WO2019000515A1 - Voice call method and device - Google Patents

Abstract

The present invention discloses a voice call method and apparatus, the method comprising the steps of: collecting voice information of an original first language; transmitting voice information of the original first language to a server for translation processing, so that the server will be original first The voice information of the language is translated into the voice information of the final second language; the voice information of the final second language returned by the server is received; and the voice information of the final second language is sent to the opposite end.

Description

 Invention name: voice call method and device

 Technical field

 [0001] The present invention relates to the field of communications technologies, and in particular, to a voice call method and apparatus.

 Background technique

 [0002] With the increasing use of communication terminals, people can realize various functions by using communication terminals, such as listening to music, watching videos, and making voice calls using communication terminals. Voice calls are a basic and commonly used function of communication terminals. Even if people are thousands of miles apart, they can realize remote voice communication through communication terminals, which virtually shortens the distance between people.

 [0003] At the same time, with the globalization of the economy and the development of internationalization, people's exchanges between different countries are becoming more and more close. People in different countries usually use different languages. When at least one of the two users does not understand the other party's language, and the other user does not speak the other party's language, the two users cannot communicate remotely through the communication terminal. Face-to-face conversations must be made and translated through manual or translation machines, reducing communication channels and increasing communication costs.

 technical problem

 [0004] Therefore, how to implement remote voice communication for users using different languages through a communication terminal is a technical problem that needs to be solved at present.

 Problem solution

 Technical solution

 [0005] A primary object of the present invention is to provide a voice call method and apparatus for solving the technical problem that a user using a different language cannot perform remote voice communication through a communication terminal.

 [0006] In order to achieve the above objective, an embodiment of the present invention provides a voice call method, where the method includes the following steps: collecting voice information of an original first language; and transmitting the voice information of the original first language to a server. Translating processing, so that the server translates the voice information of the first language into voice information of a final second language; receiving voice information of the final second language returned by the server; The voice information of the language is sent to the peer.

[0007] Based on the same inventive concept, an embodiment of the present invention further provides a voice call method, where the method includes The following steps: receiving voice information of the original second language sent by the peer end; sending the voice information of the original second language to the server for translation processing, so that the server translates the voice information of the second language into Final voice information of the first language; receiving voice information of the final first language returned by the server; and outputting voice information of the final first language.

[0008] The embodiment of the present invention further provides a voice call device, where the device includes an information collection module, a first translation processing module, a first information receiving module, and an information sending module, and the information collection module is configured to collect the original first a voice information of the language; the first translation processing module is configured to send the voice information of the original first language to a server for translation processing, so that the server translates the voice information of the original first language into a final second The voice information of the language; the first information receiving module is configured to receive the voice information of the final second language returned by the server; and the information sending module is configured to send the voice information of the final second language to the peer end.

 Advantageous effects of the invention

 Beneficial effect

 [0009] A voice call method provided by an embodiment of the present invention sends a voice message of a local user to a server for translation processing, and translates the voice information that can be recognized by the peer user, and then translates the voice. The information is sent to the peer end, so that the peer user can understand the voice of the local user. Thereby, the translation function is added to the communication terminal, so that users who use different languages realize remote voice communication, which solves the technical problem that the users who use different languages cannot communicate remotely through the communication terminal, reduces the communication cost, and improves the user experience.

 Brief description of the drawing

 DRAWINGS

 1 is a system block diagram of an application scenario of a voice call method according to an embodiment of the present invention;

 [0011] FIG. 2 is a system block diagram of still another application scenario of a voice call method according to an embodiment of the present invention;

 [0012] FIG. 3 is a system block diagram of still another application scenario of a voice call method according to an embodiment of the present invention;

 [0013] FIG. 4 is a system block diagram of still another application scenario of a voice call method according to an embodiment of the present invention;

 5 is a block diagram showing a first embodiment of a voice communication device according to the present invention;

 6 is a block diagram of a first translation processing module of FIG. 5;

7 is a block diagram showing a second embodiment of a voice communication device according to the present invention; 8 is a block diagram of a second translation processing module of FIG. 7;

 9 is a block diagram showing a third embodiment of a voice communication device of the present invention.

 BEST MODE FOR CARRYING OUT THE INVENTION

 BEST MODE FOR CARRYING OUT THE INVENTION

The specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

 [0020] The voice call method and apparatus of the embodiments of the present invention are mainly applied to a VOLTE terminal, which is a communication terminal based on VOLTE (Voice over LTE) technology. VoLTE is an IP data transmission technology that does not require a 2G/3G network. All services are carried on a 4G network, which enables data and voice services to be unified under the same network. Of course, it can also be applied to a communication terminal based on other IP data transmission technologies, as long as it can unify data and voice services in the same network, which is not limited by the present invention.

