Abstract | ||
---|---|---|
This paper considers the problem of rapid and robust speaker adaptation in automatic speech recognition (ASR) systems. We propose an approach using combination of eigenspace-based maximum likelihood linear regression (EMLLR) and evolutionary algorithms. To find the best solution for the coefficients estimation problem, we suggest using genetic algorithm (GA) for rapid speaker adaptation. This is due to the fact that genetic algorithms are not as sensitive as expectation maximization (EM) algorithm to the amount of adaptation data. Experimental results on TIMIT database illustrate that genetic algorithm, using random individuals in first population, leads to up to 1.03% improvement in phoneme recognition rate. Moreover, we show that if the first population contains coefficients initially estimated by maximum likelihood criterion, further improvement can be achieved as well. However, the amount of adaptation data does not have considerable effect on the proposed method. (C) 2010 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of the Guest Editor. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1016/j.procs.2010.12.163 | WORLD CONFERENCE ON INFORMATION TECHNOLOGY (WCIT-2010) |
Keywords | Field | DocType |
Speaker Adaptation, Eigenspace-Based Maximum Likelihood Linear Regression, Expectation Maximization, Genetic Algorithm | Population,Evolutionary algorithm,Computer science,Artificial intelligence,Eigenvalues and eigenvectors,Genetic algorithm,Pattern recognition,Expectation–maximization algorithm,Speech recognition,Maximum likelihood sequence estimation,Machine learning,Speaker adaptation,Maximum likelihood criterion | Journal |
Volume | ISSN | Citations |
3 | 1877-0509 | 0 |
PageRank | References | Authors |
0.34 | 4 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Reza Sahraeian | 1 | 15 | 2.65 |
Mehdi Mohammadi | 2 | 1091 | 50.02 |
Ahmad Akbari | 3 | 159 | 23.17 |
A. Ayatollahi | 4 | 122 | 21.87 |