8th European Conference on Speech Communication and Technology

Geneva, Switzerland
September 1-4, 2003


Improved Kalman Filter-Based Speech Enhancement

Jianqiang Wei, Limin Du, Zhaoli Yan, Hui Zeng

Chinese Academy of Sciences, China

In this paper, a Kalman filter-based speech enhancement algorithm with some improvements of previous work is presented. A new technique based on spectral subtraction is used for separation speech and noise characteristics from noisy speech and for the computation of speech and noise autoregressive (AR) parameters. In order to obtain a Kalman filter output with high audible quality, a perceptual post-filter is placed at the output of the Kalman filter to smooth the enhanced speech spectra. Experiments indicate that this newly proposed method works well.

Full Paper

Bibliographic reference.  Wei, Jianqiang / Du, Limin / Yan, Zhaoli / Zeng, Hui (2003): "Improved kalman filter-based speech enhancement", In EUROSPEECH-2003, 549-552.