Detection of voice activity in an audio signal

• US 20060053007A1
• Filed: 08/29/2005
• Published: 03/09/2006
• Est. Priority Date: 08/30/2004
• Status: Abandoned Application

• Current Assignee: Nokia Solutions and Networks US LLC (Nokia Corporation)
• Original Assignee: Nokia Corporation
• Inventors: Niemisto, Riitta
• Application Number:
  US11/214,454
• Publication Number:
  US 20060053007A1
• Time in Patent Office: Days
• US Class Current: 704/233
• 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

Abstract

A device comprising a voice activity detector for detecting voice activity in a speech signal using digital data formed on the basis of samples of an audio signal. The voice activity detector comprises a first element adapted to examine whether the signal has a highpass nature. The voice activity detector also comprises a second element adapted to examine the frequency spectrum of the signal. The voice activity detector is adapted to provide an indication of speech when the first element has determined that the signal has a highpass nature or the second element has determined that the signal does not have a flat frequency response.

Claims

1. A device comprising a voice activity detector for detecting voice activity in a speech signal using digital data formed on the basis of samples of an audio signal, the voice activity detector of the device comprising:

a first element adapted to examine, whether the signal has a highpass nature; and

a second element adapted to examine the frequency spectrum of the signal;

wherein the voice activity detector is adapted to provide an indication of speech when one of the following conditions is fulfilled;

the first element has determined that the signal has a highpass nature;

or

the second element has determined that the signal does not have a flat frequency response.

2. The device according to claim 1, wherein the voice activity detector is further adapted to provide an indication of noise when the first element has determined that the signal has not highpass nature and the second element has determined that the signal has flat frequency response.

3. The device according to claim 1, the voice activity detector also comprising a spectral distance voice activity detector for examining frequency properties of the signal and for producing spectral distance detection data on the basis of the examination, the spectral distance detection data providing an indication of speech or an indication of noise.

4. The device according to claim 1, the voice activity detector also comprising an autocorrelation voice activity detector for examining autocorrelation properties of the signal and for producing autocorrelation detection data on the basis of the examination, wherein the spectral distance voice activity detector is adapted to produce the spectral distance detection data when the autocorrelation detection data does not indicate speech.

5. The device according to claim 4, the voice activity detector comprising a decision block to form a decision signal on the basis of the combination of indications of the different voice activity detectors.

6. The device according to claim 1, wherein the voice activity detector (6) is adapted to calculate a first order predictor A(z)=1−

az<sup>−

1</sup> corresponding to a current and a previous frame of the digital data, in which the predictor coefficient a is computed by

7. The device according to claim 6, the voice activity detector comprising a first element to examine if the value of the predictor coefficient a is less or equal to a predetermined value to use the result of the examination in providing the indication of speech.

8. The device according to claim 7, the voice activity detector comprising a second element to calculate a weighted spectrum estimate and to compare the smallest and largest values of the weighted spectrum to a second predetermined value to use the result of the comparison in providing the indication of noise or speech.

9. A voice activity detector for detecting voice activity in a speech signal containing noise using digital data formed on the basis of samples of an audio signal, the voice activity detector comprising:

a first element adapted to examine, whether the signal has a highpass nature; and

a second element adapted to examine the frequency spectrum of the signal;

wherein the voice activity detector is adapted to provide an indication of speech when one of the following conditions is fulfilled;

the first element has determined that the signal has a highpass nature;

or

the second element has determined that the signal does not have a flat frequency response.

10. The voice activity detector according to claim 9, wherein the voice activity detector is further adapted to provide an indication of noise when the first element has determined that the signal has not highpass nature and the second element has determined that the signal has flat frequency response.

11. The voice activity detector according to claim 9 also comprising a spectral distance voice activity detector (6.2) for examining frequency properties of the signal and for producing spectral distance detection data on the basis of the examination, the spectral distance detection data providing an indication of speech or an indication of noise.

12. The voice activity detector according to claim 9 also comprising an autocorrelation voice activity detector for examining autocorrelation properties of the signal and for producing autocorrelation detection data on the basis of the examination, wherein the spectral distance voice activity detector is adapted to produce the spectral distance detection data when the autocorrelation detection data does not indicate speech.

