Low-complexity music detection algorithm and system

• US 20060015333A1
• Filed: 11/04/2004
• Published: 01/19/2006
• Est. Priority Date: 07/16/2004
• Status: Active Grant

• Current Assignee: Nytell Software LLC (Intellectual Ventures LLC)
• Original Assignee: Mindspeed Technologies Inc. (MACOM Technology Solutions Holdings, Inc.)
• Inventors: Gao, Yang
• Granted Patent: US 7,120,576 B2
• Time in Patent Office: Days
• US Class Current: 704/233
• CPC Class Codes: G10H 2210/046 for differentiation between music and non-music signals, based on the identification of musical parameters, e.g. based on tempo detection
• CPC Class Codes: G10L 25/48 specially adapted for particular use
• 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 method for detecting music in a speech signal having a plurality of frames. The method comprises defining a music threshold value for a first parameter extracted from a frame of the speech signal, defining a background noise threshold value for the first parameter, and defining an unsure threshold value for the first parameter. The unsure threshold value falls between the music threshold value and the background noise threshold value. If the first parameter falls between the music threshold value and the background noise threshold value, the speech signal is classified as music or background noise based on analyzing a plurality of first parameters extracted from the plurality of frames.

Claims

1. A method for detecting music in a speech signal having a plurality of frames, said method comprising:

defining a music threshold value for a first parameter extracted from a frame of said speech signal;

defining a background noise threshold value for said first parameter;

defining an unsure threshold value for said first parameter, wherein said unsure threshold value falls between said music threshold value and said background noise threshold value;

wherein if said first parameter does not fall between said music threshold value and said background noise threshold value,

classifying said speech signal as music if said first parameter is in closer range of said music threshold value than said unsure threshold value; and

classifying said speech signal as background noise if said first parameter is in closer range of said background noise threshold value than said unsure threshold value;

wherein if said first parameter falls between said music threshold value and said background noise threshold value,

classifying said speech signal as music or background noise based on analyzing a plurality of first parameters extracted from said plurality of frames.

2. The method of claim 1, said method further comprising if a value of said first parameter falls between said unsure threshold value and said background noise threshold value, then incrementing a no music frame counter.

3. The method of claim 1, said method further comprising if a value of said first parameter falls between said unsure threshold value and said music threshold value, then incrementing a music frame counter.

4. The method of claim 1, said method further comprising comparing a no music frame counter and a music frame counter after analyzing a plurality of values of said first parameter falling between said background noise threshold value and said music threshold value.

5. The method of claim 4, said method further comprising setting a VAD variable equal to a first value if said no music frame counter is greater than said music frame counter.

6. The method of claim 4, said method further comprising setting a VAD variable equal to a second value if said no music frame counter is less than said music frame counter.

7. The method of claim 4, said method further comprising setting a VAD variable equal to a third value if said no music frame counter is within a predetermined threshold value of said music frame counter.

8. The method of claim 1, wherein said first parameter is related to LPC gain.

9. The method of claim 1, said method further comprising analyzing a plurality of values of a second parameter.

10. The method of claim 9, wherein said second parameter is related to a reflection coefficient.

11. The method of claim 1, said method further comprising performing initial music and background noise detection.

12. The method of claim 1, said method further comprising using a pre-existing parameter to perform music detection.

13. A system for detecting music in a speech signal having a plurality of frames, said system comprising:

a module for defining a music threshold value for a first parameter extracted from a frame of said speech signal;

a module for defining a background noise threshold value for said first parameter;

a module for defining an unsure threshold value for said first parameter, wherein said unsure threshold value falls between said music threshold value and said background noise threshold value;

a module for classifying said speech signal as music if said first parameter is in closer range of said music threshold value than said unsure threshold value, if said first parameter does not fall between said music threshold value and said background noise threshold value;

a module for classifying said speech signal as background noise if said first parameter is in closer range of said background noise threshold value than said unsure threshold value, if said first parameter does not fall between said music threshold value and said background noise threshold value;

a module for classifying said speech signal as music or background noise based on analyzing a plurality of first parameters extracted from said plurality of frames, if said first parameter falls between said music threshold value and said background noise threshold value.