 [0021] The first embodiment of the voice call method of the present invention, the method includes the following steps:

 [0022] S11. Collect voice information of the original first language.

 [0023] In the embodiment of the present invention, the language used by the VOLTE terminal user is defined as the first language, and the language used by the peer user is the second language. When the VOLTE terminal acts as a transmitting terminal, the voice information of the user's first language is collected through the microphone.

 [0024] S12: Send the voice information of the original first language to the server for translation processing, so that the server translates the voice information of the original first language into the voice information of the final second language.

 [0025] The VOLTE terminal may directly transmit the voice information of the original first language to the server as a voice data stream. Preferably, the VOLTE terminal sends the voice information of the original first language to the server in the form of a data packet. For example, the VOLTE terminal first records the voice information of the original first language, records it as a voice file and caches it, and then sends each cached voice file to the server in the form of a data packet.

 [0026] Translation processing mainly includes three processes of identification, translation and synthesis. These three processes can be completed by one server or by two or three servers.

[0027] In the embodiment of the present invention, the server includes a voice recognition server, a translation server, and a voice synthesis server. The VOLTE terminal establishes an IP-based connection with the voice recognition server, and sets the identification information, that is, the language type to be recognized, including the local language type (first language), and may further include The language type of the terminal (second language); establishes an IP-based connection with the translation server, sets the translation information, that is, the language to be translated, including the local-to-peer mapping, and may further include the peer-to-peer mapping; The server establishes a connection based on IP communication, and sets synthetic information, that is, the type of speech synthesis, such as male and female voice, speech rate, and the like.

 [0028] In step S12, the specific process of the VOLTE terminal transmitting the original first language voice information to the server for translation processing is as follows:

 [0029] S121. Send the voice information of the original first language to the voice recognition server, so that the voice recognition server recognizes the voice information as a character string of the first language.

 [0030] The VOLTE terminal first records the voice information of the original first language, records the voice files into a single voice file, and buffers them, and then sends each cached voice file to the voice recognition server in the form of a data packet. After receiving the voice file, the voice recognition server identifies the voice file according to the preset identification information, recognizes the character string as the first language, and returns the character string of the first language to the V 0LTE terminal.

 [0031] S122. Receive a character string of the first language returned by the voice recognition server.

 [0032] S123. Send a character string of the first language to the translation server, so that the translation server translates the character string of the first language into the character string of the second language.

 [0033] After receiving the character string of the first language, the VOLTE terminal sends the character string of the first language to the translation server. After receiving the string of the first language, the translation server translates the string of the first language according to the preset translation information, translates the string into the second language, and returns the string of the second language to the VOLTE. terminal.

 [0034] S124. Receive a character string of a second language returned by the translation server.

 [0035] S125. Send a character string of the second language to the speech synthesis server, so that the speech synthesis server synthesizes the character string of the second language into the speech information of the final second language.

 [0036] After receiving the character string of the second language, the VOLTE terminal sends the character string of the second language to the voice synthesizing server. After receiving the character string in the second language, the speech synthesis server synthesizes the character string of the second language according to the preset synthesis information, synthesizes the speech information into the final second language, and finally the voice information of the second language is The form of the voice stream is returned to the VOLTE terminal.

[0037] In other embodiments, the voice information of the original first language may also be identified by a server. Translation and synthesis processing. For example, the VOLTE terminal transmits the voice information of the original first language to the server, and the server identifies, translates, and synthesizes the voice information, and returns the voice information to the VOLTE terminal. In other embodiments, the identification, translation, and synthesis processing of the speech information of the original first language may also be performed by two servers. For example, the VOLTE terminal sends the voice information of the original first language to the first server, and the first server identifies and translates the voice information and returns the voice information to the VOLTE terminal, and the VOLT E terminal sends the voice information after the identification and translation processing. The second server sends the voice information to the VOLTE terminal. For another example, the VOLTE terminal sends the voice information of the original first language to the first server, and the first server returns the voice information to the VOLTE terminal, and the VOLTE terminal sends the voice information after the identification processing to the second server. The second server translates and synthesizes the voice information and returns it to the VOLTE terminal.

 [0038] S13. Receive voice information of the final second language returned by the server.

 [0039] S14. Send the voice information of the final second language to the peer end.

 [0040] After receiving the voice information of the final second language returned by the server, the VOLTE terminal sends the voice information of the final second language to the peer end through the voice channel. After receiving the voice information of the final second language, the peer end processes the voice information of the final second language through the audio channel, and finally outputs the voice information of the final second language through the sounding device (handset, speaker, etc.), using the The peer user of the second language can understand what the local user said.

