Method and device for automatically detecting and switching languages, terminal equipment, and storage medium

Abstract

The present invention provides a method and device for automatically detecting and switching languages, a terminal device, and a storage medium. The method uses a language detection module of a terminal device and a main wake-up word module in a voice wake-up module of the terminal device to detect and wake up input voice information respectively, and obtains a first language from N languages; after obtaining the first language, the terminal device sends the first language to each module in a first voice link corresponding to the first language, and completes language switching one by one to realize automatic language switching; during the switching process, the local service is switched while the cloud service is switched, thereby improving the switching speed and the stability of the language switching.

Description

Technical Field

[0001] The present application relates to the technical field of language switching, and in particular to a method and apparatus, a terminal device, and a storage medium for automatically detecting and switching languages. Background Art

[0002] With the popularization of computer technology, people's lives today have gradually entered the intelligent era, especially in voice interaction. Not only computers and mobile phones have adopted the voice interaction mode, but also smart TVs, smart navigation, smart homes, etc. are operated through the voice interaction mode to meet users' fast service needs.

[0003] In voice interaction systems, it is often necessary to support voice wake-up, speech recognition, speech synthesis, semantic understanding, semantic generation, etc. in multiple languages, and to switch according to user preferences or needs.

[0004] The traditional way to switch is to provide options in the system settings. When the user selects a language, such as Sichuan dialect, the corresponding voice engine will be loaded accordingly. However, when two or more people use the same voice system at the same time, and two or more people use different languages, it will be very inconvenient to manually switch between different languages. Summary of the invention

[0005] In view of this, the present application provides a method and device for automatically detecting and switching languages, through which the language corresponding to the input voice is automatically detected and switched during wake-up or recognition.

[0006] In order to solve the above technical problems, this application adopts the following technical solutions:

[0007] According to an embodiment of the present invention, a method for automatically detecting and switching languages ​​is provided, the method comprising:

[0008] The terminal device receives the voice information input by the user, and uses the main wake-up word module of the voice wake-up module of the terminal device and the language detection module of the terminal device to wake up and detect the voice information respectively; wherein the voice information includes the language type and semantic information of the voice;

[0009] The language detection module obtains a first language matching the voice information from N languages; wherein N is an integer greater than 1;

[0010] The terminal device determines whether the first language is the same as its current application language; if not

[0011] then the terminal device acquires a cloud service based on the first language, and switches the voice system of the cloud service to a first voice link corresponding to the first language; and

[0012] The voice system of the local service of the terminal device is switched to a second voice link corresponding to the first language; wherein the second voice link includes at least a voice recognition module, a voice synthesis module, a semantic understanding module, a semantic generation module and the voice wake-up module.

[0013] Preferably, the terminal device receives input voice information, and uses the main wake-up word module of the voice wake-up module of the terminal device and the language detection module of the terminal device to wake up and detect the voice information respectively, including:

[0014] The terminal device receives a voice containing a wake-up word, and integrates a first language detection module in the language detection module into the main wake-up word module. The first language detection module performs language detection on the voice containing the wake-up word to obtain the first language.

[0015] Preferably, the second language detection module in the language detection module is integrated into the speech recognition module. After the cloud service and the local service are switched to the first voice link and the second voice link respectively, the second language detection module detects the voice information input by the user to obtain the second language; when the matching rate between the second language and the first language is less than a set threshold range, the voice systems of the cloud service and the local service are switched to a third voice link corresponding to the second language.

[0016] Preferably, the terminal device receives input voice information, and uses the main wake-up word module of the voice wake-up module of the terminal device and the language detection module of the terminal device to wake up and detect the voice information respectively, including:

[0017] The second language detection module in the language detection module is integrated into the speech recognition module, and the second language detection module detects input speech information to obtain the first language.

[0018] Preferably, the terminal device receives input voice information, and uses the main wake-up word module of the voice wake-up module of the terminal device and the language detection module of the terminal device to wake up and detect the voice information respectively, including:

[0019] After the voice system of the local service completes the switching, the shortcut word module of the voice wake-up module wakes up the voice containing the wake-up word.

