Please use this identifier to cite or link to this item:
https://hdl.handle.net/10356/98809
Title: | Lasso environment model combination for robust speech recognition | Authors: | Xiao, Xiong Li, Jinyu Chng, Eng Siong Li, Haizhou |
Keywords: | DRNTU::Engineering::Computer science and engineering | Issue Date: | 2012 | Source: | Xiao, X., Li, J., Chng, E. S., & Li, H. (2012). Lasso environment model combination for robust speech recognition. 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4305-4308. | Conference: | IEEE International Conference on Acoustics, Speech and Signal Processing (2012 : Kyoto, Japan) | Abstract: | In this paper, we propose a novel acoustic model adaptation method for noise robust speech recognition. Model combination is a common way to adapt acoustic models to a target test environment. For example, the mean supervectors of the adapted model are obtained as a linear combination of mean supervectors of many pre-trained environment-dependent acoustic models. Usually, the combination weights are estimated using a maximum likelihood (ML) criterion and the weights are nonzero for all the mean supervectors. We propose to estimate the weights by using Lasso (least absolute shrinkage and selection operator) which imposes an L1 regularization term in the weight estimation problem to shrink some weights to exactly zero. Our study shows that Lasso usually shrinks to zero the weights of those mean supervectors not relevant to the test environment. By removing some nonrelevant supervectors, the obtained mean supervectors are found to be more robust against noise distortions. Experimental results on Aurora-2 task show that the Lasso-based mean combination consistently outperforms ML-based combination. | URI: | https://hdl.handle.net/10356/98809 http://hdl.handle.net/10220/13389 |
DOI: | 10.1109/ICASSP.2012.6288871 | Schools: | School of Computer Engineering | Research Centres: | Temasek Laboratories | Rights: | © 2012 IEEE. | Fulltext Permission: | none | Fulltext Availability: | No Fulltext |
Appears in Collections: | TL Conference Papers |
SCOPUSTM
Citations
50
8
Updated on Mar 3, 2024
Page view(s) 10
894
Updated on Mar 18, 2024
Google ScholarTM
Check
Altmetric
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.