TEMPORAL CONSTRAINTS IN VITERBI ALIGNMENT FOR SPEECH RECOGNITION IN NOISE
Tipo
Artigo de evento
Data de publicação
1999
Periódico
6th European Conference on Speech Communication and Technology, EUROSPEECH 1999
Citações (Scopus)
0
Autores
Yoma N.B.
Ling L.L.
Stump S.D.
Ling L.L.
Stump S.D.
Orientador
Título da Revista
ISSN da Revista
Título de Volume
Membros da banca
Programa
Resumo
© 1999 6th European Conference on Speech Communication and Technology, EUROSPEECH 1999. All rights reserved.This paper addresses the problem of temporal constraints in the Viterbi algorithm using conditional transition probabilities. The results here presented suggest that in a speaker dependent small vocabulary task the statistical modelling of state durations is not relevant if the max and min state duration restrictions are imposed, and that truncated probability densities give better results than a metric previously proposed [1]. Finally, context dependent and context independent temporal restrictions are compared in a connected word speech recognition task and it is shown that the former leads to better results with the same computational load.
Descrição
Palavras-chave
Assuntos Scopus
Context dependent , Context independent , Probability densities , Speaker dependents , Statistic modeling , Temporal constraints , Temporal restrictions , Transition probabilities , Truncated probability , Viterbi