protocols may be used in addition to the BLE protocol, and are not described in this embodiment.

The foregoing provides a detailed description of an embodiment of a method for enabling a voice recognition function of a terminal through a headset, and the present invention further provides a device for enabling a voice recognition function of a terminal through a headset corresponding to the method, The embodiment of the device part and the embodiment of the method part are mutually responsive, so the embodiment of the device part can be referred to the description of the embodiment of the method part. Said.

FIG. 4 is a structural diagram of an apparatus for enabling a voice recognition function of a terminal through a headset according to an embodiment of the present invention. As shown in Figure 4, the device comprises:

The acquisition module 40 is configured to collect voice.

The opening module 41 is configured to send an opening instruction for turning on the voice recognition function to the terminal to perform voice recognition when determining that the voice includes the preset keyword.

The collection module 40 includes a first voice collection module and a second voice collection module, and the first voice collection module and the second voice collection module are used to collect voice in real time, but the voice collected by the first voice collection module is used as a headset. The voice recognized by the local voice recognition module; and the voice collected by the second voice collection module is used as the voice transmitted by the earphone to the terminal for the terminal to perform voice recognition on the voice. Generally, in order to reduce the power consumption of the earphone itself, when the earphone does not transmit voice to the terminal, only the first voice collection module is kept in an open state to collect voice in real time, so that the local voice recognition module of the earphone recognizes the first voice collection module in real time. Whether the preset voice is included in the voice, and the second voice collection module is kept in the off state. It should be noted that, in a normal case, the second voice collection module only detects the voice transmission chain after the local voice recognition module of the earphone itself recognizes that the voice collected by the first voice collection module includes a preset keyword. When the road is connected, it will be turned on, and when the second voice collection module is turned on, the first voice collection module will be turned off at the same time. Of course, if the keyword is also stored in the headset, the first voice collection module can still be kept on when the second voice collection module is turned on.

Moreover, it can be understood that when detecting that the voice transmission link has been turned off, the headset will turn off the second voice collection module to save its own power consumption, and simultaneously turn on its own first voice collection module, so that the user needs the next time. When the voice recognition function of the terminal is used, the voice recognition function of the terminal can be opened more conveniently by voice, thereby improving the user experience. However, it is worth noting that if the keyword is also stored in the headset, the first voice collection module is not turned off when the second voice collection module is turned on, but the first voice collection module is still turned on. In the state, when the second voice collection module is turned off by the earphone, it is not necessary to turn on the first voice collection module again.

The device for enabling the voice recognition function of the terminal through the earphone provided by the embodiment may be in a state where the voice recognition function of the terminal is off, without manual operation, and only the voice containing the preset keyword collected by the collection module may be turned on. The module sends an open command for turning on the voice recognition function to the terminal to enable the voice recognition function of the terminal for voice recognition. Therefore, the device can perform voice recognition through the earphone and automatically turn on the voice recognition function of the terminal, so that the terminal does not need to open the voice recognition for a long time. The function not only can reduce the power consumption of the terminal, but also can improve the convenience of the user to use the voice recognition function, thereby further improving the user experience.

In addition, an embodiment of the present invention further provides an earphone including a memory and a processor, and the processor implements the method provided by any of the foregoing embodiments by calling an instruction stored in the memory. It should be noted that, in addition to the above devices, the earphone includes a headphone body, such as a communication module, a battery, a speaker, an earpiece, and the like.

It can be seen that the earphone provided by the embodiment can be used in the state that the voice recognition function of the terminal is off, and no manual operation is required. Only the voice containing the preset keyword can be used to send an open command for turning on the voice recognition function to the terminal. The voice recognition function of the terminal is enabled to perform voice recognition. Therefore, the headset can automatically send an instruction to turn on the voice recognition function to the terminal through the voice containing the preset keyword, so that the terminal automatically turns on the voice recognition function of the terminal, so that the terminal does not need to be long. Turning on the voice recognition function not only reduces the power consumption of the terminal, but also improves the convenience of the user using the voice recognition function, thereby further improving the user experience.

