The Lincoln Continuous Speech Recognition system: recent developments and results
Published 1 January 1989Open access
Douglas B. Paul
Citations19
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The Lincoln stress-resistant HMM CSR has been extended to large vocabulary continuous speech for both speaker-dependent (SD) and speaker-independent (SI) tasks.
Abstract
The Lincoln stress-resistant HMM CSR has been extended to large vocabulary continuous speech for both speaker-dependent (SD) and speaker-independent (SI) tasks. Performance on the DARPA Resource Management task (991 word vocabulary, perplexity 60 word-pair grammar) [1] is 3.4% word error rate for SD training of word-context-dependent triphone models and 12.6% word error rate for SI training of (word-context-free) tied mixture triphone models.
Keywords
Computer Science
The DARPA 1000-word resource management database for continuous speech recognition
341 Citations2003P. Price, William M. Fisher +2 more
A database of continuous read speech has been designed and recorded within the DARPA strategic computing speech recognition program for use in designing and evaluating algorithms for speaker-independent, speaker-adaptive and speaker-dependent speech recognition.
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 SpectrumComputers: Speech recognition: Turning theory to practice: New ICs have brought the requisite computer power to speech technology; an evaluation of equipment shows where it stands today
160 Citations1981George R. Doddington, Thomas B. Schalk
An evaluation of the equipment now available for turning the theory of electronic speech recognition into practice and the fulfilment of this goal seems much closer than it did because of the pace of advance in IC technology.
A new algorithm for the estimation of hidden Markov model parameters
117 Citations2003L.R. Bahl, Peter F. Brown +2 more
The authors argue that maximum-likelihood estimation of the parameters does not lead to values which maximize recognition accuracy and describe an alternative estimation procedure called corrective training which is aimed at minimizing the number of recognition errors.
Large-vocabulary speaker-independent continuous speech recognition using HMM
95 Citations2003K.-F. Lee, Hsiao-Wuen Hon
On a 997-word task using a bigram grammar, SPHINX achieved a word accuracy of 93%.
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.
Speaker stress-resistant continuous speech recognition
52 Citations2003D.B. Paul, Edward A. Martin
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.
Continuous speech recognition results of the BYBLOS system on the DARPA 1000-word resource management database
25 Citations2003Francis Kubala, Y.-L. Chow +9 more
The system was trained in a speaker dependent mode on 28 minutes of speech from each of 8 speakers, and was tested on independent test material for each speaker with three artificial grammars spanning a broad perplexity range.
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.
Cepstral domain stress compensation for robust speech recogniton
13 Citations2005Yeunung Chen
This paper presents a study of talker- stress-induced intraword variability, and an algorithm that compensates for the systematic changes observed, based on Hidden Markov Models trained by speech tokens in various talking styles.
Dynamic adaptation of Hidden Markov models for robust isolated-word speech recognition
8 Citations2003Edward A. Martin, Richard P. Lippmann +1 more
An HMM-based isolated-word recognition system that dynamically adapts word model parameters to new speakers and to stress-induced speech variations that produces results comparable to multistyle-trained systems.