BACKGROUND SOUND REMOVAL FOR PRIVACY AND PERSONALIZATION USE

• US 20130137480A1
• Filed: 10/11/2011
• Published: 05/30/2013
• Est. Priority Date: 08/11/2010
• Status: Active Grant

• Current Assignee: DSP Group Ltd. (Synaptics Incorporated)
• Original Assignee: BoneTone Communications Limited (Synaptics Incorporated)
• Inventors: Yehuday, Uri, Heiman, Arie
• Granted Patent: US 8,768,406 B2
• Time in Patent Office: Days
• US Class Current: 455/550.1
• CPC Class Codes: G10L 2021/02166 Microphone arrays; Beamforming
• CPC Class Codes: G10L 21/003 Changing voice quality, e.g. pitch or formants
• CPC Class Codes: G10L 21/0208 Noise filtering
• CPC Class Codes: H04M 1/19 Arrangements of transmitters, receivers, or complete sets to prevent eavesdropping, to attenuate local noise or to prevent undesired transmission; Mouthpieces or receivers specially adapted therefor circuit arrangements for preventing eavesdropping H04M1/68; telephone cabinets E04H1/14
• CPC Class Codes: H04M 19/08 with current supply sources at the substations generating ringing current H04M19/04

Abstract

A system for background sound removal, the system may include: a noise reduction circuit arranged to apply a background sound reduction process on multiple samples of background sound and speech to provide first signals that comprise residual background sound; a background cancellation circuit arranged to remove the residual background sound from the first signals to provide second signals; and an output circuit arranged to output a mixture of the second signals and at least zero selected signals to a sound generating circuit that is arranged to output audio signals representative of the mixture.

Claims

1. A system for background sound removal, the system comprises:

a noise reduction circuit arranged to apply a background sound reduction process on multiple samples of background sound and speech to provide first signals that comprise residual background sound;

a background cancellation circuit arranged to remove the residual background sound from the first signals to provide second signals; and

an output circuit arranged to output a mixture of the second signals and at least zero selected signals to a sound generating circuit that is arranged to output audio signals representative of the mixture.

2. The system according to claim 1, wherein the output circuit is arranged to output only the second signals to the sound generating circuit.

3. The system according to claim 1, wherein the output signals is arranged to output a mixture of the second signals and selected signals that are represent selected background sounds.

4. The system according to claim 1, wherein the background cancellation circuit comprises a speech extractor circuit that is followed by a speech synthesis circuit.

5. The system according to claim 1, comprising a selection circuit arranged to select the selected signals out of multiple signals representing different desired background sounds.

6. The system according to claim 1, comprising a selection circuit arranged to select the selected signals out of at least one set of signals representing a desired background sound and the background sound.

7. The system according to claim 1, wherein the selecting circuit and the sound generating circuit belong to a same communication device.

8. The system according to claim 1, wherein the selecting circuit and the sound generating circuit belong to different components of a same communication device.

9. The system according to claim 1, wherein the sound generating circuit belongs to a phone while the selection circuit belongs to a headset that is arranged to communicate with the phone.

10. The system according to claim 1 wherein the noise reduction circuit is arranged to receive the multiple samples from a plurality of microphones.

11. The system according to claim 1 comprising the sound generating circuit.

12. A method for background sound removal, the method comprises:

applying, by a noise reduction circuit, a background sound reduction process on multiple samples of background sound and speech to provide first signals that comprise residual background sound;

removing, by a background cancellation circuit, the residual background sound from the first signals to provide second signals; and

outputting, by an output circuit, a mixture of the second signals and at least zero selected signals to a sound generating circuit that is arranged to output audio signals representative of the mixture.

13. The method according to claim 12, comprising outputting only the second signals to the sound generating circuit.

14. The method according to claim 12, comprising outputting a mixture of the second signals and selected signals that represent selected background sounds.

15. The method according to claim 12, comprising removing the residual background sound by extracting speech features from the first signals to provide intermediate signals and performing speech synthesis on the intermediate signals.

16. The method according to claim 12, comprising selecting the selected signals out of multiple signals representing different desired background sounds.

17. The method according to claim 12, comprising selecting the selected signals out of at least one set of signals representing a desired background sound and the background sound.

18. The method according to claim 12, wherein the selecting circuit and the sound generating circuit belong to a same communication device.

19. The method according to claim 12, wherein the selecting circuit and the sound generating circuit belong to different components of a same communication device.

20. The method according to claim 12, wherein the sound generating circuit belongs to a phone while the selection circuit belongs to a headset that is arranged to communicate with the phone.

