Method and device for sound activity detection and sound signal classification

• US 8,990,073 B2
• Filed: 06/20/2008
• Issued: 03/24/2015
• Est. Priority Date: 06/22/2007
• Status: Active Grant

• Current Assignee: VoiceAge EVS LLC (Government of ABU Dhabi)
• Original Assignee: VoiceAge Corporation
• Inventors: Malenovsky, Vladimir, Jelinek, Milan, Vaillancourt, Tommy, Salami, Redwan
• Primary Examiner(s): Desir, Pierre-Louis
• Assistant Examiner(s): Sharma, Neeraj
• Application Number:
  US12/664,934
• Publication Number:
  US 20110035213A1
• Time in Patent Office: 2,468 Days
• Field of Search: 704/208, 704/219, 704/226, 704/229, 704/223, 704/207, 704/220, 704/500, 704/233, 704/239, 704/200, 704/203, 381/94.3
• US Class Current: 704/208
• CPC Class Codes: G10L 19/22 Mode decision, i.e. based on audio signal content versus external parameters
• 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 and method for estimating a tonal stability of a sound signal include: calculating a current residual spectrum of the sound signal; detecting peaks in the current residual spectrum; calculating a correlation map between the current residual spectrum and a previous residual spectrum for each detected peak; and calculating a long-term correlation map based on the calculated correlation map, the long-term correlation map being indicative of a tonal stability in the sound signal.

Claims

1. A method for estimating a tonal stability of a sound signal using a frequency spectrum of the sound signal, the method comprising:

calculating a current residual spectrum of the sound signal by subtracting from the frequency spectrum of the sound signal a spectral floor defined by minima of the frequency spectrum;

detecting a plurality of peaks in the current residual spectrum as pieces of the current residual spectrum between pairs of successive minima of the current residual spectrum;

calculating a correlation map between each detected peak of the current residual spectrum and a shape in a previous residual spectrum corresponding to the position of the detected peak; and

identifying the tonal stability of the sound signal based on calculating a long-term correlation map, wherein the long-term correlation map is calculated based on an update factor, the correlation map of a current frame, and an initial value of the long term correlation map.

2. A method as defined in claim 1, wherein calculating the current residual spectrum comprises:

searching for the minima in the frequency spectrum of the sound signal in the current frame;

estimating the spectral floor by connecting the minima of the frequency spectrum with each other; and

subtracting the estimated spectral floor from the frequency spectrum of the sound signal in the current frame so as to produce the current residual spectrum.

3. A method as defined in claim 1, wherein detecting the peaks in the current residual spectrum comprises locating a maximum between each pair of two consecutive minima of the current residual spectrum.

4. A method as defined in claim 1, wherein calculating the correlation map comprises:

for each detected peak in the current residual spectrum, calculating a normalized correlation value with the previous residual spectrum, over frequency bins between two consecutive minima in the current residual spectrum that delimit the peak;

assigning a score to each detected peak, the score corresponding to the normalized correlation value; and

for each detected peak, assigning the normalized correlation value of the peak over the frequency bins between the two consecutive minima that delimit the peak so as to form the correlation map.

5. A method as defined in claim 1, wherein calculating the long-teen correlation map comprises:

filtering the correlation map through a one-pole filter on a frequency bin by frequency bin basis; and

summing the filtered correlation map over the frequency bins so as to produce a summed long-term correlation map.

6. A method as defined in claim 1, further comprising detecting strong tones in the sound signal.

7. A method as defined in claim 6, wherein detecting the strong tones in the sound signal comprises searching in the correlation map for frequency bins having a magnitude that exceeds a given fixed threshold.

8. A method as defined in claim 6, wherein detecting the strong tones in the sound signal comprises comparing the summed long-term correlation map with an adaptive threshold indicative of sound activity in the sound signal.

