Speaker stress-resistant continuous speech recognition

Published 6 January 2003

D.B. Paul, Edward A. Martin

DOI10.1109/icassp.1988.196571

Citations52

TL;DR

This system extends an earlier robust continuous observation HMM IWR system to continuous speech using the DARPA-robust (multi-condition with a pilot's facemask) database.

Abstract

Most speech recognizers are sensitive to the speech style and the speaker's environment. This system extends an earlier robust continuous observation HMM IWR system to continuous speech using the DARPA-robust (multi-condition with a pilot's facemask) database. Performance on a 207 word, perplexity 14 task is 0.9% word error rate under office conditions and 2.5% (best speaker) and 5% (4 speaker average) for the normal test condition of the database.>

Keywords

Computer Science

IEEE Transactions on Pattern Analysis and Machine IntelligenceA Maximum Likelihood Approach to Continuous Speech Recognition

1,220 Citations1983L.R. Bahl, Frederick Jelinek +1 more

This paper describes a number of statistical models for use in speech recognition, with special attention to determining the parameters for such models from sparse data, and describes two decoding methods appropriate for constrained artificial languages and one appropriate for more realistic decoding tasks.

Multi-style training for robust isolated-word speech recognition

313 Citations2005Richard P. Lippmann, Edward A. Martin +1 more

A new training procedure called multi-style training has been developed to improve performance when a recognizer is used under stress or in high noise but cannot be trained in these conditions.

Context-dependent modeling for acoustic-phonetic recognition of continuous speech

218 Citations2005Richard Schwartz, Y.-L. Chow +4 more

The combination of general spectral information and specific acoustic-phonetic features is shown to result in more accurate phonetic recognition than either representation by itself.

IEEE Transactions on Acoustics Speech and Signal ProcessingCepstral domain talker stress compensation for robust speech recognition

99 Citations1988Y. Chen

A study of talker-stress-induced intraword variability and an algorithm that compensates for the systematic changes observed are presented and the functional form of the compensation is shown to correspond to the equalization of spectral tilts.

Recognition of speech under stress and in noise

57 Citations2005P.K. Rajasekaran, George R. Doddington +1 more

This paper reports on recognition experiments conducted with a "simulated stress" data base using a baseline algorithm and its modifications, which show that these algorithms perform acceptably well for a vocabulary of 105 words under normal conditions, but degrade by an order of magnitude under the "stress" conditions.

A speaker-stress resistant HMM isolated word recognizer

53 Citations2005D. Paul

An effort to make a Hidden Markov Model Isolated Word Recognizer (IWR) tolerant to such speech changes caused by speaker stress was made.

Two-stage discriminant analysis for improved isolated-word recognition

24 Citations2005Edward A. Martin, Richard P. Lippmann +1 more

A two-stage isolated word speech recognition system that uses a Hidden Markov Model (HMM) recognizer in the first stage and a discriminant analysis system in the second stage, reducing the overall error rate by more than a factor of two.

Discriminant clustering using an HMM isolated-word recognizer

3 Citations2003R.P. Lipmann, Edward A. Martin

A training procedure called discriminant clustering is presented that creates subword models automatically and reduces the computation required during recognition for a 35-word vocabulary by roughly one-third while maintaining a low error rate.