Use of Gaussian selection in large vocabulary continuous speech recognition using HMMS

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 recogni...

Full description

Saved in:
Bibliographic Details
Main Authors: Knill, K.M., Gales, M.J.F., Young, S.J.
Format: Conference Proceeding
Language:English
Subjects:
Decoding
Degradation
Dynamic range
Gaussian processes
Hidden Markov models
Laboratories
Rails
Real time systems
Speech recognition
Vocabulary
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 /spl times/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 /spl times/5 reduction in likelihood computation.
DOI:10.1109/ICSLP.1996.607156