TW201306536A - Multi-language recognition and translation screen display system applied to voice over Internet protocol - Google Patents

Abstract

There is provided a multi-language recognition and translation screen display system applied to voice over Internet protocol (VoIP), which comprises a plurality of network communication devices, each including a setting unit, a voice over Internet protocol unit, a recognition unit and a translation unit. The setting unit sets the language type. The voice over Internet protocol unit sends or receives text or voice messages and converts them into recognition request messages. The recognition unit recognizes the recognition request messages. When the language types are the same, the text or voice messages are exhibited by the voice over Internet protocol unit. When the language types are different, the recognition request messages are converted into translation request messages. The translation unit receives the translation request messages and, after translating them into the desired language, sends the translated voice and text messages to the voice over Internet protocol unit, so as to show the translated voice and text by captions. Therefore, the present system can reduce language gaps.

Description

Multi-country speech recognition and translation screen imaging system applied to network protocol voice

The invention relates to a multi-country speech recognition and translation screen imaging system applied to network protocol speech, and can execute a multi-national speech recognition and translation system and presents in subtitles.

With the development of the network, Voice over Internet Protocol (VOIP), such as SKYPE software, has gradually changed the way of traditional telephone communication by transmitting voice and video through the network, and because of the low cost and huge potential market It is already a battleground for the current network communication.

However, although the network protocol voice now provides the convenience of the network without borders, there is still a lack of a system for instantly converting voice and translating text. Therefore, if a voice recognition and translation system for voice of a network protocol can be developed, The network protocol voice system will be more closely linked to future business and community.

The main object of the present invention is to provide a voice recognition and translation system for network protocol voice, the system mainly includes a plurality of network communication devices, and each of the network communication devices includes a setting unit and a network protocol. Voice over Internet Protocol (VOIP) unit, identification unit, and translation unit.

The setting unit sends a language setting message to the VOIP unit and a voice decision message to the identification unit for the language required for the VOIP unit setting, and the VOIP unit is used to send a text message or a voice message to another network communication device, or from another The VOIP unit of the network communication device receives a text message or a voice message, and converts the received text message or voice message into an identification request message and transmits the message to the identification unit, and the identification unit receives the identification request message, and recognizes the identification message. When the language of the request message is the same as the language set by the voice decision message, a message identifying the same message is sent to the VOIP unit, and the text message or voice message is directly presented on the VOIP unit, and the language and voice of the identification request message are recognized. When the language of the message setting is different, the identification message is converted into a translation request message according to the language determined by the voice decision message, and the translation unit receives the translation request message and translates the translation request message into a desired message. After the language, send a translated voice and text message to VOIP The unit thus presents the translated speech and text on the VOIP unit.

The network communication device can be a mobile phone, a personal computer, a notebook computer, a tablet computer, a personal digital assistant (PDA), etc., and further, can communicate through a server device, or on a server device. Perform identification and/or translation work to obtain more stable bandwidth and changes in various communication structures.

The invention is characterized in that the common VOIP can directly cooperate with the voice/text and translation identification system, and when the user receives the text message or the voice message, the VOIP unit can be used in the VOIP unit by the identification unit and the translation unit. The set language and text are displayed, and thus various language barriers of the world can be minimized by applying the present invention to a voice recognition and translation system for voice over internet protocols.

The implementation of the present invention will be described in more detail below with reference to the drawings and component symbols, so that those skilled in the art can implement the present specification after studying the present specification.

Referring to the first figure, a block diagram of a multi-national speech recognition and translation screen display system for a network protocol voice is applied to a first embodiment of the present invention. As shown in the first figure, the first embodiment of the present invention is applied to a network protocol voice multi-national voice recognition and translation screen display system 1 comprising a plurality of network communication devices 10A, 10B, network communication devices 10A, 10B. Each of them includes a setting unit 11, a Voice over Internet Protocol (VOIP) unit 13, an identification unit 15 and a translation unit 17, and the setting unit 11 sets a language required for the VOIP unit 13, and issues a language setting. The message to the VOIP unit 13 and a voice decision message to the identification unit 15, the VOIP unit 13 of the network communication device 10A is used to send a text message or a voice message to another network communication device 10B, or from another network communication device. The VOIP unit 13 of the 10B receives a text message or a voice message, and converts the received text message or voice message into an identification request message and transmits the message to the identification unit 15. The identification unit 15 receives the identification request message, and recognizes the identification request. When the language of the message is the same as the language set by the voice decision message, a message identifying the same message is sent to the VOIP unit 13, and the text message or voice message is transmitted. The subtitles are presented directly on the VOIP unit 13, and the speech is further presented at the same time. When the language in which the identification request message is recognized is different from the language in which the speech determination message is set, the identification message is determined according to the language determined by the speech determination message. Converting to a translation request message and issuing, the translation unit 17 receives the translation request message, and translates the translation request message into a desired language, and then sends a translated voice and text message to the VOIP unit 13, thereby being in the VOIP unit. The 13th uploading presents the translated subtitles, and further presents the voices simultaneously. The network communication devices 10A, 10B can be mobile phones, personal computers, notebook computers, tablet computers, personal digital assistants (PDAs), and the like.

