Speech recognition of mobile devices

• US 20030236099A1
• Filed: 06/20/2002
• Published: 12/25/2003
• Est. Priority Date: 06/20/2002
• Status: Active Grant

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Knauerhase, Robert C., Deisher, Michael E.
• Granted Patent: US 7,224,981 B2
• Time in Patent Office: Days
• US Class Current: 455/522
• 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 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: H04M 1/72457 according to geographic location
• CPC Class Codes: H04M 2250/74 with voice recognition means voice activated dialling H04M1/271; voice recognition algorithms G10L15/00

Abstract

Speech recognition in mobile processor-based devices may be improved by using location information. Location information may be derived from on-board hardware or from information provided remotely. The location information may assist in a variety of ways in improving speech recognition. For example, the ability to adapt to the local ambient conditions, including reverberation and noise characteristics, may be enhanced by location information. In some embodiments, pre-developed models or context information may be provided from a remote server for given locations.

Claims

1. A method comprising:

obtaining information about the location of a mobile device; and

using said location information to provide speech recognition.

2. The method of claim 1 including obtaining an acoustic model linked to a particular location for use in improving speech recognition.

3. The method of claim 2 including receiving said model from a remote server over a wireless network.

4. The method of claim 2 including tailoring the acoustic model based on local characteristics.

5. The method of claim 4 including transmitting said model together with position coordinates to a remote server.

6. The method of claim 1 wherein obtaining information includes obtaining information about the size of a surrounding space.

7. The method of claim 1 wherein obtaining information includes adjusting an acoustic model to account for reverberation.

8. The method of claim 1 wherein obtaining information includes selecting feature extraction or noise reduction algorithms.

9. The method of claim 1 wherein obtaining information includes obtaining information about nearby speakers.

10. The method of claim 1 wherein obtaining information includes obtaining information about the size of the surrounding space, obtaining information about reverberation, selecting noise reduction algorithms, and obtaining information about nearby speakers to develop a new acoustic model for the current location.

11. The method of claim 1 including configuring a microphone array based on the location of nearby speakers whose speech is not to be recognized.

12. An article comprising a medium storing instructions that, if executed, enable a processor-based system to perform the steps of:

obtaining information about the location of a mobile device; and

using said location information to provide speech recognition.

13. The article of claim 12 further storing instructions that, if executed, enable the processor-based system to perform the step of obtaining an acoustic model linked to a particular location for use in improving speech recognition.

14. The article of claim 13 further storing instructions that, if executed, enable the processor-based system to perform the step of receiving said model from a remote server over a wireless network.

15. The article of claim 13 further storing instructions that, if executed, enable the processor-based system to perform the step of tailoring the acoustic model based on local characteristics.

16. The article of claim 15 further storing instructions that, if executed, enable the processor-based system to perform the step of transmitting said model together with position coordinates to a remote server.

17. The article of claim 12 further storing instructions that, if executed, enable the processor-based system to perform the step of obtaining information includes obtaining information about the size of a surrounding space.

18. The article of claim 12 further storing instructions that, if executed, enable the processor-based system to perform the step of obtaining information includes adjusting an acoustic model to account for reverberation.

19. The article of claim 12 further storing instructions that, if executed, enable the processor-based system to perform the step of obtaining information includes selecting feature extraction or noise reduction algorithms.

20. The article of claim 12 further storing instructions that, if executed, enable the processor-based system to perform the step of obtaining information includes obtaining information about nearby speakers.

21. The article of claim 12 further storing instructions that, if executed, enable the processor-based system to perform the steps of obtaining information includes obtaining information about the size of the surrounding space, obtaining information about reverberation, selecting noise reduction algorithms, and obtaining information about nearby speakers to develop a new acoustic model for the current location.

22. The article of claim 12 further storing instructions that, if executed, enable the processor-based system to perform the step of configuring a microphone array based on the location of nearby speakers whose speech is not to be recognized.

23. A system comprising:

a processor;

a position determining device coupled to said processor; and

a storage coupled to said processor storing instructions that enable the processor to use location information to provide speech recognition.

24. The system of claim 23 wherein said position locating device is a global positioning satellite device.

25. The system of claim 23 wherein said storage stores instructions that enable the processor to obtain an acoustic model linked to a particular location for use in improving speech recognition.

26. The system of claim 25 wherein said storage stores instructions to receive a model from a remote server over a wireless network.

27. The system of claim 24 wherein said system automatically tailors an acoustic model for a particular location and transmits that model together with position coordinates to a remote server.

28. The system of claim 23 wherein said system automatically obtains information about the size of a space surrounding said system.

29. The system of claim 23 wherein said system automatically obtains information about nearby speakers.

30. The system of claim 29 wherein said system includes a microphone array and automatically configures said microphone array based on the location of nearby speakers.

31. A server comprising:

a processor;

a wireless interface coupled to said processor; and

a storage coupled to said processor that stores instructions that, if executed, enable the processor to receive requests for acoustic models, obtain information about the location of the requester, correlate the location to an appropriate model, and transmit the model to the requester.