Speech Enhancement Based on Blind Source Separation in Car Environments


This paper describes a new speech enhancement system used in car environments, where independent component analysis (ICA)-based blind source separation (BSS) and subband elimination (SBE) processing are combined to achieve a high separation performance. The proposed method consists of two parts, fast-convergence frequency domain ICA and SBE processing based… (More)
DOI: 10.1109/ICDE.2005.289


14 Figures and Tables

Cite this paper

@article{Saruwatari2005SpeechEB, title={Speech Enhancement Based on Blind Source Separation in Car Environments}, author={Hiroshi Saruwatari and Katsuyuki Sawai and Tsuyoki Nishikawa and Akinobu Lee and Kiyohiro Shikano and Atsunobu Kaminuma and Masao Sakata and Daisuke Saitoh}, journal={21st International Conference on Data Engineering Workshops (ICDEW'05)}, year={2005}, pages={1205-1205} }