13. The voice activity detector according to claim 12 comprising a decision block to form a decision signal on the basis of the combination of indications of the different voice activity detectors.

14. The voice activity detector according to claim 12, wherein the spectral distance detection data comprises autocorrelation parameters, wherein the first element is adapted to examine the autocorrelation parameters to determine the highpass nature of the signal.

15. The voice activity detector according to claim 9, wherein the voice activity detector is adapted to calculate a first order predictor A(z)=1−

az<sup>−

1</sup> corresponding to a current and a previous frame of the digital data, in which the predictor coefficient a is computed by

16. The voice activity detector according to claim 15 comprising a first element to examine if the value of the predictor coefficient a is less or equal to a predetermined value to use the result of the examination in providing the indication of speech.

17. The voice activity detector according to claim 16 comprising a second element to calculate a weighted spectrum estimate and to compare the smallest and largest values of the weighted spectrum to a second predetermined value to use the result of the comparison in providing the indication of noise or speech.

18. A system comprising a voice activity detector for detecting voice activity in a speech signal containing noise using digital data formed on the basis of samples of an audio signal, the voice activity detector of the system comprising:

a first element adapted to examine, whether the signal has a highpass nature; and

a second element adapted to examine the frequency spectrum of the signal;

wherein the voice activity detector is adapted to provide an indication of speech when one of the following conditions is fulfilled;

the first element has determined that the signal has a highpass nature;

or

the second element has determined that the signal does not have a flat frequency response.

19. The device according to claim 18, wherein the voice activity detector is further adapted to provide an indication of noise when the first element has determined that the signal has not highpass nature and the second element has determined that the signal has flat frequency response.

20. A method for detecting voice activity detector in a speech signal containing noise using digital data formed on the basis of samples of an audio signal comprising:

examining, whether the signal has a highpass nature;

examining the frequency spectrum of the signal; and

providing an indication of speech when one of the following conditions is fulfilled;

it is determined that the signal has a highpass nature;

or

it is determined that the signal does not have a flat frequency response.

21. The method according to claim 20 comprising providing an indication of noise when it is determined that the signal has not highpass nature and that the signal has flat frequency response.

22. The method according to claim 20 also comprising examining frequency properties of the signal and producing spectral distance detection data on the basis of the examination, the spectral distance detection data providing an indication of speech or an indication of noise.

23. The method according to claim 20 also comprising examining autocorrelation properties of the signal and producing autocorrelation detection data on the basis of the examination, wherein the method comprises producing the spectral distance detection data when the autocorrelation detection data does not indicate speech.

24. The method according to claim 23 also comprising forming a decision signal on the basis of the combination of indications of the different voice activity detections.

25. The method according to claim 23, wherein the spectral distance detection data comprises autocorrelation parameters, wherein the method comprises examining the autocorrelation parameters to determine the highpass nature of the signal.

26. The method according to claim 20 comprising calculating a first order predictor A(z)=1−

az<sup>−

1</sup> corresponding to a current and a previous frame of the digital data, in which the predictor coefficient a is computed by

27. The method according to claim 26 also comprising examining if the value of the predictor coefficient a is less or equal to a predetermined value and using the result of the examination in providing the indication of speech.

28. The method according to claim 27 also comprising calculating a weighted spectrum estimate and comparing the smallest and largest values of the weighted spectrum to a second predetermined value and using the result of the comparison in providing the indication of noise or speech.

29. A computer program product comprising machine executable steps for

detecting voice activity detector in a speech signal containing noise using digital data formed on the basis of samples of an audio signal, examining, whether the signal has a highpass nature;

examining the frequency spectrum of the signal; and

providing an indication of speech when one of the following conditions is fulfilled;

the signal has a highpass nature;

or

the signal does not have a flat frequency response.

30. The computer program product according to claim 29 comprising machine executable steps for providing an indication of noise when the signal has not highpass nature and that the signal has flat frequency response.