Gesture-based cues for an automatic speech recognition system

• US 9,881,609 B2
• Filed: 04/18/2014
• Issued: 01/30/2018
• Est. Priority Date: 04/18/2014
• Status: Active Grant

• Current Assignee: General Motors LLC (General Motors Company)
• Original Assignee: General Motors LLC (General Motors Company)
• Inventors: Talwar, Gaurav, Zhao, Xufang
• Primary Examiner(s): Shah, Paras D
• Assistant Examiner(s): Nguyen, Timothy
• Application Number:
  US14/256,194
• Publication Number:
  US 20150302851A1
• Time in Patent Office: 1,383 Days
• Field of Search: 704254
• CPC Class Codes: G10L 15/24 Speech recognition using non-acoustical features
• CPC Class Codes: G10L 2015/226 using non-speech characteristics

Abstract

A method of recognizing continuous digits uttered by a speaker using an automatic speech recognition (ASR) system includes receiving continuous digits via a microphone as speech from a user; detecting that recognition of one or more of the continuous digits falls below a predetermined confidence threshold; prompting the user to identify the continuous digits using a body gesture; detecting the body gesture made by the user; and identifying one or more of the continuous digits based on the body gesture.

Claims

1. A method of recognizing continuous digits using an automatic speech recognition (ASR) system, comprising the steps of:

(a) receiving continuous digits via a microphone as speech from a user;

(b) converting, using the ASR system, the received speech in step (a) into electrical signals;

(c) detecting, using the ASR system, that recognition of one or more of the continuous digits falls below a predetermined confidence threshold;

(d) prompting the user to identify the continuous digits using a body gesture in response to step (c);

(e) detecting the body gesture made by the user;

(f) identifying, using the ASR system, one or more of the continuous digits based on the body gesture, wherein identifying includes detecting at least one of the quantity and identity of the continuous digits using the body gesture; and

(g) adjusting an acoustical reference pattern associated with the continuous digits identified in step (f) using the ASR system.

2. The method of claim 1, further comprising the step of receiving speech in a tonal language.

3. The method of claim 1, further comprising the step of detecting the body gesture using a display or a camera.

4. The method of claim 1, further comprising the step of storing the identified continuous digits with the received speech.

5. The method of claim 1, wherein the speech is received as part of dialing a telephone number.

6. The method of claim 1, wherein the speech is received as part of changing a radio station or providing navigation services.

7. The method of claim 1, further comprising the step of assigning a body gesture to speech associated with one or more continuous digits.

8. A method of recognizing continuous digits using an automatic speech recognition (ASR) system, comprising the steps of:

(a) receiving continuous digits via a vehicle microphone as speech from a user;

(b) converting, using the ASR system, the received speech in step (a) into electrical signals;

(c) detecting, using the ASR system, that recognition of one or more of the continuous digits falls below a predetermined confidence threshold using the ASR system of a vehicle;

(d) prompting the user to identify the continuous digits using a body gesture in response to step (c);

(e) detecting the body gesture using an in-vehicle camera or display; and

(f) identifying, using the ASR system, one or more of the continuous digits based on the body gesture, wherein identifying includes detecting at least one of the quantity and identity of the continuous digits using the body gesture; and

(g) adjusting an acoustical reference pattern associated with the continuous digits identified in step (f) using the ASR system.

9. The method of claim 8, further comprising the step of receiving the speech in a tonal language.

10. The method of claim 8, further comprising the step of storing the identified continuous digits with the received speech.

11. The method of claim 8, wherein the continuous digits are received as part of dialing a telephone number.

12. The method of claim 8, wherein the continuous digits are received as part of changing a radio station or providing navigation services.

13. The method of claim 8, further comprising the step of assigning a body gesture to speech associated with one or more continuous digits.