Speech recognition using blind source separation and dereverberation method for mixed sound of speech and music

Abstract

In this paper, we propose a method for performing a non-stationary noise reduction and dereverberation method. We use a blind dereverberation method based on spectral subtraction using a multi-channel least mean square algorithm has been proposed in our previous study. To suppress the non-stationary noise, we used a blind source separation based on an efficient fast independent component analysis algorithm. This method is evaluated using a mixed sound of speech and music, and achieves an average relative word error reduction rate of 41.9% and 7.9% compared with a baseline method and the state-of-the-art multistep linear prediction-based dereverberation, respectively, in a real environment.

DOI: 10.1109/APSIPA.2013.6694159

Extracted Key Phrases

5 Figures and Tables

Cite this paper

@article{Wang2013SpeechRU, title={Speech recognition using blind source separation and dereverberation method for mixed sound of speech and music}, author={Longbiao Wang and Kyohei Odani and Atsuhiko Kai and Weifeng Li}, journal={2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference}, year={2013}, pages={1-4} }