Improved HMM models for high performance speech recognition

Authors:
Steve Austin;Chris Barry;Yen-Lu Chow;Alan Derr;Owen Kimball;Francis Kubala;John Makhoul;Paul Placeway;William Russell;Richard Schwartz;George Yu
Affiliations:
BBN Systems and Technologies Corporation, Cambridge, MA;BBN Systems and Technologies Corporation, Cambridge, MA;BBN Systems and Technologies Corporation, Cambridge, MA;BBN Systems and Technologies Corporation, Cambridge, MA;BBN Systems and Technologies Corporation, Cambridge, MA;BBN Systems and Technologies Corporation, Cambridge, MA;BBN Systems and Technologies Corporation, Cambridge, MA;BBN Systems and Technologies Corporation, Cambridge, MA;BBN Systems and Technologies Corporation, Cambridge, MA;BBN Systems and Technologies Corporation, Cambridge, MA;BBN Systems and Technologies Corporation, Cambridge, MA
Venue:
HLT '89 Proceedings of the workshop on Speech and Natural Language
Year:
1989

Citing 5
Cited 2

Recent progress in the SPHINX Speech Recognition system

HLT '89 Proceedings of the workshop on Speech and Natural Language
The Lincoln Continuous Speech Recognition system: recent developments and results

HLT '89 Proceedings of the workshop on Speech and Natural Language
The acoustic-modeling problem in automatic speech recognition

The acoustic-modeling problem in automatic speech recognition
A simple statistical class grammar for measuring speech recognition performance

HLT '89 Proceedings of the workshop on Speech and Natural Language
The N-Best algorithm: an efficient procedure for finding top N sentence hypotheses

HLT '89 Proceedings of the workshop on Speech and Natural Language

The Lincoln tied-mixture HMM continuous speech recognizer

HLT '90 Proceedings of the workshop on Speech and Natural Language
Factorization of language constraints in speech recognition

ACL '91 Proceedings of the 29th annual meeting on Association for Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we report on the various techniques that we implemented in order to improve the basic speech recognition performance of the BYBLOS system. Some of these methods are new, while others are not. We present methods that improved performance as well as those that did not. The methods include Linear Discriminant Analysis, Supervised Vector Quantization, Shared Mixture VQ. Deleted Estimation of Context Weights, MMI Estimation Using "N-Best" Alternatives, Cross-Word Triphone Models. While we have not yet combined all of the methods in one system, the overall word recognition error rate on the May 1988 test set using the Word-Pair grammar has decreased from 3.4% to 1.7%.