The voice call method of the embodiment of the present invention sends the voice information of the collected local user to the server for translation processing, translates the voice information that can be recognized by the peer user, and then sends the translated voice information to the pair. End, so that the peer user can understand the voice of the local user. Thereby, the translation function is added to the communication terminal, so that users who use different languages realize remote voice communication, which solves the technical problem that the users who use different languages cannot communicate remotely through the communication terminal, reduces the communication cost, and improves the user experience.

 [0042] Further, in the second embodiment of the voice call method of the present invention, after step S14, the following steps are further included:

 [0043] S15. Receive voice information of the original second language sent by the opposite end.

[0044] When the VOLTE terminal is used as the receiving end, the voice information of the original second language sent by the opposite end of the transmitting end is received through the voice channel. [0045] S16: Send the voice information of the original second language to the server for translation processing, so that the server translates the voice information of the original second language into the voice information of the final first language.

 [0046] The VOLTE terminal may directly transmit the voice information of the original second language to the server as a voice data stream. Preferably, the VOLTE terminal sends the voice information of the original second language to the server in the form of a data packet. For example, the VOLTE terminal first records the voice information of the original second language, records it as a voice file and caches it, and then sends each cached voice file to the server in the form of a data packet.

 [0047] In the embodiment of the present invention, the server includes a voice recognition server, a translation server, and a voice synthesis server. In step S16, the specific process of the VOLTE terminal transmitting the voice information of the original second language to the server for translation processing is as follows:

 [0048] S161. Send the voice information of the original second language to the voice recognition server, so that the voice recognition server recognizes the voice information as a character string of the final second language.

 [0049] The VOLTE terminal first performs recording processing on the voice information of the original second language, records the voice files as a single voice file, and buffers, and then sends each cached voice file to the voice recognition server in the form of a data packet. After receiving the voice file, the voice recognition server identifies the voice file according to the preset identification information, recognizes the character string as the second language, and returns the character string of the second language to the V OLTE terminal.

 [0050] S162. Receive a character string of a second language returned by the voice recognition server.

 [0051] S163. Send a character string of the second language to the translation server, so that the translation server translates the character string of the second language into the character string of the first language.

 [0052] After receiving the character string in the second language, the VOLTE terminal sends the character string of the second language to the translation server. After receiving the character string in the second language, the translation server translates the character string of the second language according to the preset translation information, translates the character string into the first language, and returns the character string of the first language to VOLTE. terminal.

 [0053] S164. Receive a character string of the first language returned by the translation server.

 [0054] S165. Send the character string of the first language to the speech synthesis server, so that the speech synthesis server synthesizes the character string of the first language into the speech information of the final first language.

[0055] After receiving the character string in the first language, the VOLTE terminal sends the character string of the first language to the voice combination Become a server. After receiving the character string in the first language, the speech synthesis server synthesizes the character string of the first language according to the preset synthesis information, synthesizes the voice information into the final first language, and uses the voice information of the final first language to The form of the voice stream is returned to the VOLTE terminal.

 [0056] In other embodiments, the identification, translation, and synthesis processing of the voice information of the original second language may also be performed by one server. For example, the VOLTE terminal transmits the voice information of the original second language to the server, and the server identifies, translates, and synthesizes the voice information, and returns the voice information to the VOLTE terminal. In other embodiments, the identification, translation, and composition processing of the speech information of the original second language may also be performed by two servers. For example, the VOLTE terminal sends the voice information of the original second language to the first server, and the first server identifies and translates the voice information and returns the voice information to the VOLTE terminal, and the VOLT E terminal sends the voice information after the identification and translation processing. The second server sends the voice information to the VOLTE terminal. For another example, the VOLTE terminal sends the voice information of the original second language to the first server, and the first server returns the voice information to the VOLTE terminal, and the VOLTE terminal sends the voice information after the identification processing to the second server. The second server translates and synthesizes the voice information and returns it to the VOLTE terminal.

 [0057] S17. Receive voice information of the final first language returned by the server.

 [0058] S18. Output voice information of the final first language.

 [0059] after receiving the voice information of the final first language returned by the server, the VOLTE terminal processes the voice information of the final first language through the audio path, and finally outputs the final first language through the sounding device (handset, speaker, etc.) The voice information, the local user in the first language can understand what the opposite user said.

 [0060] In this embodiment, the received voice information of the peer user is further sent to the server for translation processing, and the voice information that can be recognized by the local user is translated, and the translated voice information is output, so that the local user can Understand the voice of the opposite user. Therefore, even if the peer end is an ordinary terminal, remote voice communication can be realized for users using different languages, which greatly expands the application range and further reduces the communication cost.