FIG. 5 is a flowchart of a method for enabling a voice recognition function of a terminal according to an embodiment of the present invention. As shown in FIG. 5, the method includes:

S50: Receive an open command for turning on the voice recognition function sent by the earphone.

S51: Turn on the voice recognition function for voice recognition.

It should be noted that when the terminal receives the opening instruction of the voice recognition function that is sent by the earphone, the terminal immediately turns on its own voice recognition function to perform voice recognition.

Moreover, it can be understood that if the terminal receives the local voice recognition sent by the earphone When the function is turned on, the terminal turns on its own local voice recognition function. If the terminal receives the opening command of the network voice recognition function sent by the headset, the terminal turns on its own network voice recognition function. Preferably, when the terminal receives the opening instruction of the voice recognition function that is sent by the earphone, the terminal turns on the local voice recognition function to recognize the voice input by the user by default, and when the local voice recognition function cannot successfully recognize the voice input by the user, The terminal turns off the local voice recognition function and simultaneously turns on the network voice recognition function to recognize the voice input by the user.

Therefore, the method for enabling the voice recognition function of the terminal in the embodiment can be performed in the state that the voice recognition function of the terminal is off, without manual operation, and the terminal can start its own voice recognition only by receiving an open command sent by the earphone. Features for speech recognition. Compared with the prior art, the method can not only reduce the power consumption of the terminal, but also improve the convenience of the user using the voice recognition function, thereby further improving the user experience.

In a specific implementation, when the user speaks the voice to be recognized far away from the terminal, the quality of the voice to be recognized obtained by the microphone of the terminal itself is poor, which may result in a decrease in the success rate of voice recognition and affect the user. Experience. Of course, the user can move the terminal to a place with a small distance from the user so that the terminal can obtain a better-quality voice to be recognized, but because the portability of the terminal is poor, when the user's hands are occupied, the user is difficult. Ensure the distance between itself and the terminal. In view of this, the present invention considers that the earphone has better portability. As long as the user wears the earphone, even if the user speaks the voice to be recognized far away from the terminal, the terminal can collect the higher-quality voice to be recognized through the earphone. Therefore, after the headset sends an open command to the terminal, the terminal can also establish a voice transmission link with the earphone to obtain high quality to-be-recognized voice collected by the portable headset through the voice transmission link. .

FIG. 6 is a flowchart of another method for enabling a voice recognition function of a terminal according to an embodiment of the present invention. In this embodiment, the terminal obtains the high-quality to-be-recognized voice collected by the earphone through the voice transmission link, as shown in FIG. 6. As a preferred implementation manner, on the basis of FIG. 5, after performing step S51, the terminal further includes :

S60: Initiating a request to establish a voice transmission link to the headset to establish a voice transmission link.

S61: Receive voice sent by the earphone through a voice transmission link, and perform voice recognition.

It should be noted that the voice transmission link refers to a transmission link for transmitting a voice to be recognized before the terminal and the earphone, and the voice mentioned in step S61 is after the voice recognition function is enabled after the terminal starts the voice recognition function. , the voice collected by the headset.

In the step S60, when the terminal turns on the voice recognition function, if it is detected that the earphone is connected to itself, the headset connected to the self initiates a request for establishing a voice transmission link between the two, once the headset is received. Responding to the response message initiated by the terminal to establish a request for the voice transmission link between the two, the voice transmission link between the two is established immediately. After the voice transmission link between the two is established, the voice is transmitted. The transmission link receives the voice sent by the headset and performs voice recognition. Of course, it can be understood that after the voice recognition function of the terminal is turned on through the earphone, the terminal may not send a request for establishing a voice transmission link with the earphone to the earphone, but by using its own microphone or other connection with itself. The device that can obtain the voice obtains the voice to be recognized input by the user, and the detailed process is not described in detail in the present invention.