9. A method as defined in claim 1, further comprising verification of a presence of strong tones.

10. A method for detecting sound activity in a sound signal, wherein the sound signal is classified as one of an inactive sound signal and an active sound signal according to the detected sound activity in the sound signal, the method comprising:

estimating a parameter related to a tonal stability tonal stability of the sound signal used for distinguishing a music signal from a background noise signal;

wherein the tonal stability tonal stability estimation is performed according to claim 1.

11. A method as defined in claim 10, further comprising preventing update of noise energy estimates when a tonal sound signal is detected.

12. A method as defined in claim 10, wherein detecting the sound activity in the sound signal further comprises using a signal-to-noise ratio (SNR)-based sound activity detection.

13. A method as defined in claim 12, wherein using the signal-to-noise ratio (SNR)-based sound activity detection comprises detecting the sound signal based on a frequency dependent signal-to-noise ratio (SNR).

14. A method as defined in claim 12, wherein using the signal-to-noise ratio (SNR)-based sound activity detection comprises comparing an average signal-to-noise ratio (SNR_av) to a threshold calculated as a function of a long-term signal-to-noise ratio (SNR_LT).

15. A method as defined in claim 14, wherein using the signal-to-noise ratio (SNR)-based sound activity detection in the sound signal further comprises using noise energy estimates calculated in a previous frame in a SNR calculation.

16. A method as defined in claim 15, wherein using the signal-to-noise ratio (SNR)-based sound activity detection further comprises updating the noise estimates for a next frame.

17. A method as defined in claim 16, wherein updating the noise energy estimates for a next frame comprises calculating an update decision based on at least one of a pitch stability, a voicing, a non-stationarity parameter of the sound signal and a ratio between a second order and a sixteenth order of linear prediction residual error energies.

18. A method as defined in claim 14, comprising classifying the sound signal as one of an inactive sound signal and active sound signal, which comprises determining an inactive sound signal when the average signal-to-noise ratio (SNR_av) is inferior to the calculated threshold.

19. A method as defined in claim 14, comprising classifying the sound signal as one of an inactive sound signal and active sound signal, which comprises determining an active sound signal when the average signal-to-noise ratio (SNR_av) is larger than the calculated threshold.

20. A method as defined in claim 10, wherein estimating the parameter related to the tonal stability tonal stability of the sound signal prevents updating of noise energy estimates when a music signal is detected.

21. A method as defined in claim 10, further comprising calculating a complementary non-stationarity parameter and a noise character parameter in order to distinguish a music signal from a background noise signal and prevent update of noise energy estimates on the music signal.

22. A method as defined in claim 21, further comprising:

detecting a spectral attack;

calculating the complementary non-stationarity parameter based on an element selected from the group consisting of a current frame energy and an average frame energy.

23. A method as defined in claim 22, further comprising calculating a spectral diversity parameter.

24. A method as defined in claim 23, wherein calculating the spectral diversity parameter comprises:

calculating a ratio between an energy of the sound signal in a current frame and an energy of the sound signal in a previous frame, for frequency bands higher than a given number; and

calculating the spectral diversity as a weighted sum of the computed ratio over all the frequency bands higher than the given number.

25. A method as defined in claim 22, wherein calculating the complementary non-stationarity parameter further comprises calculating an activity prediction parameter indicative of an activity of the sound signal.

26. A method as defined in claim 25, wherein calculating the activity prediction parameter comprises:

calculating a long-term value of a binary decision obtained from estimating the parameter related to the tonal stability tonal stability of the sound signal and the complementary non-stationarity parameter.

27. A method as defined in claim 25, wherein the update of the noise energy estimates is prevented in response to having simultaneously the activity prediction parameter larger than a first given fixed threshold and the complementary non-stationarity parameter larger than a second given fixed threshold.

28. A method as defined in claim 21, wherein calculating the noise character parameter comprises:

dividing a plurality of frequency bands into a first group of a certain number of first frequency bands and a second group of a rest of the frequency bands;

calculating a first energy value for the first group of frequency bands and a second energy value of the second group of frequency bands;

calculating a ratio between the first and second energy values so as to produce the noise character parameter; and

calculating a long-term value of the noise character parameter based on the calculated noise character parameter.

