SYSTEM AND METHOD FOR RECOGNITION AND AUTOMATIC CORRECTION OF VOICE COMMANDS

• US 20150199965A1
• Filed: 01/16/2014
• Published: 07/16/2015
• Est. Priority Date: 01/16/2014
• Status: Abandoned Application

• Current Assignee: Lenny Insurance Limited (TATA Motors Limited)
• Original Assignee: CloudCar, Inc.
• Inventors: Leak, Bruce, Draganic, Zarko
• Application Number:
  US14/156,543
• Publication Number:
  US 20150199965A1
• 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 2015/221 Announcement of recognition results
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

A system and method for recognition and automatic correction of voice commands are disclosed. A particular embodiment includes: receiving a set of utterance data, the set of utterance data corresponding to a voice command spoken by a speaker; performing a first-level speech recognition analysis on the set of utterance data to produce a first result, the first-level speech recognition analysis including generating a confidence value associated with the first result, the first-level speech recognition analysis also including determining if the set of utterance data is a repeat utterance corresponding to a previously received set of utterance data; performing a second-level speech recognition analysis on the set of utterance data to produce a second result, if the confidence value associated with the first result does not meet or exceed a pre-configured threshold or if the set of utterance data is a repeat utterance; and matching the set of utterance data to a voice command and returning information indicative of the matching voice command without returning information that is the same as previously returned information if the set of utterance data is a repeat utterance.

Claims

1. A method comprising:

receiving a set of utterance data, the set of utterance data corresponding to a voice command spoken by a speaker;

performing a first-level speech recognition analysis on the set of utterance data to produce a first result, the first-level speech recognition analysis including generating a confidence value associated with the first result, the first-level speech recognition analysis also including determining if the set of utterance data is a repeat utterance corresponding to as previously received set of utterance data;

performing a second-level speech recognition analysis on the set of utterance data to produce a second result, if the confidence value associated with the first result does not meet or exceed a pre-configured threshold or if the set of utterance data is a repeat utterance; and

matching the set of utterance data to a voice command and returning information indicative of the matching voice command without returning information that is the same as previously returned information if the set of utterance data is a repeat utterance.

2. The method as claimed in claim 1 wherein the set of utterance data is received via a vehicle subsystem of a vehicle, the vehicle subsystem comprising an electronic in-vehicle infotainment (IVI) system installed in the vehicle, or a mobile device proximately located in or near the vehicle.

3. The method as claimed in claim 1 wherein producing the first result includes performing a search of a database to attempt to match the received set of utterance data to any of a plurality of sample voice commands stored in the database.

4. The method as claimed in claim 3 wherein the sample voice commands stored in the database include a typical or acceptable audio signature corresponding to a particular valid system command with an associated command code or command identifier.

5. The method as claimed in claim 3 wherein the confidence value corresponding to a likelihood that the received set of utterance data matches a corresponding sample voice command of the plurality of sample voice commands.

6. The method as claimed in claim 3 wherein any of the plurality of sample voice commands stored in the database can be dynamically updated or modified from a local or remote source.

7. The method as claimed in claim 1 wherein the second-level speech recognition analysis comprises a deeper level or different process of voice recognition analysis relative to the first-level speech recognition analysis.

8. The method as claimed in claim 1 wherein the second-level speech recognition analysis includes submitting the received set of utterance data to each of a plurality of utterance processing modules to analyze the received set of utterance data from a plurality of perspectives.

9. The method as claimed in claim 8 wherein the plurality of utterance processing modules include at least one from the group consisting of:

an utterance processing module configured to focus on specific characteristics of the particular speaker;

an utterance processing module configured to focus on a context in which the received set of utterance data is spoken; and

an utterance processing module configured to focus a context of the speaker.

10. The method as claimed in claim 1 further including using ancillary data obtained from a local or remote source to modify the operation of the first-level and the second-level speech recognition analysis.

