Distributed off-line voice services

• US 8,451,823 B2
• Filed: 12/13/2005
• Issued: 05/28/2013
• Est. Priority Date: 12/13/2005
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Ben-David, Shay, Hoory, Ron, Roytman, Alexey, Sivan, Zohar, Sliwa, James Jude
• Primary Examiner(s): Nawaz, Asad
• Assistant Examiner(s): JENSEN, NICHOLAS A
• Application Number:
  US11/301,434
• Publication Number:
  US 20070133518A1
• Time in Patent Office: 2,723 Days
• Field of Search: 370/352, 379/907, 379/88.01, 704/231
• US Class Current: 370/352
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: H04L 65/103 in the network
• CPC Class Codes: H04L 65/104 in the network
• CPC Class Codes: H04L 65/1069 Session establishment or de-establishment
• CPC Class Codes: H04L 65/1101 Session protocols
• CPC Class Codes: H04L 65/65 Network streaming protocols, e.g. real-time transport protocol [RTP] or real-time control protocol [RTCP]
• CPC Class Codes: H04M 2201/39 using speech synthesis speech synthesis per se G10L13/00
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2201/60 Medium conversion
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML

Abstract

A voice processing system includes a real-time voice server, which is arranged to process real-time voice processing tasks for clients of the system. A gateway processor is arranged to accept from a client a request to perform an off-line voice processing task, to convert the off-line voice processing task into an equivalent real-time voice processing task, to invoke the voice server to process the equivalent real-time voice processing task, and to output a result of the equivalent real-time voice processing task.

Claims

1. A voice processing system connected to at least one network, the voice processing system configured to communicate with a real-time voice server arranged to process real-time voice processing tasks received over the at least one network according to a first network communication protocol, the voice processing system comprising:

a gateway processor, arranged to accept from a client a request to perform an off-line voice processing task, the request received over the at least one network according to a second network communication protocol, the gateway processor configured to convert the off-line voice processing task into an equivalent real-time voice processing task of the first network communication protocol and to provide the equivalent real-time voice processing task to the real-time voice server over the at least one network according to the first network communication protocol for processing of the equivalent real-time voice processing task, the gateway processor further configured to output a result of the processing of the equivalent real-time voice processing task to the client.

2. The system according to claim 1, wherein the off-line voice processing task comprises a request to transcribe voice content, wherein the real-time voice server is arranged to convert the voice content to transcribed text, and wherein the gateway processor is arranged to output the result comprising the transcribed text.

3. The system according to claim 1, wherein the off-line voice processing task comprises a request to process textual information, wherein the real-time voice server is arranged to convert the textual information to synthesized speech, and wherein the gateway processor is arranged to output the result comprising the synthesized, speech.

4. The system according to claim 1, wherein the real-time voice server is arranged to apply any one of or any combination of two or more of an automatic speech recognition (ASR) process, a text-to-speech (TTS) conversion process, a speaker identification (SI) process and a speaker verification (SV) process so as to process the equivalent real-time voice processing task.

5. The system according to claim 1, wherein the real-time voice server and the gateway processor exchange control messages using a control protocol comprising one or more commands for handling off-line media.

6. The system according to claim 1, further comprising a media converter for converting between the second network communication protocol and/or a first media format associated with the off-line voice processing task and the first network communication protocol and/or a second media format associated with the equivalent real-time voice processing task.

7. The system according to claim 6, wherein the second media format comprises a voice data format supported by the voice server and the first media format comprises a voice data format for rich media or multimedia.

8. The system according to claim 6, wherein one of the first and second media formats comprises rich media comprising voice content grouped with additional content, and wherein the media converter is arranged to extract the voice content from the rich media content and/or embed the voice content into the rich media content.

9. The system according to claim 1, wherein the gateway processor is arranged to output the result of the equivalent real-time voice processing task by publishing the result and/or sending the result to the client over the at least one network.

10. The voice processing system of claim 1, wherein the first network communication protocol comprises a telephony-oriented protocol and the second network communication protocol comprises a web-access protocol.

11. The voice processing system of claim 10, wherein the first network communication protocol comprises a real-time transfer protocol (RTP) and/or a media resource control protocol (MRCP).

12. The voice processing system of claim 10, wherein the second network communication protocol comprises a hypertext transfer protocol (HTTP) or an internet protocol (IP).

13. The voice processing system of claim 1, wherein the result is sent to the client according to the second network communication protocol.

14. A gateway processor connected to at least one network, the gateway processor configured to operate in conjunction with a real-time voice server that is configured to process real-time voice processing tasks received over the at least one network according to a first network communication protocol, the gateway processor comprising:

a client interface which is arranged to receive from a client over the at least one network a request to perform an off-line voice processing task according to a second network communication protocol;

a media converter which is arranged to convert the off-line voice processing task into an equivalent real-time voice processing task of the first network communication protocol; and

a management module which is arranged to provide the equivalent real-time voice processing task to the real-time voice server over the at least one network according to the first network communication protocol for processing, by the real-time voice server, the equivalent real-time voice processing task, and to output a result of the processing of the equivalent real-time voice processing task to the client.

15. The gateway processor of claim 14, wherein the first network communication protocol comprises a telephony-oriented protocol and the second network communication protocol comprises a web-access protocol.

16. The gateway processor of claim 15, wherein the first network communication protocol comprises a real-time transfer protocol (RTP) and/or a media resource control protocol (MRCP).

