Distributed off-line voice services

• US 20070133518A1
• Filed: 12/13/2005
• Published: 06/14/2007
• Est. Priority Date: 12/13/2005
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Hoory, Ron, Ben-David, Shay, Sivan, Zohar, Roytman, Alexey, Sliwa, James
• Granted Patent: US 8,451,823 B2
• Time in Patent Office: Days
• 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, comprising:

a real-time voice server, which is arranged to process real-time voice processing tasks for clients of the system; and

a gateway processor, which 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.

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 at least one 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, and comprising a media converter, which is arranged to accept first media content associated with one of the off-line voice processing task and the equivalent real-time voice processing task, and to convert at least one of a protocol and a media format of the first media content to produce second media content associated with the other of the off-line voice processing task and the equivalent real-time voice processing task.

7. The system according to claim 6, wherein one of the first and second media contents comprises rich media comprising voice content grouped with additional content, and wherein the media converter is arranged to perform at least one of extracting the voice content from the rich media content and embedding the voice content into the rich media.

8. 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 performing at least one of publishing the result and sending the result to the client.

9. A gateway processor operating in conjunction with a real-time voice server operative to process real-time voice processing tasks, the gateway processor comprising:

a client interface, which is arranged to accept from a client a request to perform an off-line voice processing task;

a media converter, which is arranged to convert the off-line voice processing task into an equivalent real-time voice processing task; and

a management module, which is arranged to invoke the real-time voice server to process the equivalent real-time voice processing task, and to output a result of the equivalent real-time voice processing task.

10. A method for voice processing, comprising:

accepting a request from a client to perform an off-line voice processing task;

converting the off-line task into an equivalent real-time voice processing task;

invoking a real-time voice server to process the equivalent real-time voice processing task; and

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

11. The method according to claim 10, 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.

12. The method according to claim 10, 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.

13. The method according to claim 10, wherein invoking the real-time voice server comprises causing the real-time voice server to apply at least one 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.

14. The method according to claim 10, 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.

15. The method according to claim 10, wherein converting the off-line voice processing task into the equivalent real-time voice processing task comprises accepting first media content associated with one of the off-line voice processing task and the equivalent real-time voice processing task, and converting at least one of a protocol and a media format of the first media content to produce second media content associated with the other of the off-line voice processing task and the equivalent real-time voice processing task.

16. The method according to claim 15, wherein one of the first and second media contents comprises rich media comprising voice content grouped with additional content, and wherein converting the media format comprises performing at least one of extracting the voice content from the rich media content and embedding the voice content into the rich media.

17. The method according to claim 10, wherein outputting the result of the equivalent real-time voice processing task comprises performing at least one of publishing the result and sending the result to the client.

18. A computer software product for processing voice, operating in conjunction with a real-time voice server operative to process real-time voice processing tasks, the product comprising a computer-readable medium, in which program instructions are stored, which instructions, when read by a computer, cause the computer 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.

19. The product according to claim 18, wherein the instructions cause the computer to accept first media content associated with one of the off-line voice processing task and the equivalent real-time voice processing task, and to convert at least one of a protocol and a media format of the first media content to produce second media content associated with the other of the off-line task and the equivalent real-time voice processing task.

20. The product according to claim 19, wherein one of the first and second media contents comprises rich media comprising voice content grouped with additional content, and wherein the instructions cause the computer to perform at least one of extracting the voice content from the rich media content and embedding the voice content into the rich media.