HMM-based pseudo-clean speech synthesis for splice algorithm
Lists
Only you see this
Abstract
In this paper, we present a novel approach to relax the constraint of stereo-data which is needed in a series of algorithms for noise-robust speech recognition. As a demonstration in SPLICE algorithm, we generate the pseudo-clean features to replace the ideal clean features from one of the stereo channels, by using HMM-based speech synthesis. Experimental results on aurora2 database show that the performance of our approach is comparable with that of SPLICE. Further improvements are achieved by concatenating a bias adaptation algorithm to handle unknown environments. Relative word error rate reductions of 66% and 24% are achieved over the baseline systems in the clean-training and multi-training conditions, respectively.
BibTeX
@inproceedings{du2010hmm,
author = {Jun Du and Yu Hu and Li-Rong Dai and Ren-Hua Wang},
title = {{HMM-based pseudo-clean speech synthesis for splice algorithm}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2010},
doi = {10.1109/icassp.2010.5495569},
}Loading related content...