RECOGNITION MODULE AFFINITY

• US 20190057690A1
• Filed: 11/08/2017
• Published: 02/21/2019
• Est. Priority Date: 08/18/2017
• Status: Active Grant

• Current Assignee: Blackberry Limited
• Original Assignee: 2236008 Ontario Inc. (Blackberry Limited)
• Inventors: Fry, Darrin Kenneth John
• Granted Patent: US 10,497,370 B2
• Time in Patent Office: Days
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• 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 2015/223 Execution procedure of a spoken command

Abstract

A system and method to receive a spoken utterance and convert the spoken utterance into a recognized speech results through multiple automatic speech recognition modules. Multiple conversation modules interpret the recognized speech results. The system and method assign an affinity status to one or more of the multiple automatic speech recognition modules. An affinity status restricts the conversion of a subsequent spoken utterance to a selected automatic speech recognition module or modules.

Claims

1. An automatic speech recognition system, comprising:

a processor configured to receive a spoken utterance and convert the spoken utterance into a plurality of recognized speech results through a plurality of automatic speech recognition modules; and

the processor is further configured to interpret each of the plurality of recognized speech results rendered by each of the plurality of automatic speech recognition modules through a plurality of natural language processing modules;

the processor is further configured to process each of the plurality of recognized speech results through a plurality of conversation modules;

wherein the processor is further configured to assign an affinity status to one or more of the plurality of automatic speech recognition modules that restrict a conversion of a subsequent spoken utterance to the one or more automatic speech recognition modules assigned the affinity status.

2. The system of claim 1, wherein the processor assigns the affinity status in response to the plurality of recognized speech results.

3. The system of claim 1, wherein the processor assigns the affinity status prior to the conversion of the spoken utterance into a plurality of recognized speech results.

4. The system of claim 2, wherein the processor assigns the affinity status from a configuration file.

5. The system of claim 1, wherein the processor assigns the affinity status in response to a user request.

6. The system of claim 1, wherein the affinity status is determined from a plurality of rating values generated by the plurality of conversation modules.

7. The system of claim 1, wherein the plurality of automatic speech recognition modules are remote from the plurality of conversation modules.

8. The system of claim 1, wherein the extensible automatic speech recognition system comprises a vehicle.

9. A method that convert spoken commands to text and interpret a recognized speech comprising:

receiving receive a spoken utterance and convert the spoken utterance into a plurality of recognized speech results through a plurality of automatic speech recognition modules; and

interpreting each of the plurality of recognized speech results rendered by each of the plurality of automatic speech recognition modules through a plurality of natural language processing modules;

assigning an affinity status to one or more of the plurality of automatic speech recognition modules that restrict a conversion of a subsequent spoken utterance to the one or more automatic speech recognition modules assigned the affinity status.

10. The method of claim 9, wherein the affinity status is assigned in response to the plurality of recognized speech results.

11. The method of claim 9, wherein the affinity status is assigned prior the conversion of the spoken utterance into a plurality of recognized speech results.

12. The method of claim 11, wherein the affinity status is rendered from a configuration file loaded when ASR begins operation.

13. The method of claim 9, wherein the affinity status is assigned in response to a user'"'"'s verbal request.

14. The method of claim 9, wherein the affinity status is determined from a plurality of rating values generated by the plurality of conversation modules.

15. The method of claim 9, wherein the plurality automatic speech recognition modules are remote from the plurality of conversation modules.

16. The method of claim 9, wherein the method is executed by a vehicle.

17. A non-transitory machine-readable medium encoded with machine-executable instructions, wherein execution of the machine-executable instructions is for:

receiving receive a spoken utterance and convert the spoken utterance into a plurality of recognized speech results through a plurality of automatic speech recognition modules; and

interpreting each of the plurality of recognized speech results rendered by each of the plurality of automatic speech recognition modules through a plurality of natural language processing modules;

assigning an affinity status to one or more of the plurality of automatic speech recognition modules that restrict a conversion of a subsequent spoken utterance to the one or more automatic speech recognition modules assigned the affinity status.

18. The non-transitory machine-readable medium of claim 17, wherein the affinity status is assigned in response to the plurality of recognized speech results.

19. The non-transitory machine-readable medium of claim 17, wherein the affinity status is assigned prior to the conversion of the spoken utterance into a plurality of recognized speech results.

20. The non-transitory machine-readable medium of claim 17, wherein the affinity status is rendered from a configuration file.