Management of multilingual nametags for embedded speech recognition

• US 20060135215A1
• Filed: 12/16/2004
• Published: 06/22/2006
• Est. Priority Date: 12/16/2004
• Status: Active Grant

• Current Assignee: General Motors LLC (General Motors Company)
• Original Assignee: General Motors Corporation (Motors Liquidation Co. GUC Trust)
• Inventors: Correia, John J., Chengalvarayan, Rathinavelu
• Granted Patent: US 7,596,370 B2
• Time in Patent Office: Days
• US Class Current: 455/569.200
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: H04M 1/271 controlled by voice recognition
• CPC Class Codes: H04M 1/2757 by data transmission, e.g. downloading
• CPC Class Codes: H04M 1/6075 adapted for handsfree use in a vehicle H04M1/6058 takes precedence; arrangements for holding telephones in a vehicle B60R11/0241
• CPC Class Codes: H04M 1/72445 for supporting Internet browser applications

Abstract

A method for managing user nametags for a vehicle communications system, the method including receiving a nametag transfer request at a call center from a source, determining a target vehicle associated with the source based on the request and modifying a source nametag data file based on an acoustic profile of the target vehicle, wherein the source nametag data file is one of an audio file and a text file.

Claims

1. A method of managing user nametags for a vehicle communications system, the method comprising:

receiving a nametag transfer request at a call center from a source;

determining a target vehicle associated with the source based on the request; and

modifying a source nametag data file based on an acoustic profile of the target vehicle,

wherein the source nametag data file is one of an audio file and a text file.

2. The method of claim 1, further comprising:

sorting the source nametag data file, wherein the source nametag data file is sorted based on one of unilingual phonemes for one language, multilingual phonemes having characteristics of more than one language, and multilingual phonemes having universal characteristics.

3. The method of claim 2, wherein sorting the source nametag data file comprises:

retrieving the audio file associated with a respective nametag in the source nametag data file;

activating an automated speech recognition engine for at least one language to generate a phoneme set for the nametag in the at least one language;

determining if the generated phoneme set is misrecognized;

updating a nametag table with the generated phoneme set; and

updating the nametag table with identifiers.

4. The method of claim 3, further comprising:

introducing variance into the audio file associated with the nametag based on a determination of a misrecognized phoneme set.

5. The method of claim 1, wherein the source is a source vehicle, the method further comprising:

storing source vehicle data in a database in the call center, wherein the source vehicle data includes a source identification, an acoustic profile of the source vehicle, and a source vehicle speech recognition identifier.

6. The method of claim 5, wherein the source vehicle data further includes the source nametag data file.

7. The method of claim 6, wherein the source vehicle data are received from a telematics unit of the source vehicle.

8. The method of claim 5, wherein the source vehicle data are received from a telematics unit of the source vehicle.

9. The method of claim 5, wherein the source vehicle data are received from an Internet interface wherein the interface is initiated by one of a user and a vehicle dealership.

10. The method of claim 1, wherein the source is a handset and further comprising:

storing source data in a database in the call center wherein the source data includes a source identification, and a source speech recognition identifier.

11. The method of claim 1, further comprising:

storing target vehicle data in a database in the call center wherein the target vehicle data includes a target vehicle identification, the acoustic profile of the target vehicle and a target vehicle speech recognition identifier.

12. The method of claim 1, further comprising:

transferring the modified source nametag data file to the determined target vehicle from the call center.

13. The method of claim 1, wherein receiving a nametag transfer request at a call center from a source comprises:

receiving a selection of the source nametag data file to be transferred from the source to the target vehicle;

receiving a source identification; and

receiving a target vehicle identification, and

wherein determining a target vehicle associated with the source based on the request comprises;

matching the target vehicle identification with a target vehicle data in a database in the call center;

retrieving an acoustic profile of the target vehicle and a target vehicle speech recognition identifier based on the matching.

14. The method of claim 13, wherein modifying a source nametag data file based on an acoustic profile of the target vehicle comprises:

matching the source identification with a source vehicle data in a database in the call center;

retrieving at least one of an acoustic profile of the source vehicle, a source vehicle speech recognition identifier, and the source nametag data file from the source vehicle data;

determining if the acoustic profile of the target vehicle matches the acoustic profile of the source vehicle;

removing acoustic characteristics of the source vehicle from the received selected source nametag data file based on the acoustic profile determinations;

adding acoustic characteristics of the target vehicle to the modified source nametag data file;

determining if the target vehicle speech recognition identifier matches the source vehicle speech recognition identifier; and

modifying the selected source nametag data file of the source vehicle based upon the determination.

15. The method of claim 13, wherein modifying a source nametag data file based on an acoustic profile of the target vehicle comprises:

matching the source identification with a source data in a database in the call center;

retrieving at least one of a source speech recognition identifier and the source nametag data file from the source data, wherein the source nametag data file is an audio file; and

adding acoustic characteristics of the target vehicle to the selected source nametag data file.

