Method and apparatus for discriminative utterance verification u

Details Method and apparatus for discriminative utterance verification u Method and apparatus for discriminative utterance verification u

1997-09-19

2000-09-26

Zele, Krista

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

704246, 704236, 704232, G10L 506, G10L 900

Patent

active

061253456

ABSTRACT:
A multiple confidence measures subsystem of an automated speech recognition system allows otherwise independent confidence measures to be integrated and used for both training and testing on a consistent basis. Speech to be recognized is input to a speech recognizer and a recognition verifier of the multiple confidence measures subsystem. The speech recognizer generates one or more confidence measures. The speech recognizer preferably generates a misclassification error (MCE) distance as one of the confidence measures. The recognized speech output by the speech recognizer is input to the recognition verifier, which outputs one or more confidence measures. The recognition verifier preferably outputs a misverification error (MVE) distance as one of the confidence measures. The confidence measures output by the speech recognizer and the recognition verifier are normalized and then input to an integrator. The integrator integrates the various confidence measures during both a training phase for the hidden Markov models implemented in the speech recognizer and the recognition verifier and during testing of the input speech. The integrator is preferably implemented using a multi-layer perceptron (MLP). The output of the integrator, rather than the recognition verifier, determines whether the recognized utterance hypothesis generated by the speech recognizer should be accepted or rejected.

REFERENCES:
patent: 5317673 (1994-05-01), Cohen
patent: 5710866 (1998-01-01), Alleva
patent: 5799276 (1998-08-01), Komissarchik
"String-based minimum verification error (SB-MVE) training for speech recognition", Mazin G. Rahim et al., Computer Speech and Language (1997) 11, 147-160.
"A Training Procedure for Verifying String Hypotheses in Continuous Speech Recognition", R.C. Rose et al., Inter. Conf. On Acoust. Speech and Signal Proc., Detroit, May 1995.
Utterance Verification of Keywork Strings Using Word-Based Minimum Verification Error (WB-MVE) Training, Rafid A. Sukkar, et al., AT&T Bell Laboratories, Proceedings ICSLP, pp. 602-605, 1996.
"Discriminative Utterance Verification for Connected Digits Recognition", Mazin G. Rahim, et al., IEEE Transactions on Speech and Audio Processing, vol. 5. No. 3, May 1997.
"Minimum Classification Error Rate Methods for Speech Recognition", Biing-Hwang Juang, et al., IEEE Transactions on Speech and Audio Processing, vol. 5, No. 3, May 1997.
"An Introduction to Computing with Neural Nets", Richard P. Lippmann, IEEE ASSP Magazine, pp. 4-22, Apr. 1987.

Affiliated with

Also associated with

Rating

Method and apparatus for discriminative utterance verification u does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Method and apparatus for discriminative utterance verification u, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for discriminative utterance verification u will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2108354