System and method for mobile automatic speech recognition
View Patent ↗A system and method of updating automatic speech recognition parameters on a mobile device are disclosed. The method comprises storing user account-specific adaptation data associated with ASR on a computing device associated with a wireless network, generating new ASR adaptation parameters based on transmitted information from the mobile device when a communication channel between the computing device and the mobile device becomes available and transmitting the new ASR adaptation data to the mobile device when a communication channel between the computing device and the mobile device becomes available. The new ASR adaptation data on the mobile device more accurately recognizes user utterances.
1. A method comprising:
receiving automatic speech recognition data from a mobile device, wherein the mobile device performs speech recognition using automatic speech recognition parameters based on the automatic speech recognition data; and
transmitting, to the mobile device, a set of automatic speech recognition adaptation parameters which update the automatic speech recognition parameters of the mobile device, wherein the set of automatic speech recognition adaptation parameters is based on the automatic speech recognition data.
2. The method of claim 1 , wherein the set of automatic speech recognition parameters is further based on stored, user specific, adaptation data.
3. The method of claim 2 , wherein the automatic speech recognition data comprises one of: an environment of the mobile device and multi-modal input from a user associated with the mobile device.
4. The method of claim 1 , wherein the automatic speech recognition data comprises an automatic speech recognition output from the mobile device.
5. The method of claim 1 , wherein the automatic speech recognition data comprises audio data gathered by the mobile device during automatic speech recognition with a user.
6. The method of claim 1 , further comprising normalizing the automatic speech recognition data using frequency warping.
7. The method of claim 6 , wherein the frequency warping is performed by selecting a singular linear warping function using normalized automatic speech recognition data.
8. A system comprising:
a processor; and
a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising:
receiving automatic speech recognition data from a mobile device, wherein the mobile device performs speech recognition using automatic speech recognition parameters based on the automatic speech recognition data; and
transmitting, to the mobile device, a set of automatic speech recognition adaptation parameters which update the automatic speech recognition parameters of the mobile device, wherein the set of automatic speech recognition adaptation parameters is based on the automatic speech recognition data.
9. The system of claim 8 , wherein the set of automatic speech recognition parameters is further based on stored, user specific, adaptation data.
10. The system of claim 9 , wherein the automatic speech recognition data comprises one of: an environment of the mobile device and multi-modal input from a user associated with the mobile device.
11. The system of claim 8 , wherein the automatic speech recognition data comprises an automatic speech recognition output from the mobile device.
12. The system of claim 8 , wherein the automatic speech recognition data comprises audio data gathered by the mobile device during automatic speech recognition with a user.
13. The system of claim 8 , the computer-readable storage medium having additional instructions stored which result in operations comprising normalizing the automatic speech recognition data using frequency warping.
14. The system of claim 13 , wherein the frequency warping is performed by selecting a singular linear warping function using normalized automatic speech recognition data.
15. A computer-readable storage device having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprising:
receiving automatic speech recognition data from a mobile device, wherein the mobile device performs speech recognition using automatic speech recognition parameters based on the automatic speech recognition data; and
transmitting, to the mobile device, a set of automatic speech recognition adaptation parameters which update the automatic speech recognition parameters of the mobile device, wherein the set of automatic speech recognition adaptation parameters is based on the automatic speech recognition data.
16. The computer-readable storage device of claim 15 , wherein the set of automatic speech recognition parameters is further based on stored, user specific, adaptation data.
17. The computer-readable storage device of claim 16 , wherein the automatic speech recognition data comprises one of: an environment of the mobile device and multi-modal input from a user associated with the mobile device.
18. The computer-readable storage device of claim 15 , wherein the automatic speech recognition data comprises an automatic speech recognition output from the mobile device.
19. The computer-readable storage device of claim 15 , wherein the automatic speech recognition data comprises audio data gathered by the mobile device during automatic speech recognition with a user.
20. The computer-readable storage device of claim 15 , having additional instructions stored which result in operations comprising normalizing the automatic speech recognition data using frequency warping.