21. The method according to claim 12 comprising receiving the multiple samples from a plurality of microphones.

22. The method according to claim 12 comprising outputting, by the audio outputting circuit, audio signals representative of the mixture.

23. A non-transitory computer readable medium that stores instructions for:

applying a background sound reduction process on multiple samples of background sound and speech to provide first signals that comprise residual background sound;

removing the residual background sound from the first signals to provide second signals; and

outputting a mixture of the second signals and at least zero selected signals to a sound generating circuit that is arranged to output audio signals representative of the mixture.

24. The non-transitory computer readable medium according to claim 23, storing instructions for outputting only the second signals to the sound generating circuit.

25. The non-transitory computer readable medium according to claim 23, storing instructions for outputting a mixture of the second signals and selected signals that represent selected background sounds.

26. The non-transitory computer readable medium according to claim 23, storing instructions for removing the residual background sound by extracting speech features from the first signals to provide intermediate signals and performing speech synthesis on the intermediate signals.

27. The non-transitory computer readable medium according to claim 23, storing instructions for selecting the selected signals out of multiple signals representing different desired background sounds.

28. The non-transitory computer readable medium according to claim 23, storing instructions for selecting the selected signals out of at least one set of signals representing a desired background sound and the background sound.

29. The non-transitory computer readable medium according to claim 23 storing instructions for receiving the multiple samples from a plurality of microphones.

30. The non-transitory computer readable medium according to claim 23 storing instructions for outputting audio signals representative of the mixture.

31. A system for background sound removal, the system comprises:

a processor arranged to remove background sound from multiple samples from multiple microphones to provide background sound removed signals;

a memory arranged to store multiple samples of desired background sounds;

an interface coupled between the processor and a sound generating circuit;

wherein the processor is further adapted to;

determine whether to send to the sound generating circuit (a) only the background removed signals;

or (b) a mixture of the background removed signals and samples representative of a desired background sound; and

provide to the sound generating circuit, via the interface, signals in response to the determination.

32. The system according to claim 31 wherein the processor comprises a noise reduction circuit arranged to apply a background sound reduction process on the multiple samples of background sound and speech to provide first signals that comprise residual background sound;

and a background cancellation circuit arranged to remove the residual background sound from the first signals to provide second signals.

33. The system according to claim 32, wherein the background cancellation circuit comprises a speech extractor circuit that is followed by a speech synthesis circuit.

34. The system according to claim 31, wherein the processor is arranged to select the selected signals out of multiple signals representing different desired background sounds.

35. The system according to claim 31, wherein the processor is arranged to select the selected signals out of at least one set of signals representing a desired background sound and the background sound.

36. The system according to claim 31, wherein the selecting circuit and the sound generating circuit belong to a same communication device.

37. The system according to claim 31, wherein the selecting circuit and the sound generating circuit belong to different components of a same communication device.

38. The system according to claim 31, wherein the sound generating circuit belongs to a phone while the selection circuit belongs to a headset that is arranged to communicate with the phone.

39. A method, comprising:

removing background sound from multiple samples from multiple microphones to provide background sound removed signals;

storing multiple samples of desired background sounds;

determining whether to send to the sound generating circuit (a) only the background removed signals;

or (b) a mixture of the background removed signals and samples representative of a desired background sound; and

providing signals to a sound generating circuit in response to the determination.

40. The method according to claim 40, comprising:

applying, by a noise reduction circuit, a background sound reduction process on multiple samples of background sound and speech to provide first signals that comprise residual background sound;

removing, by a background cancellation circuit, the residual background sound from the first signals to provide second signals; and

outputting, by an output circuit, a mixture of the second signals and at least zero selected signals to a sound generating circuit that is arranged to output audio signals representative of the mixture.

41. A non-transitory computer readable medium that stores instructions for removing background sound from multiple samples from multiple microphones to provide background sound removed signals;

storing multiple samples of desired background sounds;

determining whether to send to the sound generating circuit (a) only the background removed signals;

or (b) a mixture of the background removed signals and samples representative of a desired background sound; and

providing signals to a sound generating circuit in response to the determination.

42. The non-transitory computer readable medium according to claim 42, storing instructions for applying a background sound reduction process on multiple samples of background sound and speech to provide first signals that comprise residual background sound;

removing the residual background sound from the first signals to provide second signals; and

outputting a mixture of the second signals and at least zero selected signals to a sound generating circuit that is arranged to output audio signals representative of the mixture.