Recognizing address and point of interest speech received at a vehicle

• US 10,006,777 B2
• Filed: 10/02/2015
• Issued: 06/26/2018
• Est. Priority Date: 10/02/2015
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: Talwar, Gaurav, Zhao, Xufang
• Primary Examiner(s): BAKER, MATTHEW H
• Application Number:
  US14/873,305
• Publication Number:
  US 20170097242A1
• Time in Patent Office: 998 Days
• CPC Class Codes: G01C 21/3608 using speech input, e.g. using speech recognition
• CPC Class Codes: G01C 21/3679 Retrieval, searching and output of POI information, e.g. hotels, restaurants, shops, filling stations, parking facilities G01C21/3611 takes precedence
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

A system and method of recognizing speech received at a vehicle includes: receiving speech from a vehicle occupant via a microphone; determining whether the speech relates to a point of interest (POI) or an address without receiving a POI command prompt or an address command prompt in the speech from the vehicle occupant; selecting a POI function or an address function based on the determination; and processing the received speech to identify a POI or an address.

Claims

1. A method of recognizing speech received at a vehicle, the steps comprising:

(a) receiving speech from a vehicle occupant via a microphone;

(b) determining, using an automatic speech recognition (ASR) system at the vehicle, whether the received speech relates to a point of interest (POI) or an address without receiving a POI command prompt or an address command prompt in the speech received from the vehicle occupant;

(c) selecting a POI processing function or an address processing function based on step (b); and

(d) configuring one or more models of the ASR system such that the received speech is processed with a bias to a POI or an address based on the processing function selected in step (c)

(e) processing the received speech using the processing function selected in step (c) to identify a POI or an address.

2. The method of claim 1, further comprising the step of determining a confidence value for the processed speech.

3. The method of claim 2, further comprising the step of changing the selected POI processing function or address processing function based on the confidence value.

4. The method of claim 2, further comprising the step of determining a second confidence value for speech processed using a different function.

5. The method of claim 4, further comprising the steps of comparing the confidence value and the second confidence value and selecting a speech hypothesis based on the comparison.

6. The method of claim 1, wherein step (b) further comprises the step of determining a temporal length of the received speech.

7. The method of claim 1, wherein the POI processing function includes a word model stored with a list of commonly-used POIs.

8. The method of claim 1, wherein the address processing function comprises listening for a number value preceding words in the received speech.

9. A method of recognizing speech received at a vehicle, the steps comprising:

(a) receiving from a vehicle occupant a selection of a default processing function to be used by an automatic speech recognition (ASR) system at the vehicle to initially process speech received by the vehicle occupant;

(b) receiving speech from the vehicle occupant via a microphone;

(c) determining, using the ASR system at the vehicle, whether the speech received in step (b) relates to a point of interest (POI) or an address without receiving a POI command prompt or an address command prompt in the received speech from the vehicle occupant;

(d) selecting a POI processing function or an address processing function based on step (a);

(e) configuring one or more models of the ASR system such that the received speech is processed with a bias to a POI or an address based on the processing function selected in step (d); and

(f) in processing the received speech using the processing function selected in step to identify a POI or an address.

10. The method of claim 9, further comprising the steps of determining a confidence value for the processed speech and changing the selected processing function based on the confidence value.

11. The method of claim 10, further comprising the step of determining a second confidence value for speech processed using a different function.

12. The method of claim 11, further comprising the steps of comparing the confidence value and the second confidence value and selecting a speech hypothesis based on the comparison.

13. The method of claim 9, wherein step (c) further comprises the step of determining a temporal length of the received speech.

14. The method of claim 9, wherein the POI processing function includes a word model stored with a list of commonly-used POIs.

15. The method of claim 9, wherein the address processing function comprises listening for a number value preceding words in the received speech.

16. A method of recognizing speech received at a vehicle, the steps comprising:

(a) establishing a plurality of commonly-used point of interest (POI) words using an automatic speech recognition (ASR) system at the vehicle;

(b) receiving speech from the vehicle occupant via a microphone;

(c) determining, using the ASR system at the vehicle, whether the speech includes one or more of the commonly-used POI words;

(d) selecting a POI processing function over an address processing function based on the determination in step (c); and

(e) configuring one or more models of the ASR system such that the received speech is processed with a bias to a POI based on the selection of the POI processing function in step (d).

17. The method of claim 16, further comprising the steps of determining a confidence value for processed speech and changing the selected POI processing function based on the confidence value.

18. The method of claim 17, further comprising the step of determining a second confidence value for speech processed using the address processing function.

19. The method of claim 16, further comprising the steps of comparing the confidence value and the second confidence value and selecting a speech hypothesis based on the comparison.

20. The method of claim 16, wherein the POI processing function includes a word model stored with a list of commonly-used POIs.