Title: Incremental MLLR speaker adaptation by fuzzy logic control
Authors: Ding, Ing-Jr
Department of Computer Science
Keywords: speech recognition;speaker adaptation;hidden Markov model;maximum likelihood linear regression;T-S fuzzy logic controller
Issue Date: 1-Nov-2007
Abstract: This paper presents a fuzzy control mechanism for conventional maximum likelihood linear regression (MLLR) speaker adaptation, called FLC-MLLR, by which the effect of MLLR adaptation is regulated according to the availability of adaptation data in such a way that the advantage of MLLR adaptation could be fully exploited when the training data are sufficient, or the consequence of poor MLLR adaptation would be restrained otherwise. The robustness of MLLR adaptation against data scarcity is thus ensured. The proposed mechanism is conceptually simple and computationally inexpensive and effective; the experiments in recognition rate show that FLC-MLLR outperforms standard MLLR especially when encountering data insufficiency and performs better than MAPLR at much less computing cost. (c) 2007 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.
URI: http://dx.doi.org/10.1016/j.patcog.2007.01.027
ISSN: 0031-3203
DOI: 10.1016/j.patcog.2007.01.027
Volume: 40
Issue: 11
Begin Page: 3110
End Page: 3119
Appears in Collections:Articles

Files in This Item:

  1. 000248468800020.pdf