Speech communications system for a vehicle and method of operating a speech communications system for a vehicle

• US 8,214,219 B2
• Filed: 09/15/2006
• Issued: 07/03/2012
• Est. Priority Date: 09/15/2006
• Status: Expired due to Fees

• Current Assignee: Volkswagen of America Inc (Volkswagen AG)
• Original Assignee: Volkswagen of America Inc (Volkswagen AG)
• Inventors: Prieto, Ramon, Mishra, Rohit
• Primary Examiner(s): Godbold, Douglas
• Assistant Examiner(s): Villena, Mark
• Application Number:
  US11/521,929
• Publication Number:
  US 20080071547A1
• Time in Patent Office: 2,118 Days
• Field of Search: 704/275, 704/270, 704/233, 704/211, 381/107, 280/735
• US Class Current: 704/275
• CPC Class Codes: B60N 2/002 Seats provided with an occupancy detection means mounted therein or thereon detection means responsive to presence or absence of children B60N2/266
• CPC Class Codes: B60N 2/0021 characterised by the type of sensor or measurement
• CPC Class Codes: B60N 2/003 characterised by the sensor mounting location in or on the seat
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 2021/02082 the noise being echo, reverberation of the speech
• CPC Class Codes: H04R 3/02 for preventing acoustic reaction , i.e. acoustic oscillatory feedback specially adapted for hearing aids H04R25/453

Abstract

A speech communications system for a vehicle includes a microphone system provided in the vehicle interior in order to detect audio information. An interaction manager provides grammar information to a speech recognizer. The speech recognizer provides speech recognition results to the interaction manager. An acoustic echo canceller eliminates portions of the audio information detected by the microphone system. A sound localizer determines a sound source location in the vehicle interior. A method of operating a speech communications system in a vehicle is also provided. An interruptible text-to-speech operation provides a speech output to a user. Voice information is requested from the user for a maximum number of times if insufficient voice information or no voice information is provided in response to the speech output provided by the interruptible text-to-speech operation. The dialog context of an unfinished speech interaction is saved.

Claims

1. In combination with a vehicle having a vehicle interior, a speech communications system comprising:

a microphone system provided in the vehicle interior, said microphone system being configured to detect audio information;

a speech recognizer operatively connected to said microphone system;

an interaction manager operatively connected to said speech recognizer, said interaction manager providing grammar information to said speech recognizer, said speech recognizer being configured to provide speech recognition results to said interaction manager;

an acoustic echo canceller operatively connected to said speech recognizer, said acoustic echo canceller being configured to at least partially eliminate portions of the audio information detected by said microphone system;

a sound localizer operatively connected to said microphone system and to said interaction manager, said sound localizer being configured to determine a positional sound source location in the vehicle interior;

said microphone system including a first microphone array and a second microphone array, each of said microphone arrays including at least two microphones that do not operate as loudspeakers and that are not configured to be switched to an audio playback state;

said at least two microphones of said first microphone array have respective positions which define a direction and a normal with respect to the direction such that the normal and the direction intersect at a center of said first microphone array, said at least two microphones of said second microphone array have respective positions which define a direction and a normal with respect to the direction such that the normal and the direction intersect at a center of said second microphone array;

said center of said first microphone array and said center of said second microphone array being spaced from one another by a given spacing distance wherein said first microphone array is disposed on a first side of the vehicle interior and said second microphone array is disposed on a second side of the vehicle interior;

said sound localizer determining a first sound source angle as a function of audio information provided by said first microphone array and said sound localizer determining a second sound source angle as a function of audio information provided by said second microphone array;

said sound localizer determining a positional sound source location in dependence on the first sound source angle and the second sound source angle;

said speech recognizer being configured to recognize a spoken keyword; and

said interaction manager being configured to retrieve a stored dialog context and to start a speech interaction triggered by the spoken keyword;

a text-to-speech unit operatively connected to said interaction manager; and

said interaction manager being configured to selectively prompt said text-to-speech unit to provide a speech output and to interrupt a speech output.

2. The speech communications system according to claim 1, wherein said interaction manager selectively enables and disables a user-controllable function in dependence on the positional sound source location.

3. The speech communications system according to claim 1, including:

a seat sensor connected to said sound localizer, said seat sensor providing seat occupancy information to said sound localizer; and

said sound localizer determining a positional sound source location in dependence on the first sound source angle, the second sound source angle and the seat occupancy information.

4. The speech communications system according to claim 1,

wherein said acoustic echo canceller is configured to at least partially eliminate the speech output provided by said text-to-speech unit from the audio information detected by said microphone system.

5. The speech communications system according to claim 1, including:

a vehicle stereo system operatively connected to said interaction manager, said interaction manager being configured to control a volume setting for said vehicle stereo system; and

said acoustic echo canceller being configured to at least partially eliminate sound produced by said vehicle stereo system from the audio information detected by said microphone system.

6. The speech communications system according to claim 1, wherein:

the vehicle has a ventilation fan operatively connected to said interaction manager; and

said interaction manager controls a fan speed setting for said ventilation fan.

7. A method of operating a speech communications system in a vehicle, the method which comprises:

detecting audio information with a microphone system provided in a vehicle interior, the microphone system including a first microphone array and a second microphone array, each of the microphone arrays including at least two microphones that do not operate as loudspeakers and that are not configured to be switched to an audio playback state, the at least two microphones of the first microphone array being disposed at respective positions which define a direction and a normal with respect to the direction such that the normal and the direction intersect at a center of the first microphone array, the at least two microphones of the second microphone array being disposed at respective positions which define a direction and a normal with respect to the direction such that the normal and the direction intersect at a center of the second microphone array, the center of the first microphone array and the center of the second microphone array being spaced from one another by a given spacing distance wherein the first microphone array is disposed on a first side of the vehicle interior and the second microphone array is disposed on a second side of the vehicle interior;

running an interruptible text-to-speech operation based on a dialog context in order to provide a speech output;

running a speech recognition operation for providing a speech recognition result;

requesting voice information for a maximum number of times if insufficient voice information or no voice information is provided in response to the speech output provided by the interruptible text-to-speech operation;

saving a dialog context of an unfinished speech interaction;

determining a first sound source angle as a function of audio information provided by the first microphone array of the microphone system;

determining a second sound source angle as a function of audio information provided by the second microphone array of the microphone system; and

determining a positional sound source location based on the first sound source angle and the second sound source angle.

8. The method according to claim 7, which comprises:

recognizing a keyword with the speech recognition operation; and

retrieving the dialog context which has been saved for the unfinished speech interaction.

9. The method according to claim 7, which comprises at least partially eliminating the speech output provided by the text-to-speech operation from the audio information detected with the microphone system by performing an echo cancellation operation.

10. The method according to claim 7, which comprises at least partially eliminating sound generated by a vehicle stereo system from the audio information detected with the microphone system by performing an echo cancellation operation.

11. The method according to claim 7, which comprises controlling a fan speed of a ventilation fan in order to improve the speech recognition result provided by the speech recognition operation.

12. The method according to claim 7, which comprises controlling a volume setting of a vehicle stereo system in order to improve the speech recognition result provided by the speech recognition operation.

13. The method according to claim 7, which comprises:

detecting a seat occupancy by using a seat sensor; and

determining a positional sound source location in dependence on the first sound source angle, the second sound source angle, and seat occupancy information.

14. The method according to claim 7, which comprises:

determining a positional sound source location in the vehicle interior; and

selectively enabling and disabling a user-controllable function in dependence on the positional sound source location.