14. The system of claim 13, said system further comprising a module for incrementing a no music frame counter if a value of said first parameter falls between said unsure threshold value and said background noise threshold value.

15. The system of claim 13, said system further comprising a module for incrementing a music frame counter if a value of said first parameter falls between said unsure threshold value and said music threshold value.

16. The system of claim 13, said system further comprising a module for comparing a no music frame counter and a music frame counter after analyzing a plurality of values of said first parameter falling between said background noise threshold value and said music threshold value.

17. The system of claim 16, said system further comprising a module for setting a VAD variable equal to a first value if said no music frame counter is greater than said music frame counter.

18. The system of claim 16, said system further comprising a module for setting a VAD variable equal to a second value if said no music frame counter is less than said music frame counter.

19. The system of claim 16, said system further comprising a module for setting a VAD variable equal to a third value if said no music frame counter is within a predetermined threshold value of said music frame counter.

20. The system of claim 13, wherein said first parameter is related to LPC gain.

21. The system of claim 13, said system further comprising a module for analyzing a plurality of values of a second parameter.

22. The system of claim 21, wherein said second parameter is related to a reflection coefficient.

23. The system of claim 13, said system further comprising a module for performing initial music and background noise detection.

24. The system of claim 13, said system further comprising a module for using a pre-existing parameter to perform music detection.

25. A computer readable medium including computer software program executable by a processor for implementing a method of detecting music in a speech signal having a plurality of frames, said computer software program comprising:

code for defining a music threshold value for a first parameter extracted from a frame of said speech signal;

code for defining a background noise threshold value for said first parameter;

code for defining an unsure threshold value for said first parameter, wherein said unsure threshold value falls between said music threshold value and said background noise threshold value;

code for classifying said speech signal as music if said first parameter is in closer range of said music threshold value than said unsure threshold value, if said first parameter does not fall between said music threshold value and said background noise threshold value;

code for classifying said speech signal as background noise if said first parameter is in closer range of said background noise threshold value than said unsure threshold value, if said first parameter does not fall between said music threshold value and said background noise threshold value;

code for classifying said speech signal as music or background noise based on analyzing a plurality of first parameters extracted from said plurality of frames, if said first parameter falls between said music threshold value and said background noise threshold value.

26. The computer software program of claim 25, said computer software program further comprising code for incrementing a no music frame counter if a value of said first parameter falls between said unsure threshold value and said background noise threshold value.

27. The computer software program of claim 25, said computer software program further comprising code for incrementing a music frame counter if a value of said first parameter falls between said unsure threshold value and said music threshold value.

28. The computer software program of claim 25, said computer software program further comprising code for comparing a no music frame counter and a music frame counter after analyzing a plurality of values of said first parameter falling between said background noise threshold value and said music threshold value.

29. The computer software program of claim 28, said computer software program further comprising code for setting a VAD variable equal to a first value if said no music frame counter is greater than said music frame counter.

30. The computer software program of claim 28, said computer software program further comprising code for setting a VAD variable equal to a second value if said no music frame counter is less than said music frame counter.

31. The computer software program of claim 28, said computer software program further comprising code for setting a VAD variable equal to a third value if said no music frame counter is within a predetermined threshold value of said music frame counter.

32. The computer software program of claim 25, wherein said first parameter is related to LPC gain.

33. The computer software program of claim 25, said computer software program further comprising code for analyzing a plurality of values of a second parameter.

34. The computer software program of claim 33, wherein said second parameter is related to a reflection coefficient.

35. The computer software program of claim 25, said computer software program further comprising code for performing initial music and background noise detection.

36. The computer software program of claim 25, said computer software program further comprising code for using a pre-existing parameter to perform music detection.