Method and apparatus for active noise cancellation

• US 7,769,593 B2
• Filed: 09/28/2006
• Issued: 08/03/2010
• Est. Priority Date: 09/28/2006
• Status: Active Grant

• Current Assignee: SRI International, Inc.
• Original Assignee: SRI International, Inc.
• Inventors: Gadde, Venkata Ramana Rao, Venkataraman, Anand, Graciarena, Martin
• Primary Examiner(s): ABEBE, DANIEL DEMELASH
• Application Number:
  US11/541,282
• Publication Number:
  US 20080082326A1
• Time in Patent Office: 1,405 Days
• Field of Search: 704/275, 704/270, 381/110
• US Class Current: 704/275
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 21/02 Speech enhancement, e.g. noise reduction or echo cancellation reducing echo effects in line transmission systems H04B3/20; echo suppression in hands-free telephones H04M9/08

Abstract

In one embodiment, the present invention is a method and apparatus for active noise cancellation. In one embodiment, a method for recognizing user speech in an audio signal received by a media system (where the audio signal includes user speech and ambient audio output produced by the media system and/or other devices) includes canceling portions of the audio signal associated with the ambient audio output and applying speech recognition processing to an uncancelled remainder of the audio signal.

Claims

1. A method for recognizing user speech in an audio signal received by a media system, said audio signal comprising user speech and ambient audio output, the method comprising:

canceling portions of said audio signal associated with said ambient audio output, where said ambient audio output is associated with an audio output delivered via at least one output channel of said media system;

applying speech recognition processing to an uncancelled remainder of said audio signal; and

calibrating said media system prior to said canceling and said applying, wherein said calibrating comprises, for each of said at least one output channel;

activating said at least one output channel;

sending a calibration signal to said at least one output channel;

measuring a response of said at least one output channel to said calibration signal; and

calculating at least one offset compensating for said audio output produced by the at least one output channel of said media system, in accordance with said response.

2. The method of claim 1, wherein said response comprises a time elapsed between said sending and a reception of said response.

3. The method of claim 2, wherein said response further comprises a distortion in said response.

4. The method of claim 1, wherein said canceling comprises:

applying at least one offset to said audio signal, said at least one offset compensating for said audio output produced by the at least one output channel of said media system.

5. The method of claim 4, wherein said applying comprises:

calculating said at least one offset in accordance with a response of said at least one output channel to a calibration signal.

6. The method of claim 1, wherein said applying comprises:

detecting a trigger word in said audio signal; and

commencing speech recognition processing of at least a portion of said audio signal following said trigger word.

7. The method of claim 6, wherein said detecting comprises:

scanning said audio signal for one or more trigger words including said trigger word on a continuous basis.

8. The method of claim 6, wherein said at least a portion of said audio signal following said trigger word comprises a command uttered by a source of said user speech.

9. The method of claim 8, further comprising:

taking an action in accordance with said command.

10. The method of claim 1, wherein said audio signal is received via a microphone interfaced to said media system.

11. The method of claim 1, wherein said canceling comprises:

determining a level of distortion in said audio signal that is attributable to said ambient audio output being received in said audio signal; and

compensating for said level of distortion prior to applying said speech recognition processing.

12. The method of claim 1, wherein said media system comprises at least one of:

a personal computer media system, a television, a car audio system, or a car navigation system.

13. A non-transitory computer readable medium containing an executable program for recognizing user speech in an audio signal received by a media system, said audio signal comprising user speech and ambient audio output, where the program performs steps of:

canceling portions of said audio signal associated with said ambient audio output, where said ambient audio output is associated with an audio output delivered via at least one output channel of said media system;

applying speech recognition processing to an uncancelled remainder of said audio signal; and

calibrating said media system prior to said canceling and said applying, wherein said calibrating comprises, for each of said at least one output channel;

activating said at least one output channel;

sending a calibration signal to said at least one output channel;

measuring a response of said at least one output channel to said calibration signal; and

calculating at least one offset compensating for said audio output produced by the at least one output channel of said media system, in accordance with said response.

14. The computer readable medium of claim 13, wherein said canceling comprises:

applying at least one offset to said audio signal, said at least one offset compensating for said audio output produced by the at least one output channel of said media system.

15. The computer readable medium of claim 14, wherein said applying comprises:

calculating said at least one offset in accordance with a response of said at least one output channel to a calibration signal.

16. The computer readable medium of claim 13, wherein said applying comprises:

detecting a trigger word in said audio signal; and

commencing speech recognition processing of at least a portion of said audio signal following said trigger word.

17. The computer readable medium of claim 16, wherein said detecting comprises:

scanning said audio signal for one or more trigger words including said trigger word on a continuous basis.

18. The computer readable medium of claim 16, wherein said at least a portion of said audio signal following said trigger word comprises a command uttered by a source of said user speech.

19. The computer readable medium of claim 18, further comprising:

taking an action in accordance with said command.

20. The computer readable medium of claim 13, wherein said audio signal is received via a microphone interfaced to said media system.

21. The computer readable medium of claim 13, wherein said canceling comprises:

determining a level of distortion in said audio signal that is attributable to said ambient audio output being received in said audio signal; and

compensating for said level of distortion prior to applying said speech recognition processing.

22. The computer readable medium of claim 13, wherein said media system comprises at least one of:

a personal computer media system, a television, a car audio system, or a car navigation system.

23. The computer readable medium of claim 13, wherein said response comprises a time elapsed between said sending and a reception of said response.

24. The computer readable medium of claim 23, wherein said response further comprises a distortion in said response.

25. An apparatus for recognizing user speech in an audio signal received by a media system, said audio signal comprising user speech and ambient audio output, comprising:

means for canceling portions of said audio signal associated with said ambient audio output, where said ambient audio output is associated with an audio output delivered via at least one output channel of said media system;

means for applying speech recognition processing to an uncancelled remainder of said audio signal; and

means for calibrating said media system, wherein said means for calibrating comprises, for each of said at least one output channel;

means for activating said at least one output channel;

means for sending a calibration signal to said at least one output channel;

means for measuring a response of said at least one output channel to said calibration signal; and

means for calculating at least one offset compensating for said audio output produced by the at least one output channel of said media system, in accordance with said response.

26. The apparatus of claim 25, wherein said means for canceling comprises:

means for applying at least one offset to said audio signal, said at least one offset compensating for said audio output produced by the at least one output channel of said media system.

27. The apparatus of claim 26, wherein said means for applying comprises:

means for calculating said at least one offset in accordance with a response of said at least one output channel to a calibration signal.

28. The apparatus of claim 25, wherein said means for applying comprises:

means for detecting a trigger word in said audio signal; and

means for commencing speech recognition processing of at least a portion of said audio signal following said trigger word.

29. The apparatus of claim 28, wherein said means for detecting scans said audio signal for one or more trigger words including said trigger word on a continuous basis.

30. The apparatus of claim 28, wherein said at least a portion of said audio signal following said trigger word comprises a command uttered by a source of said user speech.

31. The apparatus of claim 30, further comprising:

means for taking an action in accordance with said command.

32. The apparatus of claim 25, further comprising a microphone interfaced to said media system for receiving said audio signal.

33. The apparatus of claim 25, wherein said means for canceling comprises:

means for determining a level of distortion in said audio signal that is attributable to said ambient audio output being received in said audio signal; and

means for compensating for said level of distortion prior to applying said speech recognition processing.

34. The apparatus of claim 25, wherein said media system comprises at least one of:

a personal computer media system, a television, a car audio system, or a car navigation system.