Referring to the second figure, a second embodiment of the present invention is applied to a block diagram of a multi-country speech recognition and translation screen development system for network protocol speech. As shown in the second figure, the main difference between the second embodiment and the first embodiment is that the communication of the network communication devices 10A, 10B is performed by the server device 30, and the second embodiment is applied to the network protocol voice. The multi-national speech recognition and translation system 2 includes network communication devices 10A, 10B and a server device 30. The structure of the network communication devices 10A, 10B is the same as that of the first embodiment, and will not be described here. The difference between the first embodiment and the second embodiment is that the VOIP unit 13 of the network communication device 10A sends a text message or a voice message to the communication unit 31, and then transmits the message through the communication unit 31. A text message or a voice message to the VOIP unit of the other network communication device 10B is also received through the communication unit 31.

Referring to the third figure, a block diagram of a multi-national speech recognition and translation screen display system for network protocol speech is applied to a third embodiment of the present invention. As shown in the third figure, the purpose of the third embodiment is to combine the first embodiment with the second embodiment. The network communication devices 10A, 10B of the third embodiment can combine the point-to-point communication method of the first embodiment, and The second embodiment has two communication streams in the manner of the communication unit 31.

Referring to the fourth figure, a fourth embodiment of the present invention is applied to a block diagram of a multi-country speech recognition and translation screen development system for network protocol speech. As shown in the fourth figure, the fourth embodiment of the present invention is applied to a network protocol voice multi-national voice recognition and translation screen display system 4 including a plurality of network communication devices 20A, 20B and a server device 32, and network communication. Each of the devices 20A, 20B includes a setting unit 21 and a VOIP unit 23. The server device 32 includes a communication unit 31, an identification unit 33, and a translation unit 35. The main difference from the third embodiment is that the fourth embodiment is By performing the recognition and translation operations on the server device 32, the setting unit 21 sets the desired language for the VOIP unit 23, and sends a language setting message to the VOIP unit 23 and a voice decision message to the identification unit of the server device 32. The VOIP unit 23 is configured to send a text message or a voice message to the communication unit 31 of the server device 32. The communication unit 31 converts the received text message or voice message into an identification request message and sends the message to the identification unit 33. The identification unit 33 receives the identification request message, and transmits an identification phase when the language identifying the identification request message is the same as the language set by the voice determination message. The same message is sent to the communication unit 31, and the communication unit directly transmits the text message or the voice message directly to the VOIP unit 23 of the other network communication device 20B to present the subtitles, and further simultaneously presents the speech, and when the identification is recognized When the language of the request message is different from the language set by the voice decision message, the identification message is converted into a translation request message and sent according to the language determined by the voice decision message, and the translation unit 35 receives the translation request message and translates the message. The voice and text message is sent to the communication unit 31, and the translated voice and text message is sent by the communication unit 31 to the VOIP unit 23 of the other network communication device 20B, so that the translated subtitle is presented on the VOIP unit 23. The translated speech is also presented at the same time.