 [0061] A third embodiment of the voice call method of the present invention is proposed, and the method includes the following steps:

[0062] S21. Receive voice information of the original second language sent by the opposite end.

[0063] S22: Send the voice information of the original second language to the server for translation processing, so that the server will The speech information of the second language is translated into speech information of the final first language.

[0064] S23. Receive voice information of the final first language returned by the server.

[0065] S24. Output voice information of the final first language.

 [0066] In this embodiment, the steps S21 to S24 are the same as the steps S15-S18 in the second embodiment, and details are not described herein again.

 The voice call method of the embodiment of the present invention transmits the voice information of the received peer user to the server for translation processing, translates the voice information that the local user can recognize, and then outputs the translated voice information, so that The local user can understand the voice of the peer user. Thereby, the translation function is added to the communication terminal, so that users who use different languages realize remote voice communication, which solves the technical problem that the users who use different languages cannot communicate remotely through the communication terminal, reduces the communication cost, and improves the user experience.

 [0068] Further, in the fourth embodiment of the voice call method of the present invention, after step S24, the following steps are further included:

 [0069] S25. Acquire voice information of the original first language.

 [0070] S26: Send the voice information of the original first language to the server for translation processing, so that the server translates the voice information of the first language into the voice information of the final second language.

[0071] S27. Receive voice information of the final second language returned by the server.

[0072] S28. Send the voice information of the final second language to the peer end.

 [0073] In this embodiment, the steps S25-S28 are respectively related to the steps S11-S14 in the first embodiment, and details are not described herein again.

 [0074] In this embodiment, the collected voice information of the local user is further sent to the server for translation processing, translated into voice information that the peer user can recognize, and then the translated voice information is sent to the peer end, so that The peer user can understand the voice of the local user. Therefore, even if the peer end is an ordinary terminal, remote voice communication can be realized for users using different languages, which greatly expands the application range and further reduces the communication cost.

In the embodiment of the present invention, the first embodiment and the third embodiment may be applied to the application scenario shown in FIG. 1 , where the VOLTE terminal A and the VOLTE terminal B pass the IP multimedia subsystem (IP Multimedia Subsys tern, IMS). The network establishes a connection, and VOLTE terminal A and VOLTE terminal B are respectively connected to the voice recognition The other server, the translation server, and the voice synthesizing server, the VOLTE terminal A and the VOLTE terminal B both use the voice call method of the first embodiment or the second embodiment to perform a voice call, so that users in different languages can implement remote voice communication.

 [0076] The second embodiment and the fourth embodiment can be applied to the application scenarios as shown in FIGS. 2 to 4. In FIG. 2, the VOL TE terminal A and the voice terminal B establish a connection through the IMS network, and the VOLTE terminal A is respectively connected to the voice recognition server, the translation server and the voice synthesis server, and the VOLTE terminal A uses the second embodiment or the third embodiment. The voice call method and the voice terminal B make a voice call so that users in different languages can realize remote voice communication. In Figure 3, the VOLTE terminal A connects to the IMS network and the gateway of the 2G/3G network through the IMS network, and the voice terminal B connects the IMS network and the gateway of the 2G/3G network through the 2G/3G network, and the VOLTE terminal A is respectively connected to the voice recognition server, and the translation The server and the voice synthesizing server, the VO LTE terminal A uses the voice call method of the second embodiment or the third embodiment to make a voice call with the voice terminal B, so that users in different languages can realize remote voice communication. In Figure 4, the VOLTE terminal A connects to the IMS network and the public switched telephone network (PSTN) gateway through the IMS network, the voice terminal B connects the IMS network and the PSTN gateway through the PSTN, and the VOLTE terminal A is connected to the voice recognition respectively. The server, the translation server, and the voice synthesizing server, the VO LTE terminal A uses the voice call method of the second embodiment or the third embodiment to make a voice call with the voice terminal B, so that users in different languages can implement remote voice communication.

 [0077] The processing delay of the speech recognition server is generally less than 3 seconds, the processing delay of the translation server is generally less than 200 milliseconds, the processing delay of the speech synthesis server is generally less than 200 milliseconds, and the delay of the transmission of the IMS network is generally second. Therefore, using the high-rate and low-latency characteristics of LTE communication, the multi-language real-time translation function during voice call is implemented on the VOLTE terminal, and the voice translation processing speed is fast, the delay is small, and the call of the user is not affected, thereby Enables remote, accessible voice communication for users in different languages.

