Paper Info
Title
Use Of Gaussian Selection In Large Vocabulary Continuous Speech Recognition Using Hmms
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 ken reported that when GS is used on large systems the recognition accuracy tends to degrade above a x3 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 x 5 reduction in likelihood computation.
Year
DOI
Venue
1996
10.1109/ICSLP.1996.607156
ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4
Keywords
DocType
Citations 
gaussian processes,degradation,speech recognition,decoding,hidden markov models,real time systems,dynamic range
Conference
18
PageRank 
References 
Authors
1.93
6
3
Name
Order
Citations
PageRank
Kate Knill124928.02
Mark J. F. Gales23905367.45
Steve J. Young334363.09