Residual noise compensation for robust speech recognition in nonstationary noise

Abstract

We present a model-based noise compensation algorithm for robust speech recognition in nonstationary noisy environments. The effect of noise is split into a stationary part, compensated by parallel model combination, and a time varying residual. The evolution of residual noise parameters is represented by a set of state space models. The state space models… (More)
DOI: 10.1109/ICASSP.2000.859162

Topics

2 Figures and Tables

Cite this paper

@inproceedings{Yao2000ResidualNC, title={Residual noise compensation for robust speech recognition in nonstationary noise}, author={Kaisheng Yao and Bertram E. Shi and Pascale Fung and Zhigang Cao}, booktitle={ICASSP}, year={2000} }