[0020] The embodiment of the present invention also provides a device for automatically detecting and switching languages, including:

[0021] A wake-up and detection module is configured to receive voice information input by a user on a terminal device, and to wake up and detect the voice information using a main wake-up word module of the voice wake-up module of the terminal device and a language detection module of the terminal device; wherein the voice information includes a language type and semantic information of the voice;

[0022] A matching module, configured to enable the language detection module to obtain a first language matching the voice information from N languages; wherein N is an integer greater than 1;

[0023] A determination module, configured to be used by the terminal device to determine whether the first language is the same as its current application language;

[0024] a switching module configured to enable the terminal device to obtain a cloud service based on the first language, and to switch a voice system of the cloud service to a first voice link corresponding to the first language; and

[0025] The voice system of the local service of the terminal device is switched to a second voice link corresponding to the first language; wherein the second voice link includes at least a voice recognition module, a voice synthesis module, a semantic understanding module, a semantic generation module and the voice wake-up module.

[0026] Preferably, the language detection module comprises a first language detection module;

[0027] The first language detection module is configured to be integrated on the main wake-up word module, and the first language detection module performs language detection on the voice containing the wake-up word received by the terminal device to obtain the first language.

[0028] Preferably, the language detection module comprises a second language detection module;

[0029] The second language detection module is configured to be integrated in the voice recognition module. After the cloud service and the local service are switched to the first voice link and the second voice link respectively, the second language detection module detects the voice information input by the user to obtain the second language.

[0030] Preferably, the language detection module comprises a second language detection module;

[0031] The second language detection module is configured to be integrated on the speech recognition module, and the second language detection module detects the speech information input by the user to obtain the first language.

[0032] Preferably, the voice wake-up module further includes a shortcut word module;

[0033] The shortcut word module is configured to wake up the voice containing the wake-up word after the voice system of the local service completes the switching, so that the shortcut word module of the voice wake-up module wakes up the voice.

[0034] An embodiment of the present invention further provides a terminal device, the terminal device comprising:

[0035] processor;

[0036] A memory; and a program, wherein the program is stored in the memory and is configured to be executed by the processor so that the terminal device implements the method of automatically detecting and switching languages.

[0037] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored: the computer program is executed by a processor to implement the method of automatically detecting and switching languages.

[0038] The above technical solution of the present application has at least one of the following beneficial effects:

[0039] According to a method and device for automatically detecting and switching languages ​​in an embodiment of the present application, the method uses a language detection module of a terminal device and a main wake-up word module in a voice wake-up module of the terminal device to detect and wake up the input voice information respectively, and obtains a first language from N languages; after obtaining the first language, the terminal device sends the first language to each module in a first voice link corresponding to the first language, and completes language switching one by one to achieve automatic language switching; during the switching process, the local service is switched while the cloud service is switched, thereby improving the switching speed and improving the stability of the language switching. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 A schematic diagram of the structure of a method for automatically detecting and switching languages ​​according to an embodiment of the present application;

[0041] Figure 2 This is an overall flow chart of the method for automatically detecting and switching languages ​​according to an embodiment of the present application;

[0042] Figure 3 This is an overall logic diagram of the method for automatically detecting and switching languages ​​according to an embodiment of the present application;

[0043] Figure 4 A specific logic diagram of the method for automatically detecting and switching languages ​​according to an embodiment of the present application;

[0044] Figure 5 A logic diagram of a method for automatically detecting and switching languages ​​according to an embodiment of the present application;

[0045] Figure 6A logic diagram of a method for automatically detecting and switching languages ​​according to another embodiment of the present application;

[0046] Figure 7 A logic diagram of a method for automatically detecting and switching languages ​​according to another embodiment of the present application;

[0047] Figure 8 This is a module diagram of a device for automatically detecting and switching languages ​​in the present application.