Moreover, it is worth noting that, for step S61, when the timing of the user inputting the voice to be recognized is incorrect, the voice recognition may be caused to fail, for example, after the headset sends the open command, the voice transmission between the headset and the terminal. The link is not yet established, but for the voice that has already started to be recognized, the user cannot obtain the voice to be recognized when the terminal starts the voice recognition function and the voice transmission link is established in the terminal. , causing speech recognition to fail or be incomplete. Therefore, in order to enable the user to accurately input the timing of the voice to be recognized, thereby improving the success rate of the voice recognition, thereby improving the user experience, as a preferred embodiment, after the terminal establishes the voice transmission link, it also sends the voice transmission to the headset. The prompting instruction is convenient for the earphone to play the prompting signal for starting to input the voice to be recognized after receiving the prompting instruction sent by the terminal, to help the user accurately grasp the timing of inputting the voice to be recognized, and the terminal can acquire the earphone through the voice transmission link. Voice. The terminal can obtain all the voices to be recognized to improve the success rate of voice recognition, thereby improving the user experience.

It can be seen that the present invention fully considers that the speech recognition success rate of the terminal has a great relationship with the distance between the terminal and the user, and the portability of the terminal is far from the portability of the earphone, and the terminal passes The voice transmission link receives the voice to be recognized input by the user collected by the earphone, and avoids the voice recognition failure caused by the distance between the user and the terminal, which affects the user experience. Therefore, the method can improve the success rate of the voice recognition of the terminal, thereby improving the user experience.

In a specific implementation, after the terminal successfully obtains the voice to be recognized or successfully obtains the recognition result, the terminal no longer needs to obtain the voice to be recognized through the voice transmission link. At this time, the terminal can disconnect the voice transmission link to lower the terminal. Its own power consumption. And, if the terminal has obtained the recognition result, the voice recognition function can also be turned off at the same time. Therefore, the embodiment of the present invention provides another method for turning on the voice recognition function of the terminal, which is further improved on the basis of FIG. 6, and is described in detail below with reference to the accompanying drawings.

FIG. 7 is a flowchart of another method for enabling a voice recognition function of a terminal according to an embodiment of the present invention. As shown in FIG. 7 , in order to reduce the power consumption of the terminal itself, as a preferred embodiment, after performing step S61 on the basis of FIG. 6 , the method further includes:

S70: When the preset shutdown condition is reached, the voice transmission link is disconnected, and the voice recognition function is turned off.

The foregoing preset closing conditions specifically include:

The signal strength of the voice is lower than the first preset value and the duration is up to the second preset value; or the signal strength of the voice is higher than the third preset value, and the duration is up to the fourth preset value; or the voice recognition result is obtained.

It should be noted that the first preset value is smaller than the third preset value. When the signal strength of the voice acquired by the terminal is lower than the first preset value, and the signal strength continues to be lower than the first preset value for a second preset value, the terminal disconnects the voice transmission link. , turn off its own speech recognition function. For example, when the first preset value is the lowest signal strength of the terminal recognition voice, and the second preset value is 2 seconds, if the signal strength of the voice acquired by the terminal within 2 seconds is less than the voice of the lowest signal strength, the terminal considers that After the voice to be recognized has been input, the voice transmission link is disconnected and its voice recognition function is turned off.

When the signal strength of the voice acquired by the terminal is higher than the third preset value, and the time when the signal strength is higher than the third preset value is up to the fourth preset value, the terminal disconnects the voice transmission link. shut down Its own voice recognition function. For example, when the third preset value is the highest signal strength of the terminal recognition voice, and the fourth preset value is 10 seconds, if the signal strength of the voice acquired by the terminal is greater than the highest signal strength within 10 seconds, the terminal considers that If the voice input is incorrect, the voice transmission link will be disconnected and its voice recognition function will be turned off.

After the terminal obtains the recognition result, the terminal considers that the voice recognition is completed, the voice transmission link is disconnected, and the voice recognition function is turned off. Certainly, it can be understood that, in order to further improve the method for enabling the terminal voice recognition function provided by the embodiment, after the terminal obtains the recognition result, the terminal may send the audio of the recognition result to the earphone to play the audio through the earphone. Of course, the audio in the recognition result can also be played by other broadcasting devices, such as the speaker of the terminal itself and the sound connected to the terminal.

