Disambiguation of vehicle speech commands

• US 10,319,371 B2
• Filed: 05/04/2016
• Issued: 06/11/2019
• Est. Priority Date: 05/04/2016
• 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, Xufang, Talwar, Gaurav
• Primary Examiner(s): Opsasnick, Michael N
• Application Number:
  US15/146,256
• Publication Number:
  US 20170323635A1
• Time in Patent Office: 1,133 Days
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• 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 2015/085 Methods for reducing search complexity, pruning
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 25/54 for retrieval

Abstract

A system and method of recognizing speech in a vehicle. The method includes receiving a voice command at the vehicle via a microphone in the vehicle, and obtaining a recognition result from speech recognition performed on the received voice command. The recognition result may represent the voice command and be indicative of any of two or more available vehicle commands. The method may further include selecting one of the two or more available vehicle commands based on a secondary characteristic and an attribute of the selected one of the vehicle commands. The system may be implemented as vehicle electronics that include a microphone located within the vehicle and configured to receive a voice command from a user located within the vehicle, and a controller in communication with the microphone. The controller may be configured to perform speech recognition on the voice command and obtain a disambiguated recognition result.

Claims

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

(a) receiving a voice command at the vehicle via a microphone in the vehicle, and converting the voice command to digital data using a processor installed to the vehicle;

(b) obtaining a recognition result from speech recognition performed on the digital data of the received voice command, wherein the recognition result represents the voice command and is indicative of (1) one of two or more available vehicle functions and (2) an operand of the vehicle function having two or more associated vehicle commands;

(c) selecting one of the two or more associated vehicle commands associated with the operand identified in the recognition result by associating a secondary characteristic with an attribute of the selected one of the vehicle commands, wherein the attribute of the selected one of the vehicle commands and the secondary characteristic are not present in the voice command, and wherein at least one of the selected attribute or the secondary characteristic is obtained independent of the user-provided voice command; and

(d) presenting the selected vehicle command to a user.

2. The method of claim 1, wherein the vehicle function is to initiate a phone call.

3. The method of claim 1, wherein the operand includes a nametag.

4. The method of claim 3, wherein the nametag indicates a database field where an identification of the selected one of the two or more associated vehicle commands is stored.

5. The method of claim 1, wherein the secondary characteristic includes a time the voice command is received at the vehicle.

6. The method of claim 5, wherein selecting the one of the two or more associated vehicle commands includes matching the time to an expected availability period associated with the attribute of the selected one of the vehicle commands.

7. The method of claim 1, wherein the secondary characteristic includes an affiliation of the user with an operand included in the voice command, a proximity of the vehicle to a location identified by the operand, or both.

8. The method of claim 1, further comprising performing speech recognition on the voice command at the vehicle.

9. The method of claim 1, further comprising:

carrying out disambiguation of the recognition result at the vehicle by determining, based on the current date and/or time of day, which one of the two or more associated vehicle commands is an intended command wherein the disambiguated recognition result is presented to the user.

10. The method of claim 1, wherein selecting the one of the two or more associated vehicle commands includes determining a relative likelihood for each of the two or more associated vehicle commands corresponding to the voice command based upon at least the secondary characteristic.

11. The method of claim 1, wherein the recognition result corresponds to two or more different operands, and further comprising:

determining which one of the two or more different operands comprises an intended target and generating a revised recognition result comprising the voice menu command and the intended target wherein the revised recognition result is presented to the user.

12. The method of claim 11, wherein the vehicle function is to initiate a phone call and the operands comprise different nametags, each nametag representing a different phone number.

13. A method of recognizing speech in a vehicle, comprising the steps of:

(a) receiving a voice command at the vehicle from a user via a microphone in the vehicle, and converting the voice command to digital data using a processor installed to the vehicle;

(b) performing speech recognition on the digital data of the voice command at the vehicle;

(c) obtaining a recognition result from the speech recognition that represents the voice command, wherein the recognition result corresponds to (1) one of two or more available vehicle functions and (2) an operand of the vehicle function having two or more associated vehicle commands;

(d) carrying out disambiguation of the recognition result at the vehicle to determine which one of the two or more associated vehicle commands associated with the operand identified in the recognition result is an intended command by associating the current date and/or time of day with an attribute of the intended command, wherein the attribute of the selected one of the vehicle commands and the current date and/or time of day are not present in the voice command, and wherein at least one of the selected attribute or the secondary characteristic is obtained independent of the user-provided voice command; and

(e) presenting the disambiguated recognition result to the user.

14. The method of claim 13, wherein the recognition result corresponds to two or more different nametags associated with the operand, and wherein step (d) further comprises determining which one of the two or more different nametags is associated with the intended command and generating a revised recognition result comprising the voice menu command and the intended command, and wherein step (e) comprises presenting the revised recognition result to the user.

15. The method of claim 14, wherein the vehicle function comprises initiating a phone call and each nametag represents a different phone number.

16. A vehicle including vehicle electronics installed in the vehicle, the vehicle electronics comprising:

a microphone located within the vehicle and configured to receive a voice command from a user located within the vehicle; and

a controller in communication with the microphone, the controller configured to perform speech recognition on digital data representing the voice command and obtain a recognition result from the speech recognition that represents the voice command, wherein the recognition result corresponds to (1) one of two or more available vehicle functions and (2) an operand of the vehicle function having two or more associated vehicle commands, wherein the controller is configured to determine which one of two or more associated vehicle commands associated with the operand identified in the recognition result is an intended command by associating the current date and/or time of day with an attribute of the intended command, wherein the attribute of the selected one of the vehicle commands and the current date and/or time of day are not present in the voice command, and wherein at least one of the selected attribute or the current date and/or time of day is obtained independent of the user-provided voice command, wherein the controller presents the intended command to the user.