[0048] Reference numerals:

[0049] 1. Cloud, 2. Terminal device, 10. Wake-up and detection module, 110. Language detection module, 111. First language detection module, 112. Second language detection module, 120. Voice wake-up module, 121. Main wake-up word module, 122. Quick word module, 20. Switching module, 30. Judgment module, 40. Matching module. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0051] In the prior art, manual switching for different languages ​​will cause great inconvenience. In response to this technical problem, the embodiment of the present application provides a method for automatically detecting and switching languages. The method automatically wakes up and detects the input voice information through the voice wake-up module and the language detection module of the terminal device, and switches. However, when switching the voice system of the local service, it is necessary to release the previous voice system and then load the new voice system. This process takes some time, and the voice switching of the local service reduces the user experience. The method provided in the embodiment of the present application gives priority to the switching of cloud services. The switching of cloud services only requires the modification of parameters, and there is no time stagnation for users, which improves the user experience. However, due to the variability of the environment in which the user is in the process of switching languages, such as when the vehicle-mounted terminal device drives to a cave, the smoothness of the network cannot be guaranteed. Therefore, the embodiment of the present application switches the local service while giving priority to the switching of cloud services, thereby improving the speed of language switching and the stability of language switching.

[0052] The various embodiments of the present application are described in detail below in conjunction with specific drawings.

[0053] Figure 1A structural diagram of a method for automatically detecting and switching languages ​​provided in an embodiment of the present application, the structural diagram includes a cloud 1 and a terminal device 2, and the cloud 1 service and the terminal device 2 are connected via a network. The terminal device 2 is, for example, a vehicle-mounted terminal, a computer terminal, etc., which are not limited here. The terminal device 2 automatically wakes up and detects the input voice information, then obtains the cloud 1 service and switches the voice system. While the cloud 1 service switches its voice system to the first voice link, the local service of the vehicle-mounted terminal switches its voice system to the second voice link; the first voice link and the second voice link respectively correspond to the first language after switching, and the difference between the two is that the first language link is in the cloud, and the second voice link is locally.

[0054] The terminal device is user-oriented, and the terminal user may be oriented to multiple users. When multiple users interact with the terminal device in different languages, the terminal device needs to detect and switch in time to improve the user experience. The language involved in the embodiments of the present application includes switching of languages, such as switching between English and Chinese, and also includes switching between dialects under the language, such as switching between Sichuan dialect and Mandarin.

[0055] In one embodiment of the present application, a method for automatically detecting and switching languages ​​is provided, such as Figure 2 , Figure 3 As shown, the method specifically comprises the following steps:

[0056] S1. The terminal device receives input voice information, and uses the main wake-up word module of the voice wake-up module of the terminal device and the language detection module of the terminal device to wake up and detect the voice information respectively; wherein the voice information includes the language type and semantic information of the voice. When the user sends a wake-up voice message, the terminal device receives the input voice information, such as: "Hello, hello", and the main wake-up word module of the voice wake-up module of the terminal device is awakened; the language detection module of the terminal device detects the input voice information and detects which dialect or language the input voice information belongs to.

[0057] S2. The language detection module obtains a first language matching the voice information input in step S1 from N languages; wherein N is an integer greater than 1. The specific recognition method of obtaining the first language matching the input voice information by the language detection module can be implemented by an implementation method in the prior art. For example, recognition by training a recognition model, etc., which is not limited here.

[0058] S3. The terminal device determines whether the first language is the same as its current application language. When the language management module in the terminal device receives the first language obtained in step S2, the language management module compares the first language with the current application language of the terminal device to determine whether the two are the same. If they are the same, there is no need to perform the following switching steps. If they are not the same, proceed to step S4.

[0059] S4, the terminal device obtains the cloud service based on the first language, and switches the voice system of the cloud service to the first voice link corresponding to the first language; and the voice system of the local service of the terminal device is switched to the second voice link corresponding to the first language; wherein the first voice link or the second voice link includes at least a speech recognition module, a speech synthesis module, a semantic understanding module, a semantic generation module and a speech wake-up module. When it is confirmed in step S3 that the first language is different from the current application language of the terminal device, the terminal device performs a cloud switch and a local switch at the same time. The switching process includes the switching of the speech recognition module, the switching of the speech synthesis module, the switching of the semantic understanding module, the switching of the semantic production module and the switching of the shortcut word module in the speech wake-up module.