Similarly, in order to further improve the method for enabling the terminal voice recognition function provided by the embodiment, after the terminal obtains the recognition result, when the recognition result includes characters, pictures or video information, the terminal may also display the recognition result through the display screen, wherein The display screen may be the display screen of the terminal itself, or may be a display device connected to the terminal, for example, the recognition result may be displayed by a projector connected to the terminal.

Therefore, the method for enabling the voice recognition function of the terminal provided by the embodiment can reduce the power consumption of the terminal by shortening the voice recognition function of the terminal in time to extend the standby time of the terminal, thereby further improving the user experience. Of course, the audio in the recognition result and the display screen can display the characters, pictures or video information in the recognition result through the earphone to further enhance the user's experience.

Of course, it can be understood that the method for enabling the voice recognition function of the terminal provided by the embodiment of the present invention can be further improved on the basis of FIG. 5, that is, after step S51 is performed, step S70 is continued, and details are not described herein again. .

An embodiment of the method for enabling the terminal voice recognition function provided by the present invention is described in detail above. The present invention further provides a device for enabling the terminal voice recognition function corresponding to the method, which is implemented by the device part. The examples of the method and the method part are mutually responsive, so the device part For the embodiment of the method, please refer to the description of the embodiment of the method section, and details are not described herein.

FIG. 8 is a structural diagram of an apparatus for enabling a voice recognition function of a terminal according to an embodiment of the present invention. As shown in Figure 8, the device includes:

The receiving module 80 is configured to receive an opening instruction of the voice recognition function that is sent by the earphone.

The module 81 is turned on for turning on the voice recognition function for voice recognition.

It can be seen that the device for enabling the voice recognition function of the terminal in this embodiment can be operated without the manual operation when the voice recognition function of the terminal is off, and the terminal can only open the module by receiving the opening command sent by the earphone through the receiving module. The voice recognition function is enabled to perform voice recognition. Compared with the prior art, the device can not only reduce the power consumption of the terminal, but also improve the convenience of the user using the voice recognition function, thereby further improving the user experience.

In addition, an embodiment of the present invention further provides a terminal, where the terminal includes a memory and a processor, and the processor implements a method for turning on the voice recognition function of the terminal provided by any of the foregoing embodiments by calling an instruction stored in the memory. It can be seen that the terminal provided by the embodiment can be used in the state that the voice recognition function of the terminal is off, without manual operation, and the terminal can open its own voice recognition function for voice recognition only by receiving an open command sent by the earphone. Compared with the prior art, the terminal can not only reduce power consumption, but also improve the convenience of the user using the voice recognition function, thereby further improving the user experience.

In order to enable a person skilled in the art to better understand the technical solution of the present invention, the method and device for opening the voice recognition function of the terminal through the earphone, and the voice recognition of the open terminal provided by the embodiment of the present invention are provided below with reference to the accompanying drawings and the embodiments of the present invention. The above described invention will be further described in detail by the method and device of the function, the earphone and the terminal provided by the embodiment of the present invention.

FIG. 9 is a schematic diagram of an application scenario of a headset and a terminal according to an embodiment of the present invention. As shown in FIG. 9, the application process includes:

S90: When the user needs to use the voice recognition function of the terminal, the user speaks the voice containing the preset keyword to the earphone, for example, “turn on the network voice recognition function”.

S91: When the earphone captures the preset keyword, the earphone sends an open command to the terminal through the command channel.

S92: After receiving the open command, the terminal starts the network voice recognition function and establishes a voice transmission link with the earphone.

S93: The user speaks the voice to be recognized to the earphone.

S94: The earphone collects the voice to be recognized, and sends the voice to be recognized to the terminal through the voice transmission link.

S95: The terminal receives the to-be-identified voice through the voice transmission link, and sends the to-be-identified voice to the network voice recognition server through the network voice recognition module.

S96: The network speech recognition server receives the speech to be recognized for recognition, obtains the recognition result, and sends the recognition result to the terminal.

S97: The terminal receives the recognition result, and sends the audio of the recognition result to the earphone.

S98: The earphone receives the audio of the recognition result and plays the audio to the user.

