Background voice recognition trainer

Patent metadata

Field	Value
Publication number	US-9792911-B2
Application number	US-201514667134-A
Country	US
Kind code	B2
Filing date	Mar 24, 2015
Priority date	Mar 25, 2014
Publication date	Oct 17, 2017
Grant date	Oct 17, 2017

Abstract

A method of operating a speech recognition system includes converting a spoken utterance by a user into an electrical voice signal by use of a local microphone associated with a local electronic device. The electrical voice signal is transmitted to a remote voice recognizer. The remote voice recognizer is used to transcribe the electrical voice signal and to produce a confidence score. The confidence score indicates a level of confidence that the transcription of the electrical voice signal substantially matches the words of the spoken utterance. The transcription of the electrical voice signal and the confidence score are transmitted from the remote voice recognizer to the local electronic device. The electrical voice signal, the transcription of the electrical voice signal, and the confidence score are used at the local device to train a local voice recognizer.

First claim

What is claimed is:

1. A method of operating a speech recognition system, comprising the steps of:
converting a spoken utterance by a user into an electrical voice signal by use of a local microphone associated with a local electronic device;
transmitting the electrical voice signal to a remote voice recognizer;
using the remote voice recognizer to transcribe the electrical voice signal and to produce a confidence score, the confidence score indicating a level of confidence that the transcription of the electrical voice signal substantially matches the words of the spoken utterance;
transmitting the transcription of the electrical voice signal and the confidence score from the remote voice recognizer to the local electronic device; and
using the electrical voice signal, the transcription of the electrical voice signal and the confidence score at the local electronic device to train a local voice recognizer.

2. The method of claim 1 comprising the further steps of:
receiving confirmation from the user that the transcription of the electrical voice signal substantially matches the words of the spoken utterance; and
using the confirmation from the user to train the local voice recognizer.

3. The method of claim 1 wherein the training of the local voice recognizer is performed only if the confidence score is above a threshold level.

4. The method of claim 1 comprising the further step of storing the electrical voice signal and the transcription of the electrical voice signal, the training of the local voice recognizer being performed only after more than a threshold amount of data associated with the electrical voice signals and the transcriptions of the electrical voice signals has been stored.

5. The method of claim 1 wherein the local microphone, the local electronic device, and the local voice recognizer are disposed within a motor vehicle, and the remote voice recognizer is disposed outside the motor vehicle.

6. The method of claim 5 wherein the remote voice recognizer is disposed in a building away from the motor vehicle.

7. The method of claim 1 wherein the transmitting steps are performed wirelessly.

8. A motor vehicle speech recognition arrangement, comprising:
a local electronic device including a local microphone disposed in the motor vehicle, the local microphone being configured to convert a spoken utterance by a user into an electrical voice signal, the local electronic device being configured to transmit the electrical voice signal;
a remote voice recognizer disposed outside the vehicle and configured to:
receive the electrical voice signal;
transcribe the electrical voice signal;
produce a confidence score, the confidence score indicating a level of confidence that the transcription of the electrical voice signal substantially matches the words of the spoken utterance; and
transmit the transcription of the electrical voice signal and the confidence score to the local electronic device; and

a local voice recognizer disposed in the motor vehicle, the local voice recognizer configured to be trained by use of the electrical voice signal, the transcription of the electrical voice signal and the confidence score.

9. The arrangement of claim 8 wherein the local electronic device is configured to:
receive confirmation from the user that the transcription of the electrical voice signal substantially matches the words of the spoken utterance; and
use the confirmation from the user to train the local voice recognizer.

10. The arrangement of claim 8 wherein the local electronic device is configured to train the local voice recognizer only if the confidence score is above a threshold level.

11. The arrangement of claim 8 further comprising a memory device disposed in the motor vehicle and configured to store the electrical voice signal and the transcription of the electrical voice signal, the local electronic device being configured to train the local voice recognizer only after more than a threshold amount of data associated with the electrical voice signals and the transcriptions of the electrical voice signals has been stored.

12. The arrangement of claim 8 wherein the remote voice recognizer is disposed in a building away from the motor vehicle.

13. The arrangement of claim 8 wherein the electrical voice signal, the transcription of the electrical voice signal, and the confidence score are transmitted wirelessly.

14. The arrangement of claim 8 wherein the local electronic device is configured to respond to a denial received from the user that the transcription of the electrical voice signal substantially matches the words of the spoken utterance by not using the transcription to train the local voice recognizer.

15. A method of operating a speech recognition system, comprising the steps of:
converting a spoken utterance by a user into an electrical voice signal by use of a local microphone associated with a local electronic device;
transmitting the electrical voice signal to a remote voice recognizer;
using the remote voice recognizer to transcribe the electrical voice signal;
transmitting the transcription of the electrical voice signal from the remote voice recognizer to the local electronic device;
in response to receiving confirmation from the user that the transcription of the electrical voice signal substantially matches the words of the spoken utterance, using the electrical voice signal, the transcription of the electrical voice signal and the confirmation from the user to train the local voice recognizer;
in response to receiving denial from the user that the transcription of the electrical voice signal substantially matches the words of the spoken utterance, omitting the electrical voice signal and the transcription of the electrical voice signal from use in training the local voice recognizer; and
in response to receiving neither confirmation nor denial from the user that the transcription of the electrical voice signal substantially matches the words of the spoken utterance, using the electrical voice signal and the transcription of the electrical voice signal to train the local voice recognizer.

16. The method of claim 15 further comprising using the remote voice recognizer to produce a confidence score, the confidence score indicating a level of confidence that the transcription of the electrical voice signal substantially matches the words of the spoken utterance, wherein the training of the local voice recognizer is performed only if the confidence score is above a threshold level.

17. The method of claim 15 comprising the further step of storing the electrical voice signal and the transcription of the electrical voice signal, the training of the local voice recognizer being performed only after more than a threshold amount of data associated with the electrical voice signals and the transcriptions of the electrical voice signals has been stored.

18. The method of claim 15 wherein the local microphone, the local electronic device, and the local voice recognizer are disposed within a motor vehicle, and the remote voice recognizer is disposed outside the motor vehicle.

19. The method of claim 18 wherein the remote voice recognizer is disposed in a building away from the motor vehicle.

20. The method of claim 15 wherein the transmitting steps are performed wirelessly.

Assignees

• Panasonic Automotive Systems Co America Division Of Panasonic Corp North America

Inventors

• Veksler Ilya
• Kumar Ambuj
• Korupol Naveen Reddy

Classifications

• G10L15/30 Primary

  Distributed recognition, e.g. in client-server systems, for mobile phones or network applications · CPC title

• G10L2015/0638

  Interactive procedures · CPC title

• G10L15/063

  Training · CPC title