Sixth European Conference on Speech Communication and Technology
(EUROSPEECH'99)

Budapest, Hungary
September 5-9, 1999

Noise-Regularized Adaptive Filtering for Speech Enhancement

Eric A. Wan, Rudolph van der Merwe

Oregon Graduate Institute of Science & Technology, Dept. of Electrical and Computer Engineering, Portland, OR, USA

The removal of noise from speech signals has applications ranging from speech enhancement for cellular communications to front ends for speech recognition systems. In this paper, we present a new nonlinear time-domain method called NoiseRegularized Adaptive Filtering.The approach is based on minimum mean-squared estimation using a modified cost function and allows designing both linear and nonlinear filters using only the observed noisy speech.


Full Paper (PDF)   Gnu-Zipped Postscript

Bibliographic reference.  Wan, Eric A. / Merwe, Rudolph van der (1999): "Noise-regularized adaptive filtering for speech enhancement", In EUROSPEECH'99, 2643-2646.