Robust separation of speech signals in a noisy environment

• US 7,464,029 B2
• Filed: 07/22/2005
• Issued: 12/09/2008
• Est. Priority Date: 07/22/2005
• Status: Active Grant

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: Visser, Erik, Chan, Kwokleung, Toman, Jeremy
• Primary Examiner(s): Hudspeth; David R.
• Assistant Examiner(s): Albertalli; Brian L
• Application Number:
  US11/187,504
• Publication Number:
  US 20070021958A1
• Time in Patent Office: 1,236 Days
• Field of Search: None
• US Class Current: 704/210
• CPC Class Codes: G10L 2021/02165 Two microphones, one receiving mainly the noise signal and the other one mainly the speech signal
• CPC Class Codes: G10L 21/0272 Voice signal separating
• 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: H04R 2410/07 Mechanical or electrical reduction of wind noise generated by wind passing a microphone

Abstract

A method for improving the quality of a speech signal extracted from a noisy acoustic environment is provided. In one approach, a signal separation process is associated with a voice activity detector. The voice activity detector is a two-channel detector, which enables a particularly robust and accurate detection of voice activity. When speech is detected, the voice activity detector generates a control signal. The control signal is used to activate, adjust, or control signal separation processes or post-processing operations to improve the quality of the resulting speech signal. In another approach, a signal separation process is provided as a learning stage and an output stage. The learning stage aggressively adjusts to current acoustic conditions, and passes coefficients to the output stage. The output stage adapts more slowly, and generates a speech-content signal and a noise dominant signal. When the learning stage becomes unstable, only the learning stage is reset, allowing the output stage to continue outputting a high quality speech signal.

Claims

1. A method for improving a speech signal using a voice activity detector, comprising:

receiving a first signal;

receiving a second signal;

comparing an energy level in the first signal to an energy level in the second signal;

determining that voice activity is present when the energy level of the first signal is higher than the energy level of the second signal;

generating a control signal responsive to determining that voice activity is present; and

controlling a speech enhancement process using the control signal, wherein the speech enhancement process comprises a signal separation process, and a learning process for the signal separation process is activated responsive to the control signal.

2. The method according to claim 1, wherein the first signal is generated by a first microphone, and the second signal is generated by a second microphone.

3. The method according to claim 1, wherein the first signal is a speech-content signal generated by a signal separation process, and the second signal is a noise-dominant signal generated by the signal separation process.

4. The method according to claim 1, wherein the determining step includes determining that a difference between the energy level of the first signal and the energy level of the second signal exceeds a threshold value.

5. The method according to claim 4, wherein the threshold value is dynamically adjusted.

6. The method according to claim 1, wherein the comparing step includes comparing signal samples of about 10 ms to about 30 ms in length.

7. The method according to claim 1, wherein the speech enhancement process further comprises a signal separation process, and the signal separation process is activated responsive to the control signal.

8. The method according to claim 1, wherein the speech enhancement process further comprises a post processing operation, and the post processing operation is activated responsive to the control signal.

9. The method according to claim 1, wherein the speech enhancement process further comprises a post processing operation, and the post processing operation is deactivated responsive to the control signal.

10. The method according to claim 1, wherein the speech enhancement process further comprises a noise estimation process, and the noise estimation process is deactivated responsive to the control signal.

11. The method according to claim 1, wherein the speech enhancement process further comprises an automatic gain control process, and the automatic gain control process is activated responsive to the control signal.

12. The method according to claim 1, wherein the speech enhancement process further comprises a post processing spectral subtraction process, and an output from the post processing spectral subtraction process is scaled responsive to the control signal.

13. The method according to claim 1, wherein the speech enhancement process further comprises an echo cancellation process, and the echo cancellation process uses a far end signal and a microphone signal as filter inputs responsive to the control signal not being present.

14. The method according to claim 1, wherein the speech enhancement process further comprises an echo cancellation process, and the echo cancellation process freezes and applies a learned filter to an incoming far end signal responsive to the control signal.

15. A signal separation process, comprising:

receiving a first signal;

receiving a second signal;

comparing the first signal and the second signal to determine that voice activity is present;

generating a control signal responsive to determining that voice activity is present;

activating a blind signal separation process responsive to the control signal;

receiving the first and second signals into the blind signal separation process; and

generating a signal having speech content.

16. The signal separation process according to claim 15, further including the step of deactivating the blind signal separation process when the control signal is not present.

17. The signal separation process according to claim 15, wherein the blind signal separation process is an independent component analysis process.

18. A signal separation system, comprising:

a first microphone generating a first signal;

a second microphone generating a second signal;

a first learning stage receiving the first signal and the second signal, and generating a set of teaching coefficients;

the learning stage being configured to rapidly adapt its coefficients to current acoustic conditions;

an output stage coupled to the learning stage and receiving the teaching coefficients;

the output stage receiving the first signal and the second signal, and generating a speech-content signal and a noise-dominant signal; and

the output stage being configured to more slowly adapt its coefficients.

