Method and apparatus to improve accuracy of mobile speech enable services

• US 20030236665A1
• Filed: 06/24/2002
• Published: 12/25/2003
• Est. Priority Date: 06/24/2002
• Status: Active Grant

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Sharma, Sangita R.
• Granted Patent: US 7,174,298 B2
• Time in Patent Office: Days
• US Class Current: 704/260
• CPC Class Codes: G10L 15/065 Adaptation
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

A speech recognition system includes a user profile to store acoustic data and a corresponding text transcript. A speech recognition (“SR”) server downloads the acoustic data and the corresponding text transcript that are stored in the user profile. A speech recognition engine is included to adapt an acoustic model based on the acoustic data.

Claims

1. A speech recognition system, comprising:

a user profile to store acoustic data and a corresponding text transcript;

a speech recognition (“

SR”

) server to download the acoustic data and the corresponding text transcript that are stored in the user profile; and

a speech recognition engine to adapt an acoustic model based on the acoustic data.

2. The speech recognition system according to claim 1, wherein the user profile is stored within a mobile communication device.

3. The speech recognition system according to claim 1, wherein the acoustic data is a digitized sample of a user'"'"'s voice.

4. The speech recognition system according to claim 1, wherein the speech recognition server records a background environment received from a mobile communication device.

5. The speech recognition system according to claim 4, wherein the speech recognition server combines the background environment and the acoustic data, and the speech recognition engine adapts the acoustic model based on the acoustic data and the background environment.

6. The speech recognition system according to claim 1, wherein the acoustic model is user-independent.

7. A mobile communication system, comprising:

a mobile communication device to store a user profile;

a transmitter to transmit a transmitting signal to the mobile communication device;

a receiver to receive a receiving signal from the mobile communication device; and

a speech recognition system, including

a speech recognition (“

SR”

) server to download acoustic data and a corresponding text transcript, and

a speech recognition engine to adapt an acoustic model based on the acoustic data.

8. The mobile communication system according to claim 7, wherein the transmitter and the receiver are within a single device.

9. The mobile communication system according to claim 7, wherein the acoustic data is a digitized sample of a user'"'"'s voice.

10. The mobile communication system according to claim 7, wherein the speech recognition server records a background environment received from the mobile communication device.

11. The mobile communication system according to claim 10, wherein the speech recognition server combines the background environment and the acoustic data, and the speech recognition engine adapts the acoustic model based on the acoustic data and the background environment.

12. The mobile communication system according to claim 7, wherein the acoustic model is user-independent.

13. A method of adapting an acoustic model to improve recognition accuracy, comprising:

recording a user'"'"'s voice on a mobile communication device;

storing acoustic data and a corresponding text transcript in a user profile;

downloading the acoustic data and the corresponding text transcript that is stored in the user profile; and

adapting an acoustic model based on the acoustic data.

14. The method according to claim 13, wherein the acoustic data is a digitized sample of the user'"'"'s voice.

15. The method according to claim 13, wherein a speech recognition server records a background environment received from the mobile communication device.

16. The method according to claim 15, wherein the speech recognition server combines the background environment and the acoustic data, and a speech recognition engine adapts the acoustic model based on the acoustic data and the background environment.

17. The method according to claim 13, wherein the user profile is stored within the mobile communication device.

18. The method according to claim 13, wherein downloading the acoustic data and the corresponding text transcript is performed by a speech recognition server.

19. The method according to claim 13, wherein adapting the acoustic model based on the acoustic data is performed by a speech recognition engine.

20. The method according to claim 13, wherein the acoustic model is user-independent.

21. The method according to claim 13, wherein the method further includes using a revised acoustic model to process subsequent voice queries of a user.

22. An article comprising:

a storage medium having stored thereon instructions that when executed by a machine result in the following;

recording a user'"'"'s voice on a mobile communication device,

storing acoustic data and a corresponding text transcript in a user profile,

downloading the acoustic data and the corresponding text transcript that are stored in the user profile, and

adapting an acoustic model based on the acoustic data.

23. The article according to claim 22, wherein the acoustic data is a digitized sample of the user'"'"'s voice.

24. The article according to claim 22, wherein a speech recognition server records a background environment received from the mobile communication device.

25. The article according to claim 24, wherein the speech recognition server combines the background environment and the acoustic data, and a speech recognition engine adapts the acoustic model based on the acoustic data and the background environment.

26. The article according to claim 22, wherein the user profile is stored within the mobile communication device.

27. The article according to claim 22, wherein a speech recognition server performs downloading the acoustic data and the corresponding text transcript.

28. The article according to claim 22, wherein a speech recognition engine performs adapting the acoustic model based on the acoustic data.

29. The article according to claim 22, wherein the acoustic model is user-independent.

30. The article according to claim 22, wherein execution of the instructions further results in using a revised acoustic model to process subsequent voice queries of the user.