MOBILE ENVIRONMENT SPEECH PROCESSING FACILITY

• US 20080221879A1
• Filed: 10/01/2007
• Published: 09/11/2008
• Est. Priority Date: 03/07/2007
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Vlingo Corporation (Microsoft Corporation)
• Inventors: Phillips, Michael S., Nguyen, John N., Shu, Han, Kishchenko, Roman V., Cerra, Joseph P.
• Granted Patent: US 8,996,379 B2
• Time in Patent Office: Days
• US Class Current: 704/235
• CPC Class Codes: G10L 15/065 Adaptation
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

In embodiments of the present invention improved capabilities are described for a mobile environment speech processing facility. The present invention may provide for the entering of text into a software application resident on a mobile communication facility, where recorded speech may be presented by the user using the mobile communications facility'"'"'s resident capture facility. Transmission of the recording may be provided through a wireless communication facility to a speech recognition facility, and may be accompanied by information related to the software application. Results may be generated utilizing the speech recognition facility that may be independent of structured grammar, and may be based at least in part on the information relating to the software application and the recording. The results may then be transmitted to the mobile communications facility, where they may be loaded into the software application. In addition, the speech recognition facility may be adapted based on usage.

Claims

1. A method of entering text into a software application resident on a mobile communication facility comprising:

recording speech presented by a user using a mobile communication facility resident capture facility;

transmitting the recording through a wireless communication facility to a speech recognition facility;

transmitting information relating to the software application to the speech recognition facility;

generating results utilizing the speech recognition facility independent of a structured grammar based at least in part on the information relating to the software application and the recording;

transmitting the results to the mobile communications facility;

loading the results into the software application; and

adapting the speech recognition facility based on usage.

2. The method of claim 1, wherein adapting the speech recognition facility based on usage includes at least one of adapting an acoustic model, adapting a set of pronunciation, adapting a vocabulary, and adapting a language model.

3. The method of claim 1, wherein adapting the speech recognition facility includes adapting recognition models based on usage data.

4. The method of claim 3, wherein adapting recognition models is an automated process.

5. The method of claim 3, wherein adapting recognition models makes use of the recording.

6. The method of claim 3, wherein adapting recognition models makes use of words that are recognized.

7. The method of claim 3, wherein adapting recognition models makes use of human transcriptions of speech of the user.

8. The method of claim 3, wherein adapting recognition models makes use of the information relating to the software application about actions taken by the user.

9. The method of claim 3, wherein adapting recognition models is specific to the user or groups of users.

10. The method of claim 3, wherein adapting recognition models is specific to the software application or groups of software applications.

11. The method of claim 3, wherein adapting recognition models is specific to text fields within the software application or groups of text fields within the software applications.

12. The method of claim 1, wherein the information relating to the software application includes at least one of an identity of the application, an identity of a text box within the application, contextual information within the application, an identity of the mobile communication facility, and an identity of the user.

13. The method of claim 1, wherein the step of generating the results based at least in part on the information relating to the software application involves selecting at least one of a plurality of recognition models based on the information relating to the software application and the recording.

14. The method of claim 13, wherein the at least one of a plurality of recognition models includes at least one of an acoustic model, a set of pronunciations, a vocabulary, and a language model.

15. The method of claim 13, wherein the at least one of a plurality of recognition models includes at least one of a plurality of language models, wherein the at least one of the plurality of language models are selected based on the information relating to the software application and the recording.

16. The method of claim 15, wherein the selection of the at least one of a plurality of language models is based on the information relating to the software application and the recording.

17. The method of claim 16, wherein the plurality of language models is run at the same time in the speech recognition facility.

18. The method of claim 16, wherein the plurality of language models is run in multiple passes in the speech recognition facility.

19. The method of claim 18, wherein the selection of the at least one of a plurality of language models for subsequent passes in the speech recognition facility is based on results obtained in at least one of the multiple passes in the speech recognition facility.

20. The method of claim 18, wherein the outputs of the multiple passes in the speech recognition facility are combined into a single result by choosing the highest scoring result.

21. The method of claim 18, wherein the outputs of the multiple passes in the speech recognition facility are combined into a single result by a merging of results from the multiple passes.

22. The method of claim 21, wherein the merging of results is at a word level.

23. The method of claim 21, wherein the merging of results is done at a phrase level.

24. A system of entering text into a software application resident on a mobile communication facility comprising:

recording speech presented by a user using a mobile communication facility resident capture facility;

transmitting the recording through a wireless communication facility to a speech recognition facility;

transmitting information relating to the software application to the speech recognition facility;

generating results utilizing the speech recognition facility independent of a structured grammar based at least in part on the information relating to the software application and the recording;

transmitting the results to the mobile communications facility;

loading the results into the software application; and

adapting the speech recognition facility based on usage.

25. The system of claim 24, wherein adapting the speech recognition facility based on usage includes at least one of adapting an acoustic model, adapting a pronunciation, adapting a vocabulary, and adapting a language model.