Use Of Gaussian Selection In Large Vocabulary Continuous Speech Recognition Using HMMs

Use Of Gaussian Selection In Large Vocabulary Continuous Speech Recognition Using HMMs (1996)

by K.M.Knill , M.J.F.Gales , S.J.Young

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	Use Of Gaussian Selection In Large Vocabulary Continuous Speech Recognition Using HMMs	user correction - Legacy Corrections
AUTHOR NAME	K.M.Knill	user correction - Legacy Corrections
AUTHOR NAME	M.J.F.Gales	user correction - Legacy Corrections
AUTHOR NAME	S.J.Young	user correction - Legacy Corrections
ABSTRACT	This paper investigates the use of Gaussian Selection (GS) to reduce the state likelihood computation in HMM-based systems. These likelihood calculations contribute significantly (30 to 70%) to the computational load. Previously, it has been reported that when GS is used on large systems the recognition accuracy tends to degrade above a #3 reduction in likelihood computation. To explain this degradation, this paper investigates the trade-offs necessary between achieving good state likelihoods and low computation. In addition, the problem of unseen states in a cluster is examined. It is shown that further improvements are possible. For example, using a different assignment measure, with a constraint on the number of components per state per cluster, enabled the recognition accuracy on a 5k speaker-independent task to be maintained up to a #5 reduction in likelihood computation.	user correction - Legacy Corrections
YEAR	1996	user correction - Legacy Corrections
CITATIONS	10 found	ParsCit 1.0