Methods, apparatus, and products for identifying a conversation

• US 20040172252A1
• Filed: 04/16/2003
• Published: 09/02/2004
• Est. Priority Date: 02/28/2003
• Status: Active Grant

• Current Assignee: III Holdings 6, LLC (Intellectual Ventures LLC)
• Original Assignee: Palo Alto Research Center, Inc. (Xerox Holdings Corp.), Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Thornton, James D., Woodruff, Allison G., Szymanski, Margaret H., Aoki, Paul M., Wilson, Daniel H.
• Granted Patent: US 7,617,094 B2
• Time in Patent Office: Days
• US Class Current: 704/270
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 21/0208 Noise filtering
• CPC Class Codes: G10L 25/78 Detection of presence or absence of voice signals switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10
• CPC Class Codes: H04M 3/564 whereby the feature is a sub-conference
• CPC Class Codes: H04M 3/566 relating to a participants right to speak arrangements for multi-party communication with floor control, e.g. for conferences, H04L65/4038, H04L65/4046, H04L65/4053
• CPC Class Codes: H04M 3/568 audio processing specific to telephonic conferencing, e.g. spatial distribution, mixing of participants echo suppression in two-way loud-speaking telephone systems H04M9/02; sound field processing per se H04S7/30
• CPC Class Codes: H04M 3/569 using the instant speaker's algorithm speech detection per se G10L25/78

Abstract

One aspect of the invention is a method of using a computer to identify a conversation. Another aspect is a method for an audio processing system that identifies conversations and enhances each conversation for each user in the conversation.

Claims

1. A computer controlled method of identifying a conversation, said method comprising steps of:

extracting a plurality of streams of feature data from a conversational communication between a plurality of users over a corresponding communicative interval; and

analyzing said plurality of streams of feature data corresponding to various combinations of said plurality of users within said corresponding communicative interval to identify said conversation between two or more of said plurality of users.

2. The computer controlled method of claim 1, wherein said conversational communication is from a recorded media.

3. The computer controlled method of claim 1, wherein said conversational communication is captured using at least one audio capture device.

4. The computer controlled method of claim 1, further comprising enhancing said conversation with respect to said conversational communication responsive to the step of analyzing.

5. The computer controlled method of claim 1, wherein said conversational communication comprises textual information, audible information, visual information or tactile information.

6. The computer controlled method of claim 1, wherein the method further comprises a step of transcribing said conversation.

7. A computer controlled method for an audio processing system, said method comprising steps of:

receiving one or more audio streams, where each one of said one or more audio streams is from one of a plurality of audio sources;

distinguishing from said one or more audio streams a plurality of audio substreams;

mixing, responsive to a plurality of floor controls, said one or more audio substreams for one or more outputs associated with said plurality of audio sources;

analyzing, for a plurality of users associated with said plurality of audio sources, one or more conversational characteristics of two or more of said plurality of users; and

automatically adjusting said plurality of floor controls responsive to the step of analyzing.

8. The computer controlled method of claim 7, wherein one of said one or more outputs provides signals capable of driving an audio reproduction mechanism.

9. The computer controlled method of claim 7, wherein one of said one or more outputs provides signals capable of being recorded.

10. The computer controlled method of claim 7, further comprising indicating floor membership for some of said plurality of users.

11. An apparatus comprising:

an extraction mechanism configured to extract a plurality of streams of feature data from a conversational communication between a plurality of users over a corresponding communicative interval; and

an analysis mechanism, responsive to the extraction mechanism, configured to analyze said plurality of streams of feature data corresponding to various combinations of said plurality of users within said corresponding communicative interval to identify a conversation between two or more of said plurality of users.

12. The apparatus of claim 11, wherein said conversational communication is from a recorded media.

13. The apparatus of claim 11, wherein said conversational communication is captured using at least one audio capture device.

14. The apparatus of claim 11, further comprising a floor control mechanism configured to enhance said conversation with respect to said conversational communication responsive to the analysis mechanism.

15. The apparatus of claim 11, wherein said conversational communication comprises textual information, audible information, visual information or tactile information.

