Method and system for using vehicle sound information to enhance audio prompting

• US 9,418,674 B2
• Filed: 01/17/2012
• Issued: 08/16/2016
• Est. Priority Date: 01/17/2012
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: Tzirkel-Hancock, Eli, Tsimhoni, Omer
• Primary Examiner(s): Lerner, Martin
• Application Number:
  US13/351,317
• Publication Number:
  US 20130185066A1
• Time in Patent Office: 1,673 Days
• Field of Search: 704/258, 704/260, 704/267, 704/268, 704/269, 704/275, 704/207, 704/226, 704/227, 704/228, 704/231, 704/233, 379/88.16
• US Class Current: 1/1
• CPC Class Codes: G10L 13/04 Details of speech synthesis systems, e.g. synthesiser structure or memory management
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2021/03643 Diver speech
• CPC Class Codes: G10L 21/003 Changing voice quality, e.g. pitch or formants
• CPC Class Codes: G10L 21/057 for improving intelligibility

Abstract

Sound related vehicle information representing one or more sounds may be received in a processor associated with a vehicle. The sound related vehicle information may or may not include an audio signal. An audio signal output to a passenger may be modified based on the sound related vehicle information.

Claims

1. A method of improving recognizability of a voice command comprising:

capturing a voice command of a vehicle occupant through a microphone, the voice command including background noise associated with vehicle operation;

using information on a vehicle system that relates to sounds in the vehicle to obtain a vehicle parameter describing a state of the vehicle system;

using a vehicular dialogue system to;

construct a digital interference profile including noise type and noise level in accordance with the vehicle parameter describing the state of the vehicle system;

select a pre-trained acoustic model based on the interference profile;

apply the pre-trained acoustic model to the voice command so as to generate a voice command modification having enhanced recognizability, the pre-trained acoustic model generated from supervised learning of records of the noise type and the noise level;

synthesize an audio prompt requesting clarification of the voice command modification, the audio prompt having a modified syllable duration and a modified prompt spectrum in accordance with the interference profile; and

initiate a vehicular action in accordance with the voice command modification.

2. The method of claim 1, further comprising using a vehicular dialogue system wherein the vehicular dialogue system is further configured to cause text rendered into the audio prompt having a modified syllable duration to be displayed on a display device.

3. The method of claim 2, wherein the audio prompt has a modified speech rate in accordance with the interference profile.

4. The method of claim 2, further comprising using the vehicular dialogue system to request a tactile implemented clarification of the voice command modification.

5. The method of claim 2, further comprising using the vehicular dialogue system to request an audial clarification of the voice command.

6. The method of claim 1, wherein the vehicle parameter describing a state of the vehicle system indicates a window position.

7. The method of claim 1, wherein the vehicle parameter describing a state of the vehicle system indicates an engine RPM.

8. The method of claim 1, wherein the vehicle parameter describing a state of the vehicle system indicates a speed of the vehicle.

9. The method of claim 1, wherein the vehicle parameter describing a state of the vehicle system indicates a fan setting.

10. The method of claim 1, wherein the vehicle parameter describing a state of the vehicle system indicates an audio playback level.

11. A system for improving recognizability of a voice command comprising:

a vehicular microphone configured to capture a voice command of a vehicle occupant together with background noise associated with vehicle operation; and

a vehicular dialogue system linked to the microphone, the dialogue system configured to;

use information on a vehicle system that relates to sounds in the vehicle to obtain a vehicle parameter describing a state of the vehicle system;

construct a digital interference profile including noise type parameters and noise level parameters in accordance with the vehicle parameter describing the state of the vehicle system,

select a pre-trained acoustic model based on the interference profile,

apply the pre-trained acoustic model to the voice command so as to generate a voice command modification having enhanced recognizability, the pre-trained acoustic model generated from supervised learning of records of the noise type and the noise level,

synthesize an audio prompt requesting clarification of the voice command modification, the audio prompt having a modified syllable duration and modified prompt spectrum in accordance with the interference profile, and

initiate a vehicular action in accordance with the voice command modification.

12. The system of claim 11, wherein the vehicular dialogue system is further configured to display text rendered into the audio prompt having a modified syllable duration.

13. The system of claim 12, wherein the audio prompt has a modified speech rate in accordance with the interference profile.

14. The system of claim 12, wherein the vehicular dialogue system is further configured to request a tactile implemented clarification of the voice command modification.

15. A method of improving recognizability of a voice command comprising:

capturing a voice command of a vehicle occupant through a microphone positioned within a cabin of the vehicle;

capturing vehicle background noise associated with vehicle operation through a microphone positioned on an exterior to the cabin;

using information on a vehicle system that relates to sounds in the vehicle to obtain a vehicle parameter describing a state of the vehicle system;

using a vehicular dialogue system to;

construct a digital interference profile including noise type and noise level in accordance with the vehicle parameter describing the state of the vehicle system;

select a pre-trained acoustic model based on the interference profile;

apply the pre-trained acoustic model to the voice command so as to generate a voice command modification having enhanced recognizability, the pre-trained acoustic model generated from supervised learning of records of the noise type and the noise level;

synthesize an audio prompt requesting clarification of the voice command modification, the audio prompt having a modified syllable duration in accordance with the interference profile; and

initiate a vehicular action in accordance with the voice command modification.