CONTROLLING SPEECH RECOGNITION SYSTEMS BASED ON RADIO STATION AVAILABILITY

• US 20160307562A1
• Filed: 04/14/2015
• Published: 10/20/2016
• Est. Priority Date: 04/14/2015
• Status: Abandoned Application

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: TALWAR, Gaurav, HUK, Joseph M. Jr., ZHAO, Xufang
• Application Number:
  US14/686,053
• Publication Number:
  US 20160307562A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A system and method of controlling an automatic speech recognition (ASR) system includes: determining the location of a vehicle; identifying terrestrial radio stations in a database that are within a range of the vehicle location based on geographic locations of the terrestrial radio stations stored in the database; and altering the content of a speech grammar used by the ASR system to process speech received in the vehicle that requests a terrestrial radio station.

Claims

1. A method of controlling an automatic speech recognition (ASR) system, comprising the steps of:

(a) determining the location of a vehicle;

(b) identifying terrestrial radio stations in a database that are within a range of the vehicle location based on geographic locations of the terrestrial radio stations stored in the database; and

(c) altering the content of a speech grammar used by the ASR system to process speech received in the vehicle that requests a terrestrial radio station.

2. The method of claim 1, further comprising the step of determining the power values of identified terrestrial radio stations.

3. The method of claim 1, wherein step (c) further comprises limiting the content of the speech grammar based on the names of the identified terrestrial radio stations.

4. The method of claim 1, wherein step (c) further comprises assigning a probability value to each name of the identified terrestrial radio stations.

5. The method of claim 1, further comprising the step of dividing the range into a plurality of bands that are classified according to distance from the vehicle.

6. The method of claim 5, further comprising the step of assigning a probability value to each band.

7. The method of claim 5, further comprising the step of limiting the number of identified terrestrial radio stations in at least one of the bands according to a broadcast power level.

8. The method of claim 1, wherein the database is located at the vehicle.

9. A method of controlling an automatic speech recognition (ASR) system, comprising the steps of:

(a) determining the location of a vehicle;

(b) defining an area surrounding the vehicle using a predetermined distance from the vehicle;

(c) finding in a database one or more terrestrial radio stations located within the defined area;

(d) identifying the names of the identified terrestrial radio station(s) to a speech grammar; and

(e) processing received speech in the vehicle using the speech grammar.

10. The method of claim 9, further comprising the step of determining the power values of the terrestrial radio stations found in the database.

11. The method of claim 9, further comprising the step of limiting the content of the speech grammar based on the names of the identified terrestrial radio stations.

12. The method of claim 9, further comprising the step of assigning a probability value to each name of the identified terrestrial radio stations.

13. The method of claim 9, further comprising the step of dividing the area into a plurality of bands that are classified according to distance from the vehicle.

14. The method of claim 13, further comprising the step of assigning a probability value to each band.

15. The method of claim 13, further comprising the step of limiting the number of identified terrestrial radio stations in at least one of the bands according to a broadcast power level.

16. A method of controlling an automatic speech recognition (ASR) system, comprising the steps of:

(a) determining the location of a vehicle;

(b) defining an area surrounding the vehicle using a predetermined distance from the vehicle;

(c) finding in a database one or more terrestrial radio stations located within the defined area;

(d) assigning a probability value to each found terrestrial radio station based on location;

(e) identifying the names of the found terrestrial radio station(s) and assigned probability values to a speech grammar; and

(f) processing received speech in the vehicle using the speech grammar.

17. The method of claim 16, further comprising the step of identifying terrestrial radio stations that are within the defined area based on radio station power values that are stored in the database.

18. The method of claim 16, further comprising the step of dividing the area into a plurality of bands that are classified according to distance from the vehicle.

19. The method of claim 18, further comprising the step of assigning a probability value to each band.

20. The method of claim 18, further comprising the step of limiting the number of identified terrestrial radio stations in at least one of the bands according to a broadcast power level.