Rights accessRestricted access - publisher's policy
In this paper, three different techniques for building semicontinuousHMMbased
speech recognisers are compared:
the classical one, using Euclidean generated codebooks and independently trained acoustic models; jointly reestimating
the codebooks and models obtained with the classical method; and jointly creating codebooks and models growing their size from one centroid to the desired number
of them. The way this growth may be done is carefully addressed, focusing on the selection of the splitting direction and the way splitting is implemented. Results in a large vocabulary task show the ef ciency of the approach, with noticeable improvements both in accuracy and CPU consumption. Moreover, this scheme enables the use of the concatenation of features, avoiding the independence assumption usually needed in semi-continuous HMM modelling, and leading to further improvements in accuracy and CPU.
CitationNogueiras, A.; Caballero, M.; Mariño, J. Joint training of codebooks and acoustic models in automatic speech recognition using semi-continuous HMMs. A: IV Jornadas en Tecnología del Habla. "IV Jornadas en Tecnología del Habla". Zaragoza: Eduardo Lleida Solano, 2006, p. 363-368.
All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder. If you wish to make any use of the work not provided for in the law, please contact: firstname.lastname@example.org