Dynamically adding or removing functionality to speech recognition systems

• US 10,083,685 B2
• Filed: 10/13/2015
• Issued: 09/25/2018
• Est. Priority Date: 10/13/2015
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: Zhao, Xu Fang, Chowdhury, Md Foezur Rahman, Talwar, Gaurav
• Primary Examiner(s): Thomas-Homescu, Anne L
• Application Number:
  US14/881,334
• Publication Number:
  US 20170103749A1
• Time in Patent Office: 1,078 Days
• CPC Class Codes: G10L 15/07 to the speaker
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/28 Constructional details of speech recognition systems
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

A system and method of changing features of an existing automatic speech recognition (ASR) system includes: monitoring speech received from a vehicle occupant for one or more keywords identifying a feature to remove from or add to the ASR system; detecting the keywords in the monitored speech; and adding the identified feature to or removing the identified feature from from the ASR system.

Claims

1. A method of changing vehicle features of an existing automatic speech recognition (ASR) system installed in a vehicle that includes a processor, wherein the existing ASR system is configured to provide select vehicle features that are initiated by vocalized commands from a vehicle occupant, the method comprising the steps of:

(a) applying a secondary speech recognition module to the existing ASR system, wherein the secondary speech recognition module is configured to monitor speech received via a microphone from the vehicle occupant to identify one or more keywords that relate to at least one of the select vehicle features provided by the existing ASR system that is unavailable at the vehicle;

(b) detecting the one or more keywords in the monitored speech that relate to an unavailable vehicle feature using the secondary speech recognition module executed by the processor; and

(c) removing the unavailable vehicle feature from the existing ASR system based on step (b) so that the existing ASR system provides a defined number of features that conform to or match the vehicle features available at the vehicle, wherein removing the unavailable vehicle feature modifies the configuration of the existing ASR system.

2. The method of claim 1, wherein step (c) is carried out at a pre-processor software module or a post-processor software module of the existing ASR system.

3. The method of claim 1, further comprising the step of storing a plurality of keywords each with a vehicle feature in a database.

4. The method of claim 1, wherein the unavailable vehicle feature comprises a navigation feature, a radio feature, a telephone feature, or a multimedia feature.

5. The method of claim 1, further comprising the step of identifying one or more vehicle features enabled by the existing ASR system by inputting speech segments into the existing ASR system that include keywords associated with the vehicle features.

6. A method of changing vehicle features of an existing automatic speech recognition (ASR) system installed in a vehicle that includes a processor, wherein the existing ASR system is configured to provide select vehicle features that are initiated by vocalized commands from a vehicle occupant, the method, comprising the steps of:

(a) applying a secondary speech recognition module to the existing ASR system, wherein the secondary speech recognition module is configured to monitor speech received from the vehicle occupant via a microphone to identify one or more keywords that relate to a vehicle feature that is not one of the select vehicle features configured by the existing ASR system;

(b) detecting the one or more keywords in the monitored speech using the secondary speech recognition module executed by the processor;

(c) adding the vehicle feature to the existing ASR system based on step (b) so that the ASR system provides a defined number of vehicle features that conform to or match the vehicle features available at the vehicle; and

(d) generating a speech recognition output at the secondary speech recognition module that corresponds to the added vehicle feature, wherein adding the vehicle feature modifies the configuration of the existing ASR system.

7. The method of claim 6, further comprising the step of routing the speech recognition output to a post-processor software module.

8. The method of claim 6, further comprising the step of storing a plurality of keywords each with a vehicle feature in a database.

9. The method of claim 6, further comprising the step of receiving the vehicle feature at a vehicle telematics unit via wireless communications.

10. The method of claim 6, wherein the added vehicle feature comprises a navigation feature, a radio feature, a telephone feature, or a multimedia feature.

11. The method of claim 6, further comprising the step of identifying one or more vehicle features enabled by the ASR system by inputting speech segments into the ASR system that include keywords associated with the vehicle features.

12. A method of changing vehicle features of an existing automatic speech recognition (ASR) system that includes a processor, comprising the steps of:

(a) receiving, at a vehicle, a vehicle feature to add to or remove from the existing ASR system;

(b) establishing, at the vehicle, a database of keywords that identify the vehicle feature;

(c) applying a secondary speech recognition module to the existing ASR system, wherein the secondary speech recognition module is configured to monitor speech received from a vehicle occupant via a microphone for one or more of the keywords;

(d) detecting one or more keywords in the monitored speech using the secondary speech recognition module executed by the processor; and

(e) adding or removing the vehicle feature from the existing ASR system at a pre-processor software module or a post-processor software module based on step (d) so that the existing ASR system provides a defined number of vehicle features that conform to or match the features available at a vehicle, wherein adding or removing the vehicle feature modifies the configuration of the existing ASR system.

13. The method of claim 12, wherein step (c) is carried out at the pre-processor software module of the ASR system.

14. The method of claim 12, further comprising the step of receiving the vehicle feature at a vehicle from a vehicle manufacturer before the vehicle is produced.

15. The method of claim 12, further comprising the step of receiving the vehicle feature at a vehicle telematics unit via wireless communications.

16. The method of claim 12, wherein the vehicle feature comprises a navigation feature, a radio feature, a telephone feature, or a multimedia feature.

17. The method of claim 12, further comprising the step of identifying one or more vehicle features enabled by the ASR system by inputting speech segments into the ASR system that include keywords associated with the vehicle features.