|
KMID : 1022420150070030131
|
|
Phonetics and Speech Sciences
2015 Volume.7 No. 3 p.131 ~ p.138
|
|
|
L1-norm Regularization for State Vector Adaptation of Subspace Gaussian Mixture Model
|
|
Goo Ja-Hyu
Kim Young-Gwan
Kim Hoi-Rin
|
|
|
Abstract
|
|
|
|
In this paper, we propose L1-norm regularization for state vector adaptation of subspace Gaussian mixture model (SGMM). When you design a speaker adaptation system with GMM-HMM acoustic model, MAP is the most typical technique to be considered. However, in MAP adaptation procedure, large number of parameters should be updated simultaneously. We can adopt sparse adaptation such as L1-norm regularization or sparse MAP to cope with that, but the performance of sparse adaptation is not good as MAP adaptation. However, SGMM does not suffer a lot from sparse adaptation as GMM-HMM because each Gaussian mean vector in SGMM is defined as a weighted sum of basis vectors, which is much robust to the fluctuation of parameters. Since there are only a few adaptation techniques appropriate for SGMM, our proposed method could be powerful especially when the number of adaptation data is limited. Experimental results show that error reduction rate of the proposed method is better than the result of MAP adaptation of SGMM, even with small adaptation data.
|
|
|
KEYWORD
|
|
|
L1-norm regularization, speaker adaptation, state vector adaptation, subspace gaussian mixture model, automatic speech recognition
|
|
|
FullTexts / Linksout information
|
|
|
|
|
|
Listed journal information
|
|
|
|