Lasso environment model combination for robust speech recognition

• Main Authors: Xiao, Xiong, Li, Jinyu, Chng, Eng Siong, Li, Haizhou
• Other Authors: School of Computer Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2013
• Subjects: DRNTU::Engineering::Computer science and engineering
• Online Access: https://hdl.handle.net/10356/98809; http://hdl.handle.net/10220/13389
• Institution: Nanyang Technological University

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.