DocumentCode :
417297
Title :
A tree-structured clustering method integrating noise and SNR for piecewise linear-transformation-based noise adaptation
Author :
Zhang, Zhipeng ; Sugimura, Toshiaki ; Furui, Sadaoki
Author_Institution :
Multimedia Labs., NTT DoCoMo, Kanagawa, Japan
Volume :
1
fYear :
2004
fDate :
17-21 May 2004
Abstract :
This paper proposes the application of a tree-structured clustering method that integrates the effects of noise as well as SNR variation in the framework of piecewise-linear transformation (PLT)-based noise adaptation for robust speech recognition. According to the clustering results, a noisy speech HMM is made for each node of the tree structure. An HMM that best matches the input speech is selected based on the likelihood maximization criterion by tracing the tree downward from the top (root), and the selected HMM is further adapted by linear transformation. The proposed method is evaluated by applying it to a Japanese dialogue recognition system. Experimental results confirm that the proposed method is effective in recognizing numerically noise-added speech and actual noisy speech uttered by a wide range of speakers under various noise conditions.
Keywords :
hidden Markov models; maximum likelihood estimation; pattern clustering; pattern matching; piecewise linear techniques; speech recognition; tree searching; Japanese dialogue recognition system; SNR variation; likelihood maximization criterion; noisy speech HMM; numerically noise-added speech; pattern matching; piecewise linear-transformation-based noise adaptation; robust speech recognition; tree node; tree-structured clustering; Adaptation model; Additive noise; Clustering methods; Hidden Markov models; Maximum likelihood estimation; Noise figure; Noise robustness; Signal to noise ratio; Speech enhancement; Speech recognition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on
ISSN :
1520-6149
Print_ISBN :
0-7803-8484-9
Type :
conf
DOI :
10.1109/ICASSP.2004.1326152
Filename :
1326152
Link To Document :
بازگشت