Adjusting a speech engine for a mobile computing device based on background noise

• US 8,121,837 B2
• Filed: 04/24/2008
• Issued: 02/21/2012
• Est. Priority Date: 04/24/2008
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Agapi, Ciprian, Bodin, William K., Cross, Charles W. Jr., Patel, Paritosh D.
• Primary Examiner(s): Han, Qi
• Application Number:
  US12/109,151
• Publication Number:
  US 20090271188A1
• Time in Patent Office: 1,398 Days
• Field of Search: 704/233, 704/236, 704/243, 704/244, 704/250, 704/255
• US Class Current: 704/233
• 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 21/0208 Noise filtering

Abstract

Methods, apparatus, and products are disclosed for adjusting a speech engine for a mobile computing device based on background noise, the mobile computing device operatively coupled to a microphone, that include: sampling, through the microphone, background noise for a plurality of operating environments in which the mobile computing device operates; generating, for each operating environment, a noise model in dependence upon the sampled background noise for that operating environment; and configuring the speech engine for the mobile computing device with the noise model for the operating environment in which the mobile computing device currently operates.

Claims

1. A method of adjusting a speech engine for a mobile computing device based on background noise, the mobile computing device operatively coupled to a microphone, the method comprising:

determining whether a previously-generated background noise model exists for a current operating environment of the mobile computing device; and

if it is determined that no previously-generated background noise model exists for the current operating environment;

sampling, through the microphone, background noise for the current operating environment,

generating a background noise model based at least in part on the sampled background noise, and

configuring the speech engine for the mobile computing device with the background noise model.

2. The method of claim 1, wherein the method further comprises detecting a change in an operating environment of the mobile computing device.

3. The method of claim 1, wherein:

if it is determined that the previously-generated background noise model exists for the current operating environment, configuring the speech engine with the previously-generated background noise model.

4. The method of claim 1, wherein configuring the speech engine for the mobile computing device with the background noise model for the current operating environment comprises updating a current acoustic model for the speech engine with the background noise model.

5. The method of claim 1, wherein configuring the speech engine for the mobile computing device with the background noise model for the current operating environment comprises replacing a current acoustic model for the speech engine with another acoustic model already incorporating the background noise model.

6. The method of claim 1, wherein:

the mobile computing device is implemented as a multimodal device having installed upon it a multimodal application, the multimodal device supporting multiple modes of user interaction with the multimodal application, the modes of user interaction including a voice mode and one or more non-voice modes, the multimodal application operatively coupled to the speech engine; and

the method further comprises performing speech recognition for the multimodal application using the speech engine configured for the mobile computing device with the background noise model for the current operating environment.

7. The method of claim 1, wherein the background noise model comprises a predetermined number of frequency domain components.

8. An apparatus for adjusting a speech engine for a mobile computing device based on background noise, the mobile computing device operatively coupled to a microphone, the apparatus comprising:

a processor configured to;

determine whether a previously-generated background noise model exists for a current operating environment of the mobile computing device; and

if it is determined that no previously-generated background noise model exists for the current operating environment, the processor is further configured to;

sample, through the microphone, background noise for the current operating environment;

generate a background noise model based at least in part on the sampled background noise, and

configure the speech engine for the mobile computing device with the background noise model.

9. The apparatus of claim 8, wherein the processor is further configured to detect a change in an operating environment of the mobile computing device.

10. The apparatus of claim 8, wherein:

if it is determined that the previously-generated background model exists for the current operating environment, the processor is further configured to configure the speech engine for the mobile computing device with the previously-generated noise model for the current operating environment.

11. The apparatus of claim 8, wherein the processor is configured to configure the speech engine for the mobile computing device with the background noise model by updating a current acoustic model for the speech engine with the background noise model.

12. The apparatus of claim 8, wherein the processor is configured to configure the speech engine for the mobile computing device with the background noise model for the current operating environment by replacing a current acoustic model for the speech engine with another acoustic model already incorporating the background noise model.

13. The apparatus of claim 8, wherein:

the mobile computing device is implemented as a multimodal device having installed upon it a multimodal application, the multimodal device supporting multiple modes of user interaction with the multimodal application, the modes of user interaction including a voice mode and one or more non-voice modes, the multimodal application operatively coupled to the speech engine; and

the processor is configured to perform speech recognition for the multimodal application using the speech engine configured for the mobile computing device with the noise model for the current operating environment.

14. The apparatus of claim 8, wherein the background noise model comprises a predetermined number of frequency domain components.

15. A computer readable recordable storage medium storing processor-executable instructions that when executed by a processor perform:

determining whether a previously-generated background noise model exists for a current operating environment of a mobile computing device; and

if it is determined that no previously-generated background model exists for the current operating environment;

sampling, through a microphone operatively coupled to the mobile computing device, background noise for the current operating environment,

generating a background noise model based at least in part on the sampled background noise, and

configuring the speech engine for the mobile computing device with the background noise model.

16. The computer readable recordable storage medium of claim 15, wherein the method further comprises:

detecting a change in an operating environment of the mobile computing device.

17. The computer readable recordable storage medium of claim 15, wherein:

if it is determined that the previously-generated background model exists for the current operating environment, configuring the speech engine with the previously-generated background noise model.

18. The computer readable recordable storage medium of claim 15, wherein configuring the speech engine for the mobile computing device with the background noise model for the current operating environment comprises updating a current acoustic model for the speech engine with the background noise model.

19. The computer readable recordable storage medium of claim 15, wherein configuring the speech engine for the mobile computing device with the background noise model for the current operating environment comprises replacing a current acoustic model for the speech engine with another acoustic model already incorporating the background noise model.

20. The computer readable recordable storage medium of claim 15, wherein:

the mobile computing device is implemented as a multimodal device having installed upon it a multimodal application, the multimodal device supporting multiple modes of user interaction with the multimodal application, the modes of user interaction including a voice mode and one or more non-voice modes, the multimodal application operatively coupled to the speech engine; and

the computer program product comprises computer program instructions capable of performing speech recognition for the multimodal application using the speech engine configured for the mobile computing device with the background noise model for the current operating environment.