SYSTEMS AND METHODS FOR PROCESSING AUDIO SIGNALS CAPTURED USING MICROPHONES OF MULTIPLE DEVICES

• US 20130022216A1
• Filed: 07/21/2011
• Published: 01/24/2013
• Est. Priority Date: 07/21/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Ganong, William F. III, Krowitz, David Mark
• Granted Patent: US 9,313,336 B2
• Time in Patent Office: Days
• US Class Current: 381/92
• CPC Class Codes: H04M 2207/18 wireless networks
• CPC Class Codes: H04M 3/569 using the instant speaker's algorithm speech detection per se G10L25/78

Abstract

Systems, methods and apparatus for capturing at least one audio signal using a plurality of microphones that generate a plurality of representations of the at least one audio signal. In some embodiments, the plurality of microphones are disposed in a multiple-microphone setting so that the at least one audio signal is captured by at least two of the plurality of microphones. In some embodiments, at least one of the plurality of microphones is a microphone of a mobile device. The plurality of representations of the at least one audio signal may be processed to obtain a processed representation of the at least one audio signal.

Claims

1. A method comprising acts of:

capturing at least one audio signal using a plurality of microphones that generate a plurality of representations of the at least one audio signal, the plurality of microphones being disposed in a multiple-microphone setting so that the at least one audio signal is captured by at least two of the plurality of microphones, at least one of the plurality of microphones being a microphone of a mobile device; and

processing the plurality of representations of the at least one audio signal to obtain a processed representation of the at least one audio signal.

2. The method of claim 1, wherein each of the plurality of representations is generated using at least one corresponding microphone of the plurality of microphones, and wherein each of the plurality of microphones is associated with at least one corresponding mobile device of a plurality of mobile devices.

3. The method of claim 2, wherein a first mobile device of the plurality of mobile devices is personal to a first user, and a second mobile device of the plurality of mobile devices is personal to a second user different from the first user.

4. The method of claim 1, wherein the act of processing the plurality of representations comprises acts of:

assessing at least one quality of the plurality of representations of the at least one audio signal; and

selecting, as the processed representation, at least one representation from the plurality of representations based at least in part on the at least one quality.

5. The method of claim 1, wherein the act of processing the plurality of representations comprises an act of applying at least one signal enhancement technique to the plurality of representations to obtain the processed representation of the at least one audio signal.

6. The method of claim 1, wherein the act of processing the plurality of representations comprises an act of:

shifting, in time, at least one first representation of the plurality of representations at least in part by performing auto-correlation processing on the at least one first representation and at least one second representation of the plurality of representations.

7. The method of claim 6, wherein the act of shifting the at least one first representation in time is performed in response to detecting movement of at least one of the plurality of microphones.

8. The method of claim 1, wherein:

the at least one audio signal is captured by the plurality of microphones during a meeting attended by a plurality of participants, each of the plurality of microphones corresponding to one of a plurality of devices present at the meeting; and

the plurality of devices are arranged in an ad hoc array that is not constrained to a fixed geometry.

9. The method of claim 8, wherein at least one of the plurality of devices is unknown prior to a beginning of the meeting.

10. The method of claim 8, wherein a total number of devices in the plurality of devices is unknown prior to a beginning of the meeting.

11. The method of claim 8, wherein the ad hoc array has a first geometry at a beginning of the meeting, and wherein the method further comprises:

rearranging, during the meeting, the plurality of devices so that the ad hoc array has a second geometry different from the first geometry.

12. At least one non-transitory computer readable medium having encoded thereon computer executable instructions for causing at least one computer to perform a method comprising acts of:

capturing at least one audio signal using a plurality of microphones that generate a plurality of representations of the at least one audio signal, the plurality of microphones being disposed in a multiple-microphone setting so that the at least one audio signal is captured by at least two of the plurality of microphones, at least one of the plurality of microphones being a microphone of a mobile device; and

processing the plurality of representations of the at least one audio signal to obtain a processed representation of the at least one audio signal.

13. The at least one non-transitory computer readable medium of claim 12, wherein the act of processing the plurality of representations comprises acts of:

assessing at least one quality of the plurality of representations of the at least one audio signal; and

selecting, as the processed representation, at least one representation from the plurality of representations based at least in part on the at least one quality.

14. The at least one non-transitory computer readable medium of claim 12, wherein the act of processing the plurality of representations comprises an act of applying at least one signal enhancement technique to the plurality of representations to obtain the processed representation of the at least one audio signal.

15. The at least one non-transitory computer readable medium of claim 12, wherein the act of processing the plurality of representations comprises an act of:

shifting, in time, at least one first representation of the plurality of representations at least in part by performing auto-correlation processing on the at least one first representation and at least one second representation of the plurality of representations.

16. The at least one non-transitory computer readable medium of claim 15, wherein the act of shifting the at least one first representation in time is performed in response to detecting movement of at least one of the plurality of microphones.

17. A system comprising at least one processor programmed to:

capture at least one audio signal using a plurality of microphones that generate a plurality of representations of the at least one audio signal, the plurality of microphones being disposed in a multiple-microphone setting so that the at least one audio signal is captured by at least two of the plurality of microphones, at least one of the plurality of microphones being a microphone of a mobile device; and

process the plurality of representations of the at least one audio signal to obtain a processed representation of the at least one audio signal.

18. The system of claim 17, wherein the at least one processor is programmed to process the plurality of representations at least in part by:

assessing at least one quality of the plurality of representations of the at least one audio signal; and

selecting, as the processed representation, at least one representation from the plurality of representations based at least in part on the at least one quality.

19. The system of claim 17, wherein the at least one processor is programmed to process the plurality of representations at least in part by applying at least one signal enhancement technique to the plurality of representations to obtain the processed representation of the at least one audio signal.

20. The system of claim 17, wherein the at least one processor is programmed to process the plurality of representations at least in part by:

shifting, in time, at least one first representation of the plurality of representations at least in part by performing auto-correlation processing on the at least one first representation and at least one second representation of the plurality of representations.

21. The system of claim 20, wherein the at least one processor is programmed to shift the at least one first representation in time in response to detecting movement of at least one of the plurality of microphones.

22. The system of claim 17, further comprising a plurality of devices, wherein:

the at least one audio signal is captured by the plurality of microphones during a meeting attended by a plurality of participants, each of the plurality of microphones corresponding to one of the plurality of devices present at the meeting; and

the plurality of devices are arranged in an ad hoc array that is not constrained to a fixed geometry.