 Referring to FIG. 5, a first embodiment of a voice call device of the present invention is provided. The device includes an information collection module 10, a first translation processing module 20, a first information receiving module 30, and an information sending module 40, where:

[0079] The information collection module 10 is configured to collect voice information of the original first language. The first translation processing module 20 is configured to send the voice information of the original first language to the server for translation processing, so that the server translates the voice information of the original first language into the voice information of the final second language. First information receiving mode Block 30 is arranged to receive the voice information of the final second language returned by the server. The information sending module 40 is configured to send the voice information of the final second language to the opposite end. In the embodiment of the present invention, the language used by the VOLTE terminal user is the first language, and the language used by the peer user is the second language. When the VOLTE terminal is used as the transmitting end, the information collecting module 10 collects the voice information of the original first language of the user through the microphone. The first translation processing module 20 may send the voice information of the original first language to the server directly as a voice data stream. Preferably, the first translation processing module 20 subdivides the voice information of the original first language in the form of a data packet. Sent to the server. For example, the first translation processing module 20 first records the voice information of the original first language, records the voice files into a single voice file, and caches them, and then sequentially sends each cached voice file to the server in the form of a data packet.

 [0080] The translation process mainly includes three processes of identification, translation and synthesis. The three processes can be completed by one server or by two or three servers.

 [0081] In the embodiment of the present invention, the server includes a voice recognition server, a translation server, and a voice synthesis server. The VOLTE terminal establishes an IP-based communication connection with the voice recognition server, and sets the identification information through the first setting module, that is, the language type to be recognized, including the local language type (first language), and may further include the language type of the opposite end (first The second language); establishes an IP-based connection with the translation server, and sets the translation information through the second setting module, that is, the language to be translated, including the local-to-peer mapping, and may further include the peer-to-end mapping; The server establishes a connection based on IP communication, and sets the synthesized information through the third setting module, that is, the type of speech synthesis, such as male and female voice, speech rate, and the like.

 As shown in FIG. 6, the first translation processing module 20 includes a first transmitting unit 21, a first receiving unit 22, a second transmitting unit 23, a second receiving unit 24, and a third transmitting unit 25, where:

[0083] The first transmitting unit 21 is configured to transmit the voice information of the original first language to the voice recognition server, so that the voice recognition server recognizes the voice information as a character string of the first language. The first sending unit 21 first performs recording processing on the voice information of the original first language, records the voice files as a single voice file, and buffers, and then sequentially sends each cached voice file to the voice recognition server in the form of a data packet. After receiving the voice file, the voice recognition server identifies the voice file according to the preset identification information, recognizes the character string as the first language, and returns the character string of the first language to the VOLTE terminal. The first receiving unit 22 is arranged to receive a character string of the first language returned by the voice recognition server. Second send order The element 23 is arranged to send a string of the first language to the translation server to cause the translation server to translate the string of the first language into a string of the second language. After receiving the character string of the first language, the second transmitting unit 23 transmits the character string of the first language to the translation server. After receiving the string of the first language, the translation server translates the string of the first language according to the preset translation information, translates the string into the second language, and returns the string of the second language to the VOLTE. terminal. The second receiving unit 24 is arranged to receive a character string of the second language returned by the translation server. The third transmitting unit 25 is arranged to transmit the character string of the second language to the speech synthesis server such that the speech synthesis server synthesizes the character string of the second language into the speech information of the final second language. After receiving the character string of the second language, the third transmitting unit 25 transmits the character string of the second language to the speech synthesis server. After receiving the character string in the second language, the speech synthesis server synthesizes the character string of the second language according to the preset synthesis information, synthesizes the speech information into the final second language, and finally the voice information of the second language is The form of the voice stream is returned to the VOLTE terminal.

 [0084] In other embodiments, the identification, translation, and synthesis processing of the voice information of the original first language may also be performed by one server. For example, the first translation processing module 20 transmits the voice information of the original first language to the server, and the server identifies, translates, and synthesizes the voice information and returns it to the VOLTE terminal. In other embodiments, the identification, translation, and synthesis processing of the speech information of the original first language may also be performed by two servers. For example, the first translation processing module 20 sends the voice information of the original first language to the first server, and the first server identifies and translates the voice information and returns the result to the V OLTE terminal, where the first translation processing module 20 identifies And the voice information after the translation processing is sent to the second server, and the second server combines the voice information and returns to the VOLTE terminal. For another example, the first translation processing module 20 sends the voice information of the original first language to the first server, and the first server performs the identification process and returns the voice information to the VOLTE terminal, and the first translation processing module 20 further identifies the processing. The voice information is sent to the second server, and the second server translates and synthesizes the voice information and returns it to the VOLTE terminal.