The method and device, the earphone and the terminal provided by the embodiment of the present invention can be seen that the voice recognition function of the terminal is closed in a detailed description of the method and device, the application method of the earphone and the terminal provided by the embodiment of the present invention. In the state, the manual voice operation is not required, and the voice recognition function of the terminal can be enabled only by the voice containing the preset keyword, and the voice recognition function of the terminal can be used normally. Therefore, the method and device provided by the embodiment of the present invention and the earphone are provided. And the terminal can open and use the voice recognition function of the terminal through voice to save the power consumption of the terminal, thereby improving the convenience of the user using the voice recognition function, and further improving the user experience.

The method and device for enabling the voice recognition function of the terminal through the earphone provided by the embodiment of the present invention provided by the embodiment of the present invention, the method and device for opening the voice recognition function of the terminal provided by the embodiment of the present invention, and the earphone and the terminal provided by the embodiment of the present invention Detailed introduction. The various embodiments in the specification are described in a progressive manner, and each embodiment is described as being different from the other embodiments, and the same similar parts between the various embodiments may be referred to each other.

It should be noted that those skilled in the art can also make several improvements and modifications to the present invention without departing from the principles of the present invention. Within the scope of the claims of the invention.

It should also be noted that in this specification, relational terms such as first and second are used merely to distinguish one entity or operation from another entity or operation, without necessarily requiring or implying such entities or operations. There is any such actual relationship or order between them. Furthermore, the term "comprises" or "comprises" or "comprises" or "comprises" or "includes" or "includes" or "includes" or "includes" or "includes" Other elements, or elements that are inherent to such a process, method, article, or device. An element that is defined by the phrase "comprising a ..." does not exclude the presence of additional equivalent elements in the process, method, item, or device that comprises the element.

Claims

A method for enabling a voice recognition function of a terminal through a headset, comprising:

Collecting speech;

When it is determined that the preset keyword is included in the voice, an open command for turning on the voice recognition function is sent to the terminal to enable the terminal to perform voice recognition.
The method according to claim 1, wherein after the sending the opening instruction of the voice recognition function to the terminal, the method further comprises:

Responding to a request initiated by the terminal to establish a voice transmission link;

When it is detected that the voice transmission link is turned on, voice can be transmitted to the terminal through the voice transmission link.
The method according to claim 1 or 2, further comprising:

When detecting that the terminal closes the voice transmission link, stopping transmission of voice to the terminal through the voice transmission link.
The method according to claim 3, wherein the opening command for sending the voice recognition function to the terminal is specifically:

The open command is sent to the terminal through an instruction channel based on the BLE protocol.
An apparatus for enabling a voice recognition function of a terminal through a headset, comprising:

An acquisition module for collecting voices;

The opening module is configured to, when determining that the voice includes a preset keyword, send an open command to enable the voice recognition function to enable the terminal to perform voice recognition.
An earphone characterized by comprising a memory and a processor, the processor executing the method of any one of claims 1-4 by invoking an instruction stored in the memory.
A method for enabling a voice recognition function of a terminal, comprising:

Receiving an open command for turning on the voice recognition function sent by the earphone;

The speech recognition function is turned on for speech recognition.
The method according to claim 7, wherein after the opening the voice recognition function, the method further comprises:

Initiating a request to establish a voice transmission link to the headset to establish the voice transmission link;

Receiving voice transmitted by the earphone through the voice transmission link, and performing voice recognition.
The method according to claim 7 or 8, wherein after receiving the voice sent by the headset through the voice transmission link, the method further includes:

When the preset shutdown condition is reached, disconnecting the voice transmission link and turning off the voice recognition function;

The preset shutdown condition specifically includes:

The signal strength of the voice is lower than the first preset value and the duration is up to the second preset value;

Or the signal strength of the voice is higher than the third preset value, and the duration is up to the fourth preset value;

Or get a speech recognition result;

The first preset value is smaller than the third preset value.
An apparatus for enabling a voice recognition function of a terminal, comprising:

a receiving module, configured to receive an open instruction for turning on the voice recognition function sent by the earphone;

The module is turned on for turning on the voice recognition function for voice recognition.
A terminal, comprising a memory and a processor, the processor executing the method of any one of claims 7-9 by invoking an instruction stored in the memory.