[0060] like Figure 4 As shown, when switching locally, the local service's speech recognition (Automatic Speech Recognition, ASR) model needs to be released and then a new ASR model needs to be loaded. This process takes time, about three seconds. Therefore, this embodiment first uses the cloud ASR model for speech recognition. Since the cloud ASR model only needs to change the parameters, there is no time stagnation for the user. This can improve the switching speed during the language switching process and improve the user's experience quality.

[0061] In one embodiment of the present invention, Figure 5 As shown, the terminal device receives a voice containing a wake-up word, integrates the first language detection module in the language detection module on the main wake-up word module, and the first language detection module performs language detection on the voice containing the wake-up word to obtain the first language. The main wake-up word module of the terminal device wakes up after receiving the voice containing the wake-up word, and at the same time, the first language detection module detects the voice containing the wake-up word and obtains the first language. For example: the user sends the wake-up word "Hello, hello" to the terminal device, and the main wake-up word module of the terminal device wakes up after receiving the wake-up word. After waking up, the first language detection module detects the language type of "Hello, hello", for example, the detected "Hello, hello" is Sichuan dialect. In an embodiment of the present invention, the specific method of obtaining the first language by inputting a voice containing a wake-up word includes the following two methods but is not limited to these two methods.

[0062] In the first method, each of the N languages ​​corresponds to its own wake-up word. The main wake-up word module and the first language detection module use the mixed phoneme set of the N languages ​​as the basic modeling unit. The main wake-up words of different languages ​​correspond to different phoneme sequences. The main wake-up word wakes up the first language detection module by decoding the input speech, and determines whether the wake-up word is contained and which language the wake-up word corresponds to based on the obtained phoneme sequence.

[0063] In the second method, each of the N languages ​​corresponds to its own wake-up word. The main wake-up word module and the first language detection module use an end-to-end neural network model. The input includes speech containing the wake-up word, and the output is the corresponding probability value of the wake-up word and non-wake-up word in the N languages. The output with the highest matching probability determines the wake-up word and the language corresponding to the wake-up word.

[0064] In an alternative embodiment of the present invention, Figure 6 As shown, the terminal device receives a voice containing a wake-up word, integrates the first language detection module into the main wake-up word module, and the first language detection module performs language detection on the voice containing the wake-up word to obtain the first language. At the same time, the second language detection module in the language detection module is integrated into the speech recognition module, and the second language detection module detects the input voice information to obtain the second language. When the matching rate between the second language and the first language is less than the set threshold range, the voice system of the cloud service switches to the third voice link corresponding to the second language; and the voice system of the local service is also switched at the same time. In this embodiment, based on the previous embodiment, the second language detection module is integrated into the speech recognition module. The speech recognition module can be understood as recognizing the voice information input by the user, including converting the input voice information into text information or accepting the input voice information to execute instructions, etc., which is not limited here. The second language detection module is integrated into the speech recognition module, that is, the input voice information after the terminal device completes the language switching is detected. For example, when the language of the voice link switch of the terminal device is Sichuan dialect, when the user sends a voice message of "please play music", the second language detection module performs correction detection on the input voice message of "please play music", detects the language of the input voice message of "please play music" and compares it with the first language.

[0065] When the matching rate of the language type detected by the second language detection module and the first language detection module is less than the set threshold range, the voice system of the cloud service and the local service is switched to the voice link corresponding to the second language. There may be errors when the first detection module performs language detection on the wake-up word, because the wake-up word is relatively short and can recognize less information, while the second language detection module receives a relatively long voice information and can recognize more information. Therefore, when there is a large difference between the detection results of the two, the detection result of the second language detection module shall prevail.

[0066] In another alternative embodiment of the present invention, Figure 7 As shown, the second language detection module in the language detection module is integrated into the speech recognition module, and the second language detection module detects the input voice information to obtain the first language. In this embodiment, the language detection module will not be integrated on the main wake-up word module, that is, only the speech recognition module in the entire voice link is integrated with the speech detection module. After the main wake-up word module receives the voice containing the wake-up word, the voice system of the terminal device is awakened. After the user inputs the voice information, the second language detection module detects the input voice information to obtain the first language. The terminal device performs the subsequent switching between cloud services and local services according to the first language.

[0067] In the embodiment of the present application, the language detection module can be integrated separately on the main wake-up word module or separately on the speech recognition module, and can also be integrated on both the main wake-up word module and the speech recognition module, thereby increasing the flexibility of the terminal device for the language switching method.

