Sixth International Conference on Spoken Language Processing
October 16-20, 2000
Loosely Coupled HMMs for ASR
Harriet J. Nock, Steve J. Young
Cambridge University Engineering Department, Cambridge, UK
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. This paper presents a preliminary feasibility study of an
alternative class of models: loosely coupled HMMs. 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. The paper evaluates one coupled model on a simple
ASR task, using both exact and approximate estimation schemes.
We conclude such models merit further investigation.
Nock, Harriet J. / Young, Steve J. (2000):
"Loosely coupled HMMs for ASR",
In ICSLP-2000, vol.3, 143-146.