Share Email Print

Proceedings Paper

Comparison of wavelet- and FFT-based single-channel speech signal noise reduction techniques
Author(s): Ningping Fan; Radu V. Balan; Justinian Rosca
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

This paper compares wavelet and short time Fourier transform based techniques for single channel speech signal noise reduction. Despite success of wavelet denoising of images, it has not yet been widely used for removal of noise in speech signals. We explored how to extend this technique to speech denoising, and discovered some problems in this endeavor. Experimental comparison with large amount test data has been performed. Our results have shown that although the Fourier domain methods still has the superiority, wavelet based alternatives can be very close, and enormous different configurations can still be tried out for possible better solutions.

Paper Details

Date Published: 1 November 2004
PDF: 12 pages
Proc. SPIE 5607, Wavelet Applications in Industrial Processing II, (1 November 2004); doi: 10.1117/12.574050
Show Author Affiliations
Ningping Fan, Siemens Corporate Research, Inc. (United States)
Radu V. Balan, Siemens Corporate Research, Inc. (United States)
Justinian Rosca, Siemens Corporate Research, Inc. (United States)

Published in SPIE Proceedings Vol. 5607:
Wavelet Applications in Industrial Processing II
Frederic Truchetet; Olivier Laligant, Editor(s)

© SPIE. Terms of Use
Back to Top