DMCA
CONSTRUCTION OF MODEL-SPACE CONSTRAINTS
| Citations: | 1 - 0 self |
BibTeX
@MISC{Nguyen_constructionof,
author = {Patrick Nguyen and Luca Rigazio and Christian Wellekens and Jean-claude Junqua},
title = {CONSTRUCTION OF MODEL-SPACE CONSTRAINTS},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
HMM systems exhibit a large amount of redundancy. To this end, a technique called Eigenvoices was found to be very effective for speaker adaptation. The correlation between HMM parameters is exploited via a linear constraint called eigenspace. This constraint is obtained through a PCA analysis of the training speakers. In this paper, we show how PCA can be linked to the maximum-likelihood criterion. Then, we extend the method to LDA transformations and piecewise linear constraints. On the Wall Street Journal (WSJ) dictation task, we obtain 1.7 % WER improvement (15 % relative) when using selfadaptation. 1. OPTIMAL ESTIMATION OF THE EIGENSPACE In this section, we show that the expected log-likelihood of the data is related to a sum of squared euclidean distances in the model space. This justifies using the SVD to compute the eigenspace. First, we will show that the log-likelihood of rows of MLLR matrices defines a quadratic form. Then, we define proper normalization to reduce the ML problem to a standard least-squares problem, that can be solved by SVD. 1.1. Gaussianity of MLLR rows Speaker dependent models are needed to build the eigenspace. However, for large vocabulary applications, building these models is difficult because of data sparsity and memory requirements. In practice, most systems use MLLR-adapted models [1]. MLLR transforms model ¦¨ § means by a matrix
Keyphrases
model-space constraint training speaker quadratic form dictation task linear constraint ml problem speaker dependent model model space hmm parameter squared euclidean distance pca analysis mllr matrix data sparsity wer improvement speaker adaptation mllr-adapted model maximum-likelihood criterion large vocabulary application lda transformation memory requirement wall street journal expected log-likelihood model mean piecewise linear constraint standard least-squares problem hmm system proper normalization large amount optimal estimation