[0068] In one embodiment of the present invention, after the voice system of the local service completes the switching in step S1, the shortcut word module of the voice wake-up module wakes up the voice containing the wake-up word. The voice wake-up module includes a main wake-up word module and a shortcut word module. In the prior art, the main wake-up word module and the shortcut word module are generally coupled together. When the two are coupled together, they can only be implemented through an algorithm solution, such as: context-dependent acoustic model (contextdependent phone, CD-phone). In this embodiment, the main wake-up word module and the shortcut word module are independent of each other. When the first language detection module is integrated into the main wake-up word module, the main wake-up word module not only has a wake-up function but also a language detection function, while the shortcut word module only has a wake-up function. When the main wake-up word module and the shortcut word module are independent of each other, they can select new algorithms suitable for each other, so that the functional effects of each are better, and the accuracy of the wake-up of the voice wake-up module is improved.

[0069] The present invention also provides a device for automatically detecting and switching languages, such as Figure 8 As shown, it includes a wake-up and detection module 10, a matching module 40, a judgment module 30 and a switching module 20; wherein,

[0070] The wake-up and detection module 10 is configured to receive input voice information of the terminal device, and wake up and detect the voice information respectively by using the main wake-up word module 121 of the voice wake-up module 120 of the terminal device and the language detection module 110 of the terminal device; wherein the voice information includes the language type and semantic information of the voice;

[0071] The matching module 40 is configured to enable the language detection module to obtain a first language that matches the speech information from N languages; wherein N is an integer greater than 1;

[0072] The determination module 30 is configured to be used by the terminal device to determine whether the first language is the same as its current application language;

[0073] The switching module 20 is configured to enable the terminal device to obtain a cloud service based on a first language, and to switch a voice system of the cloud service to a first voice link corresponding to the first language; and

[0074] The voice system of the local service of the terminal device is switched to a second voice link corresponding to the first language; wherein the second voice link includes at least a voice recognition module, a voice synthesis module, a semantic understanding module, a semantic generation module and a voice wake-up module.

[0075] In one embodiment of the present invention, the language detection module 110 includes a first language detection module 111;

[0076] The first language detection module 111 is configured to be integrated on the main wake-up word module 121. The first language detection module 111 performs language detection on the speech containing the wake-up word received by the terminal device to obtain the first language.

[0077] In one embodiment of the present invention, the language detection module 110 includes a second language detection module 112;

[0078] The second language detection module 112 is configured to be integrated in the voice recognition module. After the cloud service and the local service are switched to the first voice link and the second voice link respectively, the second language detection module 112 detects the voice information input by the user to obtain the second language.

[0079] In one embodiment of the present invention, the second language detection module 112 is configured to be integrated on the speech recognition module. The second language detection module detects the speech information input by the user and obtains the first language.

[0080] In one embodiment of the present invention, the voice wake-up module 120 further includes a shortcut word module 122;

[0081] The shortcut word module 122 is configured to wake up the voice containing the wake-up word after the voice system of the local service completes the switching.

[0082] An embodiment of the present invention further provides a terminal device, comprising: a processor; a memory; and a program, wherein the program is stored in the memory and is configured to be executed by the processor, so that the terminal device implements a method for automatically detecting and switching languages.

[0083] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored: the computer program is executed by a processor to implement a method for automatically detecting and switching languages.

[0084] It should be noted that in the examples and description of this patent, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including one" do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0085] The above is a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles described in the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for automatically detecting and switching languages, characterized in that: The method comprises: The terminal device receives the voice information input by the user, and uses the main wake-up word module of the voice wake-up module of the terminal device and the language detection module of the terminal device to wake up and detect the voice information respectively; wherein the voice information includes the language type and semantic information of the voice; The language detection module obtains a first language matching the voice information from N languages; wherein N is an integer greater than 1; The terminal device determines whether the first language is the same as its current application language; if not then the terminal device acquires a cloud service based on the first language, and switches the voice system of the cloud service to a first voice link corresponding to the first language; and The voice system of the local service of the terminal device is switched to a second voice link corresponding to the first language; wherein the second voice link includes at least a voice recognition module, a voice synthesis module, a semantic understanding module, a semantic generation module and the voice wake-up module, and the voice system switching of the local service of the terminal device includes releasing the old voice recognition model and loading the new voice recognition model; Before the voice system of the local service of the terminal device completes the switching, the voice system of the cloud service that has completed the switching is used to recognize the voice information.