29. A method as defined in claim 28, wherein the update of the noise energy estimates is prevented in response to having the noise character parameter inferior than a given fixed threshold.

30. A device for estimating a tonal stability tonal stability of a sound signal using a frequency spectrum of the sound signal, the device comprising:

means for calculating a current residual spectrum of the sound signal by subtracting from the frequency spectrum of the sound signal a spectral floor defined by minima of the frequency spectrum;

means for detecting a plurality of peaks in the current residual spectrum as pieces of the current residual spectrum between pairs of successive minima of the current residual spectrum;

means for calculating a correlation map between each detected peak of the current residual spectrum and a shape in a previous residual spectrum corresponding to the position of the detected peak; and

means for identifying the tonal stability of the sound signal based on calculating a long-term correlation map, wherein the long-term correlation map is calculated based on an update factor, the correlation map of a current frame, and an initial value of the long-term correlation map.

35. A device for detecting sound activity in a sound signal, wherein the sound signal is classified as one of an inactive sound signal and an active sound signal according to the detected sound activity in the sound signal, the device comprising:

means for estimating a parameter related to a tonal stability tonal stability of the sound signal used for distinguishing a music signal from a background noise signal;

wherein the tonal stability tonal stability parameter estimation means comprises a device according to claim 30.

31. A device for estimating a tonal stability tonal stability of a sound signal using a frequency spectrum of the sound signal, the device comprising:

a calculator of a current residual spectrum of the sound signal by subtracting from the frequency spectrum of the sound signal a spectral floor defined by minima of the frequency spectrum;

a detector of a plurality of peaks in the current residual spectrum as pieces of the current residual spectrum between pairs of successive minima of the current residual spectrum;

a calculator of a correlation map between each detected peak of the current residual spectrum and a shape in a previous residual spectrum corresponding to the position of the detected peak; and

a calculator identifying the tonal stability of the sound signal based on calculating a long-term correlation map, wherein the long-term correlation map is calculated based on an update factor, the correlation map of a current frame, and an initial value of the long-term correlation map.

32. A device as defined in claim 31, wherein the calculator of the current residual spectrum comprises:

a locator of the minima in the frequency spectrum of the sound signal in the current frame;

an estimator of the spectral floor which connects the minima of the frequency spectrum with each other; and

a subtractor of the estimated spectral floor from the frequency spectrum so as to produce the current residual spectrum.

33. A device as defined in claim 31, wherein the calculator of the long-term correlation map comprises:

a filter for filtering the correlation map on a frequency bin by frequency bin basis; and

an adder for summing the filtered correlation map over the frequency bins so as to produce a summed long-term correlation map.

34. A device as defined in claim 31, further comprising a detector of strong tones in the sound signal.

36. A device for detecting sound activity in a sound signal, wherein the sound signal is classified as one of an inactive sound signal and an active sound signal according to the detected sound activity in the sound signal, the device comprising:

a tonal stability tonal stability estimator of the sound signal, used for distinguishing a music signal from a background noise signal;

wherein the tonal stability tonal stability estimator comprises a device according to claim 31.

37. A device as defined in claim 36, further comprising a signal-to-noise ratio (SNR)-based sound activity detector.

38. A device as defined in claim 37, wherein the (SNR)-based sound activity detector comprises a comparator of an average signal to noise ratio (SNR_av) with a threshold which is a function of a long-term signal to noise ratio (SNR_LT).

39. A device as defined in claim 37, further comprising a noise estimator for updating noise energy estimates in a calculation of a signal-to-noise ratio (SNR) in the SNR-based sound activity detector.

40. A device as defined in claim 36, further comprising a calculator of a complementary non-stationarity parameter and a calculator of a noise character of the sound signal for distinguishing a music signal from a background noise signal and preventing update of noise energy estimates.

41. A device as defined in claim 36, further comprising a calculator of a spectral parameter used for detecting spectral changes and spectral attacks in the sound signal.