The voice call device of the embodiment of the present invention transmits the voice information of the local user of the collection to the server for translation processing, translates the voice information that can be recognized by the peer user, and then sends the translated voice information to the voice message. The peer end enables the peer user to understand the voice of the local user. Therefore, the translation function is added to the communication terminal, so that users who use different languages realize remote voice communication, and the use is different. Language users can't communicate technical problems with remote voice communication through communication terminals, which reduces communication costs and improves user experience.

 Referring to FIG. 7, a second embodiment of a voice call device of the present invention is provided. The device includes a second information receiving module 50, a second translation processing module 60, a third information receiving module 70, and an information output module 80, wherein The second information receiving module 50 is configured to receive the voice information of the original second language sent by the opposite end. When the V OLTE terminal is used as the receiving end, the second information receiving module 50 receives the voice information of the original second language sent by the opposite end of the transmitting end through the voice channel. The second translation processing module 60 is arranged to transmit the voice information of the original second language to the server for translation processing, so that the server translates the voice information of the original second language into the voice information of the final first language. The second translation processing module 60 may directly transmit the voice information of the original second language to the server as a voice data stream. Preferably, the second translation processing module 60 segments the voice information of the original second language in the form of a data packet. Sent to the server. For example, the second translation processing module 60 first performs recording processing on the voice information of the original second language, records the voice files as a single voice file, and caches them, and then sequentially sends each cached voice file to the server in the form of a data packet.

 [0087] In the embodiment of the present invention, the server includes a voice recognition server, a translation server, and a voice synthesis server. The VOLTE terminal establishes an IP-based communication connection with the voice recognition server, and sets the identification information through the first setting module, that is, the language type to be recognized, including the language type of the opposite end (second language), and may further include the local language type (first) a language); establishing a connection based on the IP communication with the translation server, setting the translation information through the second setting module, that is, the language to be translated, including the mapping of the peer to the local end, and further including the mapping of the local end to the opposite end; and speech synthesis The server establishes a connection based on IP communication, and sets the synthesized information through the third setting module, that is, the type of speech synthesis, such as male and female voice, speech rate, and the like.

As shown in FIG. 8, the second translation processing module 60 includes a fourth transmitting unit 61, a third receiving unit 62, a fifth transmitting unit 63, a fourth receiving unit 64, and a sixth transmitting unit 65, where: The transmitting unit 61 is arranged to transmit the voice information of the original second language to the voice recognition server such that the voice recognition server recognizes the voice information as a character string of the second language. The fourth sending unit 61 first performs recording processing on the voice information of the original second language, records the voice files into a single voice file, and buffers them, and then sequentially sends each cached voice file to the voice recognition server in the form of a data packet. Received by the speech recognition server After the voice file, the voice file is identified according to the preset identification information, recognized as a character string of the second language, and the character string of the second language is returned to the VOLTE terminal. The third receiving unit 62 is arranged to receive a character string of the second language returned by the voice recognition server. The fifth transmitting unit 63 is arranged to transmit the character string of the second language to the translation server to cause the translation server to translate the character string of the second language into a character string of the first language. After receiving the character string of the second language, the fifth transmitting unit 63 transmits the character string of the second language to the translation server. After receiving the character string in the second language, the translation server translates the character string of the second language according to the preset translation information, translates the character string into the first language, and returns the character string of the first language to VOLTE. terminal. The fourth receiving unit 64 is arranged to receive a character string of the first language returned by the translation server. The sixth transmitting unit 65 is arranged to transmit the character string of the first language to the speech synthesis server such that the speech synthesis server synthesizes the character string of the first language into the speech information of the final first language. After receiving the character string of the first language, the sixth transmitting unit 65 transmits the character string of the first language to the speech synthesis server. After receiving the character string in the first language, the speech synthesis server synthesizes the character string of the first language according to the preset synthesis information, synthesizes the voice information into the final first language, and uses the voice information of the final first language to The form of the voice stream is returned to the VOLTE terminal.

In other embodiments, the identification, translation, and synthesis processing of the voice information of the original second language may also be performed by a server. For example, the second translation processing module 60 transmits the voice information of the original second language to the server, and the server identifies, translates, and synthesizes the voice information, and returns the result to the VOLTE terminal. In other embodiments, the identification, translation, and synthesis processing of the speech information of the original second language may also be performed by two servers. For example, the second translation processing module 60 sends the voice information of the original second language to the first server, and the first server identifies and translates the voice information and returns the result to the V 0LTE terminal, where the second translation processing module 60 identifies And the voice information after the translation processing is sent to the second server, and the second server combines the voice information and returns to the VOLTE terminal. For another example, the second translation processing module 60 sends the voice information of the original second language to the first server, and the first server performs the identification process and returns the voice information to the VOLTE terminal, and the second translation processing module 60 performs the identification process. The voice information is sent to the second server, and the second server translates and synthesizes the voice information and returns it to the VOLTE terminal. The third information receiving module 70 is configured to receive the voice information of the final first language returned by the server. The information output module 80 is configured to output the voice of the final first language Information. After receiving the voice information of the final first language returned by the server, the information output module 80 processes the voice information of the final first language through the audio path, and finally outputs the final first through the sounding device (handset, speaker, etc.) The voice information of the language, the local user who uses the first language can understand what the opposite user said.