11. The method as claimed in claim 1 further including presenting a plurality of result options to a user for selection if the confidence value associated with the first result does not meet or exceed a pre-configured threshold and the received set of utterance data is determined to not be a repeat utterance.

12. A system comprising:

a data processor;

a voice interface, in data communication with the data processor, to receive a set of utterance data; and

a voice command recognition and auto-correction module being configured to;

receive the set of utterance data via the voice interface, the set of utterance data corresponding to a voice command spoken by a speaker;

perform a first-level speech recognition analysis on the set of utterance data to produce a first result, the first-level speech recognition analysis being further configured to generate a confidence value associated with the first result, the first-level speech recognition analysis also including determining if the set of utterance data is a repeat utterance corresponding to a previously received set of utterance data;

perform a second-level speech recognition analysis on the set of utterance data to produce a second result, if the confidence value associated with the first result does not meet or exceed a pre-configured threshold or if the set of utterance data is a repeat utterance; and

match the set of utterance data to a voice command and return information indicative of the matching voice command without returning information that is the same as previously returned information if the set of utterance data is a repeat utterance.

13. The system as claimed in claim 12 wherein the voice interface is part of a vehicle subsystem comprising an electronic in-vehicle infotainment (IVI) system installed in a vehicle, or a mobile device proximately located in or near the vehicle.

14. The system as claimed in claim 12 being further configured to perform a search of a database to attempt to match the received set of utterance data to any of a plurality of sample voice commands stored in the database.

15. The system as claimed in claim 14 wherein the sample voice commands stored in the database include a typical or acceptable audio signature corresponding to a particular valid system command with an associated command code or command identifier.

16. The system as claimed in claim 14 wherein the confidence value corresponding to a likelihood that the received set of utterance data matches a corresponding sample voice command of the plurality of sample voice commands.

17. The system as claimed in claim 14 wherein any of the plurality of sample voice commands stored in the database can be dynamically updated or modified from a local or remote source.

18. The system as claimed in claim 12 wherein the second-level speech recognition analysis being further configured to submit the received set of utterance data to each of a plurality of utterance processing modules to analyze the received set of utterance data from a plurality of perspectives, the plurality of utterance processing modules including at least one from the group consisting of:

an utterance processing module configured to focus on specific characteristics of the particular speaker;

an utterance processing module configured to focus on a context in which the received set of utterance data is spoken; and

an utterance processing module configured to focus a context of the speaker.

19. The system as claimed in claim 12 being further configured to use ancillary data obtained from a local or remote source to modify the operation of the first-level and the second-level speech recognition analysis.

20. The system as claimed in claim 12 being further configured to present a plurality of result options to a user for selection if the confidence value associated with the first result does not meet or exceed a pre-configured threshold and the received set of utterance data is determined to not be a repeat utterance.

21. A non-transitory machine-useable storage medium embodying instructions which, when executed by a machine, cause the machine to:

receive a set of utterance data, the set of utterance data corresponding to a voice command spoken by a speaker;

perform a first-level speech recognition analysis on the set of utterance data to produce a first result, the first-level speech recognition analysis being further configured to generate a confidence value associated with the first result, the first-level speech recognition analysis also including determining if the set of utterance data is a repeat utterance corresponding to a previously received set of utterance data;

perform a second-level speech recognition analysis on the set of utterance data to produce a second result, if the confidence value associated with the first result does not meet or exceed a pre-configured threshold or if the set of utterance data is a repeat utterance; and

match the set of utterance data to a voice command and return information indicative of the matching voice command without returning information that is the same as previously returned information if the set of utterance data is a repeat utterance.

22. The machine-useable storage medium as claimed in claim 21 wherein the set of utterance data is received via a vehicle subsystem of a vehicle, the vehicle subsystem comprising an electronic in-vehicle infotainment (IVI) system installed in the vehicle, or a mobile device proximately located in or near the vehicle.