Refinement Approach for Adaptation Based on Combination of MAP and fMLLR

Authors:
Zbyněk Zajíc;Lukáš Machlica;Luděk Müller
Affiliations:
Faculty of Applied Sciences, Department of Cybernetics, University of West Bohemia in Pilsen, Pilsen 306 14;Faculty of Applied Sciences, Department of Cybernetics, University of West Bohemia in Pilsen, Pilsen 306 14;Faculty of Applied Sciences, Department of Cybernetics, University of West Bohemia in Pilsen, Pilsen 306 14
Venue:
TSD '09 Proceedings of the 12th International Conference on Text, Speech and Dialogue
Year:
2009

Citing 1
Cited 4

A tutorial on hidden Markov models and selected applications in speech recognition

Readings in speech recognition

Fast phonetic/lexical searching in the archives of the Czech holocaust testimonies: advancing towards the MALACH project visions

TSD'10 Proceedings of the 13th international conference on Text, speech and dialogue
Integration of speech and text processing modules into a real-time dialogue system

TSD'10 Proceedings of the 13th international conference on Text, speech and dialogue
Czech senior COMPANION: wizard of Oz data collection and expressive speech corpus recording and annotation

LTC'09 Proceedings of the 4th conference on Human language technology: challenges for computer science and linguistics
Prior-shared feature and model space speaker adaptation by consistently employing map estimation

Speech Communication

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper deals with a combination of basic adaptation techniques of Hidden Markov Model used in the speech recognition. The adaptation methods approach the data only through their statistics, which have to be accumulated before the adaptation process. When performing two adaptations subsequently, the data statistics have to be accumulated twice in each of the adaptation passes. However, when the adaptation methods are chosen with care, the data statistics may be accumulated only once, as proposed in this paper. This significantly reduces the time consumption and avoids the need to store all the adaptation data. Combination of Maximum A-Posteriori Probability and feature Maximum Likelihood Linear Regression adaptation is considered. Motivation for such an approach could be the on-line adaptation, where the time consumption is of big importance.