Share Email Print

Proceedings Paper

Robust estimators for speech enhancement in real environments
Author(s): Yuma Sandoval-Ibarra; Victor H. Diaz-Ramirez; Vitaly Kober
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

Common statistical estimators for speech enhancement rely on several assumptions about stationarity of speech signals and noise. These assumptions may not always valid in real-life due to nonstationary characteristics of speech and noise processes. We propose new estimators based on existing estimators by incorporation of computation of rank-order statistics. The proposed estimators are better adapted to non-stationary characteristics of speech signals and noise processes. Through computer simulations we show that the proposed estimators yield a better performance in terms of objective metrics than that of known estimators when speech signals are