Referring to the fifth figure, a block diagram of a multi-national speech recognition and translation screen display system for a network protocol voice is applied to a fifth embodiment of the present invention. As shown in FIG. 5, the fifth embodiment of the present invention is applied to a network protocol voice multi-national voice recognition and translation screen display system 5 including a plurality of network communication devices 22A, 22B and a server device 34, and network communication. Each of the devices 22A, 22B includes a setting unit 21, a VOIP unit 23, and an identification unit 25, and the server device 34 includes a communication unit 31 and a translation unit 35. The setting unit 21 sets a language required for the VOIP unit 23, and issues a language. The message is sent to the VOIP unit 23 and a voice decision message to the identification unit 25. The VOIP unit 23 of the network communication device 22A is configured to send a text message or a voice message to the communication unit 31 of the server device 34, and the communication unit 31 will receive the message. The received text message or voice message is converted into an identification request message and sent to the identification unit 33 of the network communication device 22B. The identification unit 33 receives the identification request message, and recognizes the language of the recognition request message and the language of the voice determination message setting. In the same case, a message identifying the same message is sent to the communication unit 31, and the communication unit directly directly sends the text message or the voice message directly. The VOIP unit 23 sent to the other network communication device 22B presents the subtitles, and further presents the speech at the same time, and when the language identifying the identification request message is different from the language set by the voice decision message, it is determined according to the voice decision message. The language, the identification message is converted into a translation request message and sent, the translation unit 35 of the server device 34 receives the translation request message, and sends the translated voice and text message to the communication unit 31, where the communication unit 31 The translated voice and text messages are sent to the VOIP unit 23 of the other network communication device 22B, thereby presenting the translated subtitles on the VOIP unit 23, and further presenting the translated speech.

Referring to the sixth figure, a sixth embodiment of the present invention is applied to a block diagram of a multi-country speech recognition and translation screen development system for network protocol speech. As shown in the sixth figure, the sixth embodiment of the present invention is applied to a network protocol voice multi-national voice recognition and translation screen display system 6 including a plurality of network communication devices 24A, 24B and a server device 36 for network communication. Each of the devices 20A, 20B includes a setting unit 21, a VOIP unit 23, and a translation unit 27. The server device 32 includes a communication unit 31 and an identification unit 33. The setting unit 21 sets a desired language for the VOIP unit 23. Sending a language setting message to the VOIP unit 23 and a voice decision message to the identification unit 33 of the server device 6, the VOIP unit 23 of the network communication device 24A is configured to send a text message or a voice message to the server device 36 for communication. The unit 31 converts the received text message or voice message into an identification request message and sends it to the identification unit 33. The identification unit 33 receives the identification request message, and recognizes the language and voice determination message of the identification request message. When the set language is the same, a message identifying the same message is sent to the communication unit 31, and the communication unit directly sends the text message or the voice message. The VOIP unit 23 transmitted to the other network communication device 24B presents the subtitles, and further presents the speech at the same time. When the language identifying the identification request message is different from the language set by the voice decision message, the message is determined according to the voice. Determining the language, converting the identification message into a translation request message and sending, the translation unit 27 of the network communication device 24B receives the translation request message, and transmits the translated voice and text message to the other network communication device 24B. The VOIP unit 23, thereby presenting the translated subtitles on the VOIP unit 23, further presents the translated speech at the same time.

The invention is characterized in that the common VOIP can directly cooperate with the voice/text and translation identification system, and when the user receives the text message or the voice message, the VOIP unit can be used in the VOIP unit by the identification unit and the translation unit. The set language and text are displayed in subtitles, and thus various language barriers of the world can be minimized by the present invention applied to the speech recognition and translation system of the network protocol speech.

The various information in the present invention may be a digital signal or an analog signal. The manner of transmitting the message includes using a streamer and a packet, and the overall system architecture is a Session Initiation Protocol (SIP) or It is a variety of peer-to-peer (P2P) communication, for example, anonymous peer-to-peer, structured peer-to-peer, unstructured peer-to-peer communication (Unstructured peer-to- Peer), pure peer-to-peer communication, hybrid peer-to-peer communication, and centralized peer-to-peer communication. The above is only an exemplification, but it is not intended to limit the invention, but those skilled in the art can extend or improve the combination of the teachings of the present invention and the conventional techniques.

The above is only a preferred embodiment for explaining the present invention, and is not intended to limit the present invention in any way, and any modifications or alterations to the present invention made in the spirit of the same invention. All should still be included in the scope of the intention of the present invention.