2. The method according to claim 1, characterized in that The terminal device receives voice information input by a user, and uses a main wake-up word module of a voice wake-up module of the terminal device and a language detection module of the terminal device to wake up and detect the voice information respectively, including: The terminal device receives a voice containing a wake-up word, and integrates a first language detection module in the language detection module into the main wake-up word module. The first language detection module performs language detection on the voice containing the wake-up word to obtain the first language.

3. The method according to claim 2, characterized in that The second language detection module in the language detection module is integrated into the speech recognition module. After the cloud service and the local service are respectively switched to the first voice link and the second voice link, the second language detection module detects the voice information input by the user to obtain the second language; when the matching rate between the second language and the first language is less than a set threshold range, the voice systems of the cloud service and the local service are switched to a third voice link corresponding to the second language.

4. The method according to claim 1, characterized in that: The terminal device receives voice information input by a user, and uses a main wake-up word module of a voice wake-up module of the terminal device and a language detection module of the terminal device to wake up and detect the voice information respectively, including: The second language detection module in the language detection module is integrated into the speech recognition module, and the second language detection module detects input speech information to obtain the first language.

5. The method according to claim 1, characterized in that The terminal device receives voice information input by the user, and uses the main wake-up word module of the voice wake-up module of the terminal device and the language detection module of the terminal device to wake up and detect the voice information respectively, including: After the voice system of the local service completes the switching, the shortcut word module of the voice wake-up module wakes up the voice containing the wake-up word.

6. A device for automatically detecting and switching languages, characterized in that: include: A wake-up and detection module is configured to receive voice information input by a user on a terminal device, and to wake up and detect the voice information using a main wake-up word module of the voice wake-up module of the terminal device and a language detection module of the terminal device; wherein the voice information includes a language type and semantic information of the voice; A matching module, configured to enable the language detection module to obtain a first language matching the voice information from N languages; wherein N is an integer greater than 1; A determination module, configured to be used by the terminal device to determine whether the first language is the same as its current application language; a switching module configured to enable the terminal device to obtain a cloud service based on the first language, and to switch a voice system of the cloud service to a first voice link corresponding to the first language; and The voice system of the local service of the terminal device is switched to a second voice link corresponding to the first language; wherein the second voice link includes at least a voice recognition module, a voice synthesis module, a semantic understanding module, a semantic generation module and the voice wake-up module, and the voice system switching of the local service of the terminal device includes releasing the old voice recognition model and loading the new voice recognition model; Before the voice system of the local service of the terminal device completes the switching, the voice system of the cloud service that has completed the switching is used to recognize the voice information.

7. The device according to claim 6, characterized in that The language detection module includes a first language detection module; The first language detection module is configured to be integrated on the main wake-up word module, and the first language detection module performs language detection on the voice containing the wake-up word received by the terminal device to obtain the first language.

8. The device according to claim 7, characterized in that The language detection module includes a second language detection module; The second language detection module is configured to be integrated on the voice recognition module. After the cloud service and the local service are switched to the first voice link and the second voice link respectively, the second language detection module detects the voice information input by the user to obtain the second language.

9. The device according to claim 6, characterized in that The language detection module includes a second language detection module; The second language detection module is configured to be integrated on the speech recognition module, and the second language detection module detects the speech information input by the user to obtain the first language.

10. The device according to claim 6, characterized in that The voice wake-up module also includes a shortcut word module; The shortcut word module is configured to wake up the voice containing the wake-up word after the voice system of the local service completes the switching, so that the shortcut word module of the voice wake-up module wakes up the voice.

11. A terminal device, characterized in that: The terminal device comprises: processor; A memory; and a program, wherein the program is stored in the memory and is configured to be executed by a processor so that the terminal device implements the method according to any one of claims 1 to 5.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images