TEMPORAL CONSTRAINTS IN VITERBI ALIGNMENT FOR SPEECH RECOGNITION IN NOISE

Página do item simplificado
dc.contributor.authorYoma N.B.
dc.contributor.authorLing L.L.
dc.contributor.authorStump S.D.
dc.date.accessioned2024-03-13T01:47:30Z
dc.date.available2024-03-13T01:47:30Z
dc.date.issued1999
dc.description.abstract© 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.
dc.description.firstpage2861
dc.description.lastpage2864
dc.identifier.urihttps://dspace.mackenzie.br/handle/10899/38066
dc.relation.ispartof6th European Conference on Speech Communication and Technology, EUROSPEECH 1999
dc.rightsAcesso Restrito
dc.titleTEMPORAL CONSTRAINTS IN VITERBI ALIGNMENT FOR SPEECH RECOGNITION IN NOISE
dc.typeArtigo de evento
local.scopus.citations0
local.scopus.eid2-s2.0-85135255683
local.scopus.subjectContext dependent
local.scopus.subjectContext independent
local.scopus.subjectProbability densities
local.scopus.subjectSpeaker dependents
local.scopus.subjectStatistic modeling
local.scopus.subjectTemporal constraints
local.scopus.subjectTemporal restrictions
local.scopus.subjectTransition probabilities
local.scopus.subjectTruncated probability
local.scopus.subjectViterbi
local.scopus.updated2024-05-01
local.scopus.urlhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85135255683&origin=inward
Arquivos
Coleções
Artigo de evento