1. . . Multi-country speech recognition and translation screen imaging system applied to network protocol voice

2. . . Multi-country speech recognition and translation screen imaging system applied to network protocol voice

3. . . Multi-country speech recognition and translation screen imaging system applied to network protocol voice

4. . . Multi-country speech recognition and translation screen imaging system applied to network protocol voice

5. . . Multi-country speech recognition and translation screen imaging system applied to network protocol voice

6. . . Multi-country speech recognition and translation screen imaging system applied to network protocol voice

10A. . . Network communication device

10B. . . Network communication device

11. . . Setting unit

13. . . Network protocol speech unit

15. . . Identification unit

17. . . Translation unit

20A. . . Network communication device

20B. . . Network communication device

twenty one. . . Setting unit

22A. . . Network communication device

22B. . . Network communication device

twenty three. . . Network protocol speech unit

24A. . . Network communication device

24B. . . Network communication device

25. . . Identification unit

27. . . Translation unit

30. . . Server device

31. . . Communication unit

32. . . Server device

33. . . Identification unit

34. . . Server device

35. . . Translation unit

36. . . Server device

The first figure is a block diagram of a multi-national speech recognition and translation screen display system for a network protocol voice according to a first embodiment of the present invention.

Second Embodiment A block diagram of a multi-national speech recognition and translation screen display system for a network protocol voice is applied to a second embodiment of the present invention.

Third Embodiment A block diagram of a multi-national speech recognition and translation screen display system for a network protocol voice according to a third embodiment of the present invention.

FIG. 4 is a block diagram showing a fourth embodiment of the present invention applied to a multi-country speech recognition and translation screen development system for network protocol speech.

Figure 5 is a block diagram showing a multi-national speech recognition and translation screen display system for a network protocol voice according to a fifth embodiment of the present invention.

Figure 6 is a block diagram showing a sixth embodiment of the present invention applied to a multi-country speech recognition and translation screen development system for network protocol speech.

1. . . Multi-country speech recognition and translation screen imaging system applied to network protocol voice

10A. . . Network communication device

10B. . . Network communication device

11. . . Setting unit

13. . . Network protocol speech unit

15. . . Identification unit

17. . . Translation unit

Claims (14)