17. The gateway processor of claim 15, wherein the second network communication protocol comprises a hypertext transfer protocol (HTTP) or an internet protocol (IP).

18. A method for voice processing, comprising:

receiving, over at least one network, a request from a client to perform an off-line voice processing task according to a first network communication protocol;

converting the off-line voice processing task of the first network communication protocol into an equivalent real-time voice processing task of a second network communication protocol;

providing the equivalent real-time voice processing task to a real-time voice server over the at least one network according to the second network communication protocol for processing the equivalent real-time voice processing task; and

outputting a result of the processing of the equivalent real-time voice processing task to the client.

19. The method according to claim 18, wherein accepting the request comprises accepting a request to transcribe voice content, wherein invoking the real-time voice server comprises requesting the real-time voice server to convert the voice content to transcribed text, and wherein outputting the result comprising outputting the transcribed text.

20. The method according to claim 18, wherein accepting the request comprises accepting a request to process textual information, wherein invoking the real-time voice server comprises requesting the real-time voice server to convert the textual information into synthesized speech, and wherein outputting the result comprising outputting the synthesized speech.

21. The method according to claim 18, wherein invoking the real-time voice server comprises causing the real-time voice server to apply one or any combination of two or more of an automatic speech recognition (ASR) process, a text-to-speech (TTS) conversion process, a speaker identification (SI) process and a speaker verification (SV) process so as to process the equivalent real-time voice processing task.

22. The method according to claim 18, wherein invoking the real-time voice server comprises exchanging control messages between the real-time voice server and the gateway processor using a control protocol comprising one or more commands for handling off-line media.

23. The method according to claim 18, wherein converting the off-line voice processing task into the equivalent real-time voice processing task comprises converting between the first network communication protocol and/or a first media format associated with the off-line voice processing task and the second network communication protocol and/or a second media format associated with the equivalent real-time voice processing task.

24. The method according to claim 23, wherein the second media format comprises a voice data format supported by the voice server and the first media format comprises a voice data format for rich media or multimedia.

25. The method according to claim 23, wherein one of the first and second media formats comprises rich media comprising voice content grouped with additional content, and wherein converting the media format comprises extracting the voice content from the rich media content and/or embedding the voice content into the rich media.

26. The method according to claim 18, wherein outputting the result of the equivalent real-time voice processing task comprises publishing the result and/or sending the result to the client over the at least one network.

27. The method of claim 18, wherein the converting the off-line task comprises receiving voice data and performing a format and protocol conversion to provide the voice data to the real-time voice server in accordance with a protocol and format supported by the real-time voice server;

and

the invoking the real-time voice server comprises formatting control information associated with the voice data and providing the formatted control information to the real-time voice server.

28. The method of claim 27, wherein the converting the off-line task comprises performing a protocol conversion to provide the voice data to the real-time voice server in accordance with a real time protocol (RTP).

29. The method of claim 27, wherein the converting the off-line task comprises performing a format conversion of the voice data to provide the voice data to the real-time voice server in real time protocol (RTP) data packets.

30. The method of claim 27, wherein the invoking the real-time voice server comprises formatting control information according to an extended media resource control protocol (MRCP⁺).

31. The method of claim 18, wherein the first network communication protocol comprises a telephony-oriented protocol and the second network communication protocol comprises a web-access protocol.

32. The method of claim 31, wherein the first network communication protocol comprises a real-time transfer protocol (RTP) and/or a media resource control protocol (MRCP).

33. The method of claim 31, wherein the second network communication protocol comprises a hypertext transfer protocol (HTTP) or an internet protocol (IP).

34. The method of claim 18, wherein outputting the result comprises sending the result to the client according to the second network communication protocol.

35. A computer software product for processing voice, the product comprising a non-transitory computer-readable medium, in which program instructions are stored, which instructions, when read by a computer, cause the computer to:

receive, over at least one network from a client a request to perform an off-line voice processing task according to a first network communication protocol;

convert the off-line voice processing task of the first network communication protocol into an equivalent real-time voice processing task of a second network communication protocol;

provide the equivalent real-time voice processing task to a real-time voice server over the at least one network according to the second network communication protocol for processing the equivalent real-time voice processing task; and

output a result of the processing of the equivalent real-time voice processing task to the client.

36. The product according to claim 35, wherein the instructions cause the computer to convert between the first network communication protocol and/or a first media format associated with the off-line voice processing task and the second network communication protocol and/or a second media format associated with the equivalent real-time voice processing task.

37. The product according to claim 36, wherein one of the first and second media formats comprises rich media comprising voice content grouped with additional content, and wherein the instructions cause the computer to perform either one of or both of extracting the voice content from the rich media content and embedding the voice content into the rich media.

38. The product according to claim 36, wherein the second media format comprises a voice data format supported by the voice server and the first media format comprises a voice data format for rich media or multimedia.

39. The computer software product of claim 35, wherein the first network communication protocol comprises a telephony-oriented protocol and the second network communication protocol comprises a web-access protocol.

40. The computer software product of claim 39, wherein the first network communication protocol comprises a real-time transfer protocol (RTP) and/or a media resource control protocol (MRCP).

41. The computer software product of claim 39, wherein the second network communication protocol comprises a hypertext transfer protocol (HTTP) or an internet protocol (IP).