16. The apparatus of claim 11, wherein the apparatus further comprises a transcription mechanism configured to transcribe said conversation.

17. An apparatus for an audio processing system, said apparatus comprises:

a receiver configured to receive one or more audio streams, where each one of said one or more audio streams is from one of a plurality of audio sources;

a distinguishing mechanism configured to distinguish from said one or more audio streams a plurality of audio substreams;

a mixer configured to mix, responsive to a plurality of floor controls, said one or more audio substreams for one or more outputs associated with said plurality of audio sources;

an analysis mechanism configured to analyze, for a plurality of users associated with said plurality of audio sources, one or more conversational characteristics of two or more of said plurality of users; and

a floor control mechanism configured to automatically adjust said plurality of floor controls responsive to the analysis mechanism.

18. The apparatus of claim 17, wherein one of said one or more outputs provides signals capable of driving an audio reproduction mechanism.

19. The apparatus of claim 17, wherein one of said one or more outputs provides signals capable of being recorded.

20. The apparatus of claim 17, further comprising a presentation mechanism configured to indicate floor membership for some of said plurality of users.

21. A computer program product comprising:

a computer usable data carrier having computer readable code embodied therein for causing a computer to provide a conversation identification service, the computer program product comprising;

computer readable program code configured to cause said computer to effect an extraction mechanism configured to extract a plurality of streams of feature data from a conversational communication between a plurality of users over a corresponding communicative interval; and

computer readable program code configured to cause said computer to effect an analysis mechanism, responsive to the extraction mechanism, configured to analyze said plurality of streams of feature data corresponding to various combinations of said plurality of users within said corresponding communicative interval to identify a conversation between two or more of said plurality of users.

22. The computer program product of claim 21, wherein the computer usable data carrier is a computer readable media.

23. The computer program product of claim 21, wherein the computer usable data carrier is a carrier wave.

24. The computer program product of claim 21, wherein said conversational communication is from a recorded media.

25. The computer program product of claim 21, wherein said conversational communication is captured using at least one audio capture device.

26. The computer program product of claim 21, further comprising computer readable program code configured to cause said computer to effect a floor control mechanism configured to enhance said conversation with respect to said conversational communication responsive to the analysis mechanism.

27. The computer program product of claim 21, wherein said conversational communication comprises textual information, audible information, visual information or tactile information.

28. The computer program product of claim 21, wherein the product further comprises computer readable program code configured to cause said computer to effect a transcription mechanism configured to transcribe said conversation.

29. A computer program product comprising:

a computer usable data carrier having computer readable code embodied therein for causing a computer to provide an audio processing system, the computer program product comprising;

computer readable program code configured to cause said computer to effect a receiver configured to receive one or more audio streams, where each one of said one or more audio streams is from one of a plurality of audio sources;

computer readable program code configured to cause said computer to effect a distinguishing mechanism configured to distinguish from said one or more audio streams a plurality of audio substreams;

computer readable program code configured to cause said computer to effect a mixer configured to mix, responsive to a plurality of floor controls, said one or more audio substreams for one or more outputs associated with said plurality of audio sources;

computer readable program code configured to cause said computer to effect an analysis mechanism configured to analyze, for a plurality of users associated with said plurality of audio sources, one or more conversational characteristics of two or more of said plurality of users; and

computer readable program code configured to cause said computer to effect a floor control mechanism configured to automatically adjust said plurality of floor controls responsive to the analysis mechanism.

30. The computer program product of claim 29, wherein the computer usable data carrier is a computer readable media.

31. The computer program product of claim 29, wherein the computer usable data carrier is a carrier wave.

32. The computer program product of claim 29, wherein one of said one or more outputs provides signals capable of driving an audio reproduction mechanism.

33. The computer program product of claim 29, wherein one of said one or more outputs provides signals capable of being recorded.

34. The computer program product of claim 29, further comprising computer readable program code configured to cause said computer to effect a presentation mechanism configured to indicate floor membership for some of said plurality of users.