A multi-country speech recognition and translation screen display system for network protocol voice, comprising: a plurality of network communication devices, each of the network communication devices comprising: a setting unit, issuing a language setting message and a Voice determines the message to set the desired language; a network protocol voice unit receives the language setting message and sends a text message or a voice message to another network communication device, or from another network communication device network The agreement voice unit receives a text message or a voice message, and converts the received text message or voice message into an identification request message and transmits the same; an identification unit receives the language determination message and the identification request message, and recognizes the When the language of the request message is the same as the language set by the voice decision message, the same message is sent to the network protocol voice unit, and the text message or voice message is directly presented on the network protocol voice unit, and is recognized. When the language of the identification request message is different from the language set by the voice decision message, The voice determines the language set by the message, converts the identification message into a translation request message and sends it; and a translation unit receives the translation request message and translates the translation request message into a desired language, and then translates The voice and text messages are sent to the network protocol voice unit to present the translated voice and text on the network protocol voice unit. The system of claim 1, wherein the network communication device is at least one of a mobile phone, a personal computer, a notebook computer, a tablet computer, and a personal digital assistant. A multi-country speech recognition and translation screen imaging system for network protocol voice, comprising: a plurality of network communication devices; and a server unit comprising a communication unit; wherein each of the network communication devices comprises a setting unit that issues a language setting message and a voice decision message to set a desired language; a network protocol voice unit receives the language setting message and sends a text message or a voice message to the communication unit, or from the The communication unit receives a text message or a voice message from another network communication device, and converts the received text message or voice message into an identification request message and transmits the same; an identification unit receives the language decision message and the identification request a message, when the language identifying the identification request message is the same as the language set by the voice decision message, transmitting a message identifying the same message to the network protocol voice unit, and the text message or voice message is directly in the network protocol voice unit Presented on, and when the language of the identification request message is recognized and the voice decision message is set When the language is different, the identification message is converted into a translation request message and sent according to the language set by the voice decision message; and a translation unit receives the translation request message and translates the translation request message into a desired After the language, a translated voice and text message is sent to the network protocol voice unit, so that the translated voice and text are presented on the network protocol voice unit. The system of claim 3, wherein the network communication device is at least one of a mobile phone, a personal computer, a notebook computer, a tablet computer, and a personal digital assistant. The system of claim 3, wherein the network protocol voice unit of the network communication device is further capable of transmitting the text message or the voice message to the network protocol voice of another network communication device. And receiving the text message or the voice message from the network protocol voice unit of another network communication device. A multi-country speech recognition and translation screen imaging system for network protocol voice, comprising: a plurality of network communication devices, wherein the network communication device comprises a setting unit and a network protocol voice unit, the setting unit, Sending a language setting message and a voice decision message to set a desired language; the network protocol voice unit receiving the language setting message and transmitting a text message or a voice message; and a server device including a communication a unit, an identification unit, and a translation unit, the communication unit receives the text message or the voice message, and converts the received text message or voice message into an identification request message, and the identification unit receives the voice decision message and the Identifying the request message, when the language identifying the identification request message is the same as the language set by the voice decision message, transmitting a same message to the communication unit, and the communication unit directly directly sends the text message or the voice message directly Presented to the network communication device unit of another network communication device, and When the language of the identification request message is different from the language set by the voice decision message, the identification message is converted into a translation request message and sent according to the language determined by the voice decision message, and the translation unit receives the translation request. Sending a translated voice and text message to the communication unit, and then transmitting, by the communication unit, a translated voice and text message to the network protocol voice unit of another network communication device, thereby The translated speech unit is presented with translated speech and text. The system of claim 6, wherein the network communication device is at least one of a mobile phone, a personal computer, a notebook computer, a tablet computer, and a personal digital assistant. The system of claim 6, wherein the network protocol voice unit of the network communication device is further capable of transmitting the text message or the voice message to the network protocol voice of another network communication device. And receiving the text message or the voice message from the network protocol voice unit of another network communication device. A multi-country speech recognition and translation screen display system for network protocol voice, comprising: a plurality of network communication devices, each of the network communication devices comprising: a setting unit, issuing a language setting message and a a voice determining message; a network protocol voice unit receiving the language setting message for sending and receiving a text message or a voice message, and converting the received text message or voice message into an identification request message and transmitting; a translation unit, receiving the translation request message, and transmitting a translated voice and text message to the network protocol voice unit; and a server device comprising a communication unit and an identification unit, the communication unit receiving the text message or The voice message is sent to a network protocol voice unit of another network communication device, so that the translated voice and text are presented on the voice protocol voice unit, and the identification unit receives the identification request message and recognizes When the language of the identification request message is the same as the language of the voice decision message, an identification phase is transmitted. Sending a message to the communication unit, and the text message or the voice message is directly presented on the network protocol voice unit, and when the language identifying the identification request message is different from the language of the voice decision message, according to the voice Determining the language determined by the message, converting the identification message into a translation request message and sending it to the translation unit of the network communication device. The system of claim 9, wherein the network communication device is at least one of a mobile phone, a personal computer, a notebook computer, a tablet computer, and a personal digital assistant. The system of claim 9, wherein the network protocol voice unit of the network communication device is further capable of transmitting the text message or the voice message to the network protocol voice of another network communication device. And receiving the text message or the voice message from the network protocol voice unit of another network communication device. A multi-country speech recognition and translation screen display system for network protocol voice, comprising: a plurality of network communication devices, each of the network communication devices comprising: a setting unit, issuing a language setting message and a a voice determining message; a network protocol voice unit receiving the language setting message for sending and receiving a text message or a voice message, and converting the received text message or voice message into an identification request message and transmitting; The identification unit receives the identification request message, and when the language identifying the identification request message is the same as the language of the voice determination message, transmitting a same message to the network protocol voice unit, and the text message or the voice message is Directly presenting on the network protocol voice unit, and when the language identifying the identification request message is different from the language of the voice decision message, converting the identification message into a translation according to the language determined by the voice decision message Requesting a message and issuing; and a server device comprising a communication unit and a translation list Receiving, by the communication unit, the text message or the voice message, in a network protocol voice unit sent to another network communication device, to present the translated voice and text on the network protocol voice unit, the translation The unit receives the translation request message and sends a translated voice and text message to the network protocol voice unit. The system of claim 12, wherein the network communication device is at least one of a mobile phone, a personal computer, a notebook computer, a tablet computer, and a personal digital assistant. The system of claim 12, wherein the network protocol voice unit of the network communication device is further capable of transmitting the text message or the voice message to the network protocol voice of another network communication device. And receiving the text message or the voice message from the network protocol voice unit of another network communication device.