[0090] The voice call apparatuses of the foregoing first embodiment and the second embodiment can be applied to the application scenario as shown in FIG. 1.

 The voice call device of the embodiment of the present invention transmits the voice information of the received peer user to the server for translation processing, translates the voice information that the local user can recognize, and then outputs the translated voice information, so that The local user can understand the voice of the peer user. Thereby, the translation function is added to the communication terminal, so that users who use different languages realize remote voice communication, which solves the technical problem that the users who use different languages cannot communicate remotely through the communication terminal, reduces the communication cost, and improves the user experience.

 Further, as shown in FIG. 9, the voice communication devices of the foregoing first embodiment and the second embodiment may be combined to form the voice communication device of the third embodiment. The voice call device can not only translate the voice information collected by the local end but also send the voice information to the opposite end, and can also translate the voice information sent by the opposite end and then output the voice information, so that even if the opposite end is an ordinary voice terminal, The ability to implement remote voice communication for users using different languages greatly expands the scope of application and further reduces communication costs.

 [0093] The voice call device of this embodiment can be applied to the application scenario as shown in FIG. 2 to FIG. 4.

Claims

[Claim 1] A voice call method includes the following steps:  Collecting voice information in the original first language;  Transmitting the voice information of the original first language to a server for translation processing, so that the server translates the voice information of the original first language into voice information of a final second language;  Receiving voice information of the final second language returned by the server;  Transmitting the voice information of the final second language to the peer end. [Claim 2] The voice call method according to claim 1, wherein the server includes a voice recognition server, a translation server, and a voice synthesis server, and the voice information in the first language is sent to a server for translation processing. The step of: transmitting the voice information of the original first language to a voice recognition server, so that the voice recognition server recognizes the voice information as a character string of a first language; receiving the returned by the voice recognition server a character string of the first language; sending the character string of the first language to the translation server, so that the translation server translates the character string of the first language into a character string of the second language;  Receiving a character string of the second language returned by the translation server;  Transmitting the character string of the second language to the speech synthesis server, so that the speech synthesis server synthesizes the character string of the second language into the speech information of the final second language [Claim 3] The voice call method according to claim 1, wherein the method further comprises: receiving voice information of the original second language sent by the opposite end; transmitting voice information of the original second language Translating processing to the server, so that the server translates the voice information of the original second language into voice information of the final first language;  Receiving the voice information of the final first language returned by the server;  The voice information of the final first language is output. [Claim 4] The voice call method according to claim 3, wherein the server includes voice recognition The server, the translation server, and the voice synthesizing server, the step of transmitting the voice information of the original second language to the server for translation processing includes:  Transmitting the voice information of the original second language to a voice recognition server, so that the voice recognition server recognizes the voice information as a character string of a second language; receiving the second language returned by the voice recognition server a string of the second language is sent to the translation server to cause the translation server to translate the string of the second language into a string of the first language;  Receiving a character string of the first language returned by the translation server;  Transmitting the character string of the first language to the speech synthesis server, so that the speech synthesis server synthesizes the character string of the first language into the speech information of the final first language [Claim 5] The voice call method according to claim 1, wherein the method is applied to VOLTE  terminal.  [Claim 6] A voice call method includes the following steps:  Receiving voice information of the original second language sent by the opposite end;  Transmitting the voice information of the original second language to a server for translation processing, so that the server translates the voice information of the original second language into a language first of the final first language;  Receiving the voice information of the final first language returned by the server;  The voice information of the final first language is output. [Claim 7] The voice call method according to claim 6, wherein the server includes a voice recognition server, a translation server, and a voice synthesis server, and the voice information of the original second language is sent to a server for translation. The steps of processing include: Transmitting the voice information of the original second language to a voice recognition server, so that the voice recognition server recognizes the voice information as a character string of a second language; receiving the second language returned by the voice recognition server a string of the second language is sent to the translation server to cause the translation server to translate the string of the second language into a string of the first language; Receiving a character string of the first language returned by the translation server;  Transmitting the character string of the first language to the speech synthesis server, so that the speech synthesis server synthesizes the character string of the first language into the speech information of the final first language [Claim 8] The voice call method according to claim 6, wherein the method further comprises: collecting voice information of the original first language;  Transmitting the voice information of the original first language to a server for translation processing, so that the server translates the voice information of the first language into a voice of a final second language;  Receiving voice information of the final second language returned by the server;  Transmitting the voice information of the final second language to the peer. [Claim 9] The voice call method according to claim 6, wherein the method is applied to a VOLTE terminal.  [Claim 10] A voice call device, comprising: an information collecting module, a first translation processing module, a first information receiving module, and an information sending module,  The information collection module is configured to collect voice information in the original first language;  The first translation processing module is configured to send the voice information of the original first language to a server for translation processing, so that the server translates the voice information of the original first language into voice information of a final second language;  a first information receiving mode, configured to receive voice information of the final second language returned by the server;  The information sending module is configured to send the voice information of the final second language to the peer end. [Claim 11] The voice communication device according to claim 10, wherein the server comprises a voice recognition server, a translation server, and a voice synthesis server, and the first translation processing module includes: a first sending unit, configured to send the voice information of the original first language to a voice recognition server, so that the voice recognition server recognizes the voice information as a character string of a first language; a first receiving unit, configured to receive a character string of the first language returned by the voice recognition server;  a second sending unit, configured to send the character string of the first language to the translation server, so that the translation server translates the character string of the first language into a character string of a second language;  a second receiving unit, configured to receive the character string of the second language returned by the translation server;  And a third transmitting unit configured to send the character string of the second language to the speech synthesis server, so that the speech synthesis server synthesizes the character string of the second language into the speech information of the final second language. [Claim 12] The voice communication device according to claim 10, wherein the device further includes: a second information receiving module, configured to receive a voice fp of the original second language sent by the opposite end;  a second translation processing module, configured to send the voice information of the original second language to a server for translation processing, so that the server translates the voice information of the second language into voice information of a final first language;  a third information receiving module, configured to receive the voice information of the final first language returned by the server;  The information output module is configured to output the voice information of the final first language.  [Claim 13] The voice communication device according to claim 12, wherein the server includes a voice recognition server, a translation server, and a voice synthesis server, and the second translation processing module includes:  a fourth sending unit, configured to send the voice information of the original second language to the voice recognition server, so that the voice recognition server recognizes the voice information as a character string of the second language;  a third receiving unit, configured to receive a character string of the second language returned by the voice recognition server; a fifth sending unit, configured to send the character string of the second language to the translation service So that the translation server translates the string of the second language into a string of the first language;  a fourth receiving unit, configured to receive the character string of the first language returned by the translation server;  The sixth transmitting unit is configured to transmit the character string of the first language to the speech synthesis server, so that the speech synthesis server synthesizes the character string of the first language into the speech information of the final first language. [Claim 14] The voice communication device according to claim 10, wherein the device is applied to VOLT  E terminal.  [Claim 15] A voice communication device, comprising:  a second information receiving module, configured to receive the voice fn of the original second language sent by the opposite end;  a second translation processing module, configured to send the voice information of the original second language to a server for translation processing, so that the server translates the voice information of the original second language into voice information of a final first language ;  a third information receiving module, configured to receive the voice information of the final first language returned by the server;  The information output module is configured to output the voice information of the final first language.  [Claim 16] The voice communication device according to claim 15, wherein the server includes a voice recognition server, a translation server, and a voice synthesis server, and the second translation processing module includes:  a fourth sending unit, configured to send the voice information of the original second language to the voice recognition server, so that the voice recognition server recognizes the voice information as a character string of the second language;  a third receiving unit, configured to receive a character string of the second language returned by the voice recognition server; a fifth sending unit, configured to send the character string of the second language to the translation server, so that the translation server translates the character string of the second language into a first language String  a fourth receiving unit, configured to receive the character string of the first language returned by the translation server;  The sixth transmitting unit is configured to transmit the character string of the first language to the speech synthesis server, so that the speech synthesis server synthesizes the character string of the first language into the speech information of the final first language. [Claim 17] The voice communication device according to claim 15, wherein the device further comprises: an information collection module, configured to collect voice information in the original first language;  a first translation processing module, configured to send the voice information of the original first language to a server for translation processing, so that the server translates the voice information of the first language into voice information of a final second language;  a first information receiving module, configured to receive voice information of the final second language returned by the server;  The information sending module is configured to send the voice information of the final second language to the peer end. [Claim 18] The voice communication device according to claim 15, wherein the device is applied to VOLT  E terminal.