SPEECH PROCESSING RESPONSIVE TO ACTIVE NOISE CONTROL MICROPHONES

• US 20130211828A1
• Filed: 02/13/2012
• Published: 08/15/2013
• Est. Priority Date: 02/13/2012
• Status: Abandoned Application

• Current Assignee: General Motors LLC (General Motors Company)
• Original Assignee: General Motors LLC (General Motors Company)
• Inventors: Gratke, Jesse T., Ampunan, Nathan D., Buch, Gary M., Shahmurad, Bassam S., Martin, Douglas C.
• Application Number:
  US13/372,249
• Publication Number:
  US 20130211828A1
• Time in Patent Office: Days
• US Class Current: 704/226
• CPC Class Codes: G10L 2021/02165 Two microphones, one receiving mainly the noise signal and the other one mainly the speech signal
• CPC Class Codes: G10L 21/0216 characterised by the method used for estimating noise

Abstract

Speech processing for a vehicle, including receiving speech from a user via at least one speech microphone that converts the speech into a speech signal, receiving vehicle noise via at least one active noise control microphone that converts the noise into a vehicle noise signal, and processing the speech signal in response to the vehicle noise signal to reduce vehicle noise in the speech signal.

Claims

1. A speech processing system for a vehicle, comprising:

at least one speech microphone that converts user speech into speech signals;

at least one active noise control microphone that converts vehicle noise into vehicle noise signals; and

a controller in communication with the microphones to process the speech signal in response to the vehicle noise signal to reduce vehicle noise in the speech signal.

2. The system of claim 1, wherein the at least one speech microphone is positioned in front of, above, and laterally between driver and passenger seats.

3. The system of claim 1 wherein the at least one speech microphone includes a single directional microphone.

4. The system of claim 1, wherein the at least one speech microphone includes multiple directional microphones.

5. The system of claim 4, wherein the multiple directional microphones include beamforming microphones, and the at least one speech microphone also includes at least two omnidirectional microphones positioned laterally outboard of the beamforming microphones.

6. The system of claim 1, wherein the at least one speech microphone includes at least one omnidirectional microphone.

7. The system of claim 1, wherein the at least one active noise control microphone includes multiple omnidirectional microphones.

8. The system of claim 1, wherein the at least one speech microphone is positioned in front of a user in the vehicle, and the at least one active noise control microphone is positioned to the side of the user in the vehicle.

9. The system of claim 1, wherein the at least one speech microphone includes a single directional microphone, and the at least one active noise control microphone is used as a speech correlation microphone for correlation based dual microphone speech signal processing.

10. The system of claim 1, wherein the system is a speech recognition system.

11. The system of claim 10, wherein the controller includes:

a speech recognition pre-processor to process the speech signal in response to the vehicle noise signal to reduce vehicle noise in the speech signal and to generate acoustic feature vectors from the speech signal;

a speech recognition decoder to decode the acoustic feature vectors and produce speech hypotheses; and

a speech recognition post-processor to identify recognized speech from the speech hypotheses.

12. A method of speech processing for a vehicle, comprising:

(a) receiving speech from a user via at least one speech microphone that converts the speech into a speech signal;

(b) receiving vehicle noise via at least one active noise control microphone that converts the noise into a vehicle noise signal; and

(c) processing the speech signal in response to the vehicle noise signal to reduce vehicle noise in the speech signal.

13. The method of claim 12, further comprising adjusting a noise reduction algorithm in response to the vehicle noise signal.

14. The method of claim 13, wherein step (c) includes applying the adjusted noise reduction algorithm to the speech signal.

15. The method of claim 12, further comprising using the at least one active noise control microphone as a speech correlation microphone for correlation based dual microphone speech signal processing.

16. The method of claim 12, wherein the method is a speech recognition method.

17. The method of claim 16, wherein the method also includes:

pre-processing the speech signal in response to the vehicle noise signal to reduce vehicle noise in the speech signal and to generate acoustic feature vectors from the speech signal;

decoding the acoustic feature vectors to produce speech hypotheses; and

post-processing the speech hypotheses to identify recognized speech from the speech hypotheses.

18. A computer program product embodied in a computer-readable medium and including instructions usable by a computer processor of a speech processing system to cause the system to implement steps of a method according to claim 12.