Premium
Modelling asynchrony in automatic speech recognition using loosely coupled hidden Markov models
Author(s) -
Nock H.J.,
Young S.J.
Publication year - 2002
Publication title -
cognitive science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.498
H-Index - 114
eISSN - 1551-6709
pISSN - 0364-0213
DOI - 10.1207/s15516709cog2603_5
Subject(s) - hidden markov model , computer science , speech recognition , task (project management) , decoding methods , asynchrony (computer programming) , markov model , word (group theory) , artificial intelligence , algorithm , machine learning , markov chain , asynchronous communication , mathematics , computer network , management , economics , geometry
Hidden Markov models (HMMs) have been successful for modelling the dynamics of carefully dictated speech, but their performance degrades severely when used to model conversational speech. Since speech is produced by a system of loosely coupled articulators, stochastic models explicitly representing this parallelism may have advantages for automatic speech recognition (ASR), particularly when trying to model the phonological effects inherent in casual spontaneous speech. This paper presents a preliminary feasibility study of one such model class: loosely coupled HMMs . Exact model estimation and decoding is potentially expensive, so possible approximate algorithms are also discussed. Comparison of one particular loosely coupled model on an isolated word task suggests loosely coupled HMMs merit further investigation. An approximate algorithm giving performance which is almost always statistically indistinguishable from the exact algorithm is also identified, making more extensive research computationally feasible.