19. The signal separation system according to claim 18, further including a reset monitor that monitors the learning stage for an unstable condition, and generates a reset signal when an unstable condition is found.

20. The signal separation system according to claim 19, wherein the coefficients for the learning stage are reset responsive to the reset signal, and the output stage is not reset.

21. The signal separation system according to claim 19, wherein the coefficients for the learning stage are reset with a set of default coefficients responsive to the reset signal.

22. The signal separation system according to claim 21, wherein the coefficients are selected from a plurality of sets of default coefficients, with each set of coefficients defined according to a different expected operating environment.

23. The signal separation system according to claim 18, wherein said first learning stage comprises a circuit.

24. The signal separation system according to claim 18, wherein said output stage comprises a circuit.

25. A signal separation system, comprising:

means for generating a first signal;

means for generating a second signal;

means for comparing the first signal and the second signal to determine that voice activity is present;

means for generating a control signal responsive to determining that voice activity is present;

means for activating a blind signal separation process responsive to the control signal;

means for receiving the first and second signals into the blind signal separation process; and

means for generating a signal having speech content.

26. The system of claim 25, wherein said means for generating a first signal comprises a microphone.

27. The system of claim 25, wherein said means for generating a second signal comprises a microphone.

28. A computer readable storage medium storing computer executable instructions which when executed on a computer perform a method for improving a speech signal using a voice activity detector, the method comprising:

receiving a first signal;

receiving a second signal;

comparing an energy level in the first signal to an energy level in the second signal;

determining that voice activity is present when the energy level of the first signal is higher than the energy level of the second signal;

generating a control signal responsive to determining that voice activity is present; and

controlling a speech enhancement process using the control signal, wherein the speech enhancement process comprises a signal separation process, and a learning process for the signal separation process is activated responsive to the control signal.

29. The computer readable storage medium of claim 28, wherein the first signal is a speech-content signal generated by a signal separation process, and the second signal is a noise-dominant signal generated by the signal separation process.

30. The computer readable storage medium of claim 28, wherein the speech enhancement process further comprises a signal separation process, and the signal separation process is activated responsive to the control signal.

31. The computer readable storage medium of claim 28, wherein the speech enhancement process further comprises a post processing operation, and the post processing operation is activated responsive to the control signal.

32. The computer readable storage medium of claim 28, wherein the speech enhancement process further comprises an automatic gain control process, and the automatic gain control process is activated responsive to the control signal.

33. A computer readable storage medium storing computer executable instructions which when executed on a computer perform a method for separating signals, the method comprising:

receiving a first signal;

receiving a second signal;

comparing the first signal and the second signal to determine that voice activity is present;

generating a control signal responsive to determining that voice activity is present;

activating a blind signal separation process responsive to the control signal;

receiving the first and second signals into the blind signal separation process; and

generating a signal having speech content.

34. The computer readable storage medium of claim 33, further including the step of deactivating the blind signal separation process when the control signal is not present.

35. The computer readable storage medium of claim 33, wherein the blind signal separation process is an independent component analysis process.

36. A speech signal improvement system comprising:

means for receiving a first signal;

means for receiving a second signal;

means for comparing an energy level in the first signal to an energy level in the second signal;

means for determining that voice activity is present when the energy level of the first signal is higher than the energy level of the second signal;

means for generating a control signal responsive to determining that voice activity is present; and

means for controlling a speech enhancement process using the control signal, wherein the speech enhancement process comprises a signal separation process, and a learning process for the signal separation process is activated responsive to the control signal.

37. The system of claim 36, wherein said means for generating a first signal comprise a microphone.

38. The system of claim 36, wherein said means for generating a second signal comprise a microphone.

39. A speech signal system, comprising:

a first microphone generating a first signal;

a second microphone generating a second signal;

a voice activity detection module configured to;

compare an energy level in the first signal to an energy level in the second signal;

determine that voice activity is present when the energy level of the first signal is higher than the energy level of the second signal; and

generate a control signal for controlling a speech enhancement process and activating a learning process, the control signal being responsive to determining that voice activity is present;

wherein the speech enhancement process comprises a signal separation process.

40. The system according to claim 39, the voice activity detection module is further configured to determine that a difference between the energy level of the first signal and the energy level of the second signal exceeds a threshold value.

41. The system according to claim 39, further comprising a processor device configured to perform a signal separation process, the signal separation process being activated by the control signal.

42. A signal separation system comprising:

a first microphone generating a first signal;

a second microphone generating a second signal;

a voice activity detection module configured to;

compare the first signal and the second signal to determine that voice activity is present; and

generate a control signal for activating a blind signal separation process, the control signal being responsive to determining that voice activity is present; and

a processor device configured to;

receive the first and second signals;

separate the received signals using the blind signal separation process; and

generate a signal having speech content.

43. The system according to claim 42, wherein the voice activity diction module is further configured to deactivate the blind signal separation process when the control signal is not present.

44. The system according to claim 42, wherein the blind signal separation process is an independent component analysis process.