ACOUSTIC SIGNAL MODIFICATION

• US 20140278396A1
• Filed: 12/29/2011
• Published: 09/18/2014
• Est. Priority Date: 12/29/2011
• Status: Abandoned Application

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Graumann, David L.
• Application Number:
  US13/977,547
• Publication Number:
  US 20140278396A1
• Time in Patent Office: Days
• US Class Current: 704/233
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 2021/02085 Periodic noise
• CPC Class Codes: G10L 2021/02087 the noise being separate speech, e.g. cocktail party
• CPC Class Codes: G10L 2021/02166 Microphone arrays; Beamforming
• CPC Class Codes: G10L 21/0216 characterised by the method used for estimating noise
• CPC Class Codes: G10L 21/0364 for improving intelligibility
• CPC Class Codes: H04R 2499/13 Acoustic transducers and sound field adaptation in vehicles
• CPC Class Codes: H04R 3/005 for combining the signals of two or more microphones specially adapted for hearing aids H04R25/407

Abstract

Systems and methods for modifying acoustic signals are provided by one or more microphones using acoustic transfer functions. The acoustic transfer functions may be determined based in part on an acoustic model and on a determined location of an acoustic element.

Claims

1. A method comprising:

receiving, by one or more processors, an acoustic model;

monitoring the location of at least one acoustic element;

determining, by the one or more processors, a respective acoustic transfer function corresponding to each of at least one microphone based at least in part on the acoustic model and the location of the at least one acoustic element;

receiving an acoustic signal from each of the at least one microphone; and

modifying, by one or more processors, each of the received acoustic signals based at least in part on the corresponding acoustic transfer function.

2. The method of claim 1, wherein the acoustic model comprises at least one initial transfer function, each of the at least one initial transfer function corresponding to at least one predetermined location.

3. The method of claim 1, wherein the at least one acoustic element is a lip ring associated with an individual.

4. The method of claim 1, wherein monitoring the location of at least one acoustic element comprises imaging the at least one acoustic element using an image sensor.

5. The method of claim 1, wherein monitoring the location of the at least one acoustic element comprises determining a distance between the at least one acoustic element and a range sensor using the range sensor.

6. The method of claim 1, wherein the location of the at least one acoustic element is defined as a point in three-dimensional space.

7. The method of claim 1, wherein determining the acoustic transfer function comprises at least one of:

(i) a volumetric interpolation;

(ii) a volumetric extrapolation;

(iii) a two dimensional interpolation;

(iv) a two-dimensional extrapolation;

(v) a single dimensional interpolation;

or (vi) a single dimensional extrapolation.

8. The method of claim 1, wherein each of the acoustic signals is an electrical signal corresponding to a sound generated by the at least one acoustic element.

9. The method of claim 1, wherein modifying each of the acoustic signals comprises multiplying each of the acoustic signals by an inverse of its corresponding acoustic transfer function.

10. The method of claim 1, further comprising providing at least one of the modified acoustic signals to a speech recognition engine.

11. The method of claim 1, further comprising determining, by the one or more processors, the acoustic model.

12. The method of claim 11, wherein determining the acoustic model comprises determining at least one physical transfer function, each physical transfer function corresponding to a respective location.

13. The method of claim 12, wherein determining the at least one physical transfer function further comprises determining an acoustic response at each of the at least one microphones from a sound provided at each of the respective locations.

14. A system comprising:

at least one sensor configured to provide information of a region of interest associated with a user;

at least one computer-readable medium with an acoustic model stored thereon;

one or more microphones, each microphone configured to generate an acoustic signal based upon a detected sound; and

at least one processor communicatively coupled to the at least one sensor, the computer-readable medium, and the one or more microphones and configured to modify each of the acoustic signals based at least in part on the information of the region of interest and the acoustic model.

15. The system of claim 14, wherein the at least one sensor comprises at least one of a range sensor or an image sensor.

16. The system of claim 14, wherein the information of the region of interest comprises a spatial location of a lip ring for the user.

17. The system of claim 14, wherein the detected sound is a human voice.

18. The system of claim 14, wherein each of the acoustic signals is an electrical signal corresponding to the detected sound.

19. The system of claim 14, wherein the at least one processor is configured to modify each of the acoustic signals by determining an acoustic transfer function corresponding to each of the at least one microphone based on the information of the region of interest and the acoustic model.

20. The system of claim 14, further comprising a speech recognition engine receiving at least one of each of the modified acoustic signals.

21. At least one computer-readable medium comprising computer-executable instructions that, when executed by one or more processors, execute a method comprising;

identifying an acoustic model;

monitoring the location of at least one acoustic element;

determining a respective acoustic transfer function corresponding to each of at least one microphone based at least in part on the acoustic model and the location of the at least one acoustic element;

receiving an acoustic signal from each of the at least one microphone; and

modifying each of the acoustic signals based at least in part on the corresponding acoustic transfer function.

22. The computer-readable medium of claim 21, wherein the acoustic model comprises at least one initial transfer function, each of the at least one initial transfer function corresponding to a location.

23. The computer-readable medium of claim 21, wherein modifying each of the acoustic signals comprises multiplying each of the acoustic signals by an inverse of its corresponding acoustic transfer function.