16. The method of claim 13, wherein modifying a source nametag data file based on an acoustic profile of the target vehicle comprises:

matching the source identification with a source data in a database in the call center;

retrieving at least one of a source speech recognition identifier and the source nametag data file from the source data, wherein the source nametag data file is a text file;

applying a text-to-speech algorithm to the received selected source nametag data file to generate an audio source nametag data file, wherein the generated source nametag data file is a synthetic-audio file; and

adding acoustic characteristics of the target vehicle to the generated source nametag data file.

17. The method of claim 16, further comprising:

receiving the modified source nametag data file at a telematics unit in the target vehicle, wherein the modified source nametag data file is a synthetic-audio file;

storing the modified source nametag data file in a memory in the telematics unit, receiving a voice command from a user at the telematics unit, wherein the voice command includes a spoken nametag;

retrieving the modified source nametag data file from the memory;

matching at least a portion of the stored modified source nametag data file with the spoken nametag;

replacing the matched portion of the modified source nametag data file with the spoken nametag responsive to the matching to form a revised source nametag data file; and

storing the revised source nametag data file in the memory.

18. A system for managing user nametags for a vehicle communications system, the system comprising:

means for receiving a nametag transfer request at a call center from a source;

means for determining a target vehicle associated with the source based on the request; and

means for modifying a source nametag data file based on an acoustic profile of the target vehicle, wherein the source nametag data file is one of an audio file and a text file.

19. A computer readable medium storing a computer program comprising:

computer readable code for receiving a nametag transfer request at a call center from a source;

computer readable code for determining a target vehicle associated with the source based on the request; and

computer readable code for modifying a source nametag data file based on an acoustic profile of the target vehicle, wherein the source nametag data file is one of an audio file and a text file.

20. The medium of claim 19, further comprising:

computer readable code for sorting the source nametag data file, wherein the source nametag data file is sorted into a table based on one of unilingual phonemes for one language, multilingual phonemes having characteristics of more than one language, and multilingual phonemes having universal characteristics.

21. The medium of claim 19, wherein the source is a source vehicle, the medium further comprising:

computer readable code for storing source vehicle data in a database in the call center, wherein the source vehicle data includes a source identification, an acoustic profile of the source vehicle, and a source vehicle speech recognition identifier.

22. The medium of claim 19, wherein the computer readable code for receiving a nametag transfer request at a call center from a source comprises:

computer readable code for receiving a selection of the source nametag data file to be transferred from the source to the target vehicle;

computer readable code for receiving a source identification; and

computer readable code for receiving a target vehicle identification; and

wherein the computer readable code for determining a target vehicle associated with the source based on the request comprises;

computer readable code for matching the target vehicle identification with a target vehicle data in a database in the call center; and

computer readable code for retrieving an acoustic profile of the target vehicle and a target speech recognition identifier based on the matching.

23. The medium of claim 22, wherein the computer readable code for modifying a source nametag data file based on an acoustic profile of the target vehicle comprises:

computer readable code for matching the source identification with a source vehicle data in a database in the call center;

computer readable code for retrieving at least one of an acoustic profile of the source vehicle, a source vehicle speech recognition identifier, and the source nametag data file from the source vehicle data;

computer readable code for determining if the acoustic profile of the target vehicle matches the acoustic profile of the source vehicle;

computer readable code for removing the acoustic characteristics of the source vehicle from the received selected source nametag data file based on the acoustic profile determinations;

computer readable code for adding the acoustic characteristics of the target vehicle to the modified source nametag data file;

computer readable code for determining if the target vehicle speech recognition identifier matches the source vehicle speech recognition identifier; and

computer readable code for modifying the selected source nametag data file of the source vehicle based upon the determination.

24. The medium of claim 23, wherein the computer readable code for modifying a source nametag data file based on an acoustic profile of the target vehicle comprises:

computer readable code for matching the source identification with a source data in a database in the call center;

computer readable code for retrieving at least one of a source speech recognition identifier and the source nametag data file from the source data, wherein the source nametag data file is an audio file; and

computer readable code for adding acoustic characteristics of the target vehicle to the selected source nametag data file.

25. The medium of claim 23, wherein the computer readable code for modifying a source nametag data file based on an acoustic profile of the target vehicle comprises:

computer readable code for matching the source identification with a source data in a database in the call center;

computer readable code for retrieving at least one of a source speech recognition identifier and the source nametag data file from the source data, wherein the source nametag data file is a text file;

computer readable code for applying a text-to-speech algorithm to the received selected source nametag data file to generate audio source nametag data file, wherein the generated source nametag data file is a synthetic-audio file; and

computer readable code for adding acoustic characteristics of the target vehicle to the generated source nametag data file.

26. The medium of claim 23, further comprising:

computer readable code for receiving the modified source nametag data file at a telematics unit in the target vehicle, wherein the modified source nametag data file is a synthetic-audio file;

computer readable code for storing the modified source nametag data file in a memory in the telematics unit;

computer readable code for receiving a voice command from a user at the telematics unit, wherein the voice command includes a spoken nametag;

computer readable code for retrieving the modified source nametag data file from the memory;

computer readable code for matching at least a portion of the stored modified source nametag data file with the spoken nametag; and

computer readable code for replacing the matched portion of the modified source nametag data file with the spoken nametag responsive to the matching to form a revised source nametag data file;

computer readable code for storing the revised source nametag data file in the memory.