5th International Conference on Spoken Language Processing

Sydney, Australia
November 30 - December 4, 1998

Wavelet Transform-based Speech Enhancement

Eliathamby Ambikairajah (1), Graham Tattersall (2), Andrew Davis (3)

(1) Athlone Institute of Technology, Ireland
(2) University of East Anglia, UK
(3) BT Laboratories, UK

This paper describes a speech enhancement system using a novel combination of a Fast Wavelet Transform structure, together with "Wiener filtering" in the wavelet domain. The specific application of interest is the enhancement of speech when a cellular phone is used within a moving vehicle. Subjective tests carried out using speech with additive vehicle noise at a signal-to-noise ratio of 10 dB indicate that the Wavelet transform-based Wiener filtering approach works well. In particular, the technique was compared to several other common enhancement methods such as thresholding applied in the wavelet domain, FFT-based Wiener filtering, and spectral subtraction, and was found to outperform these other techniques.

Full Paper

Bibliographic reference.  Ambikairajah, Eliathamby / Tattersall, Graham / Davis, Andrew (1998): "Wavelet transform-based speech enhancement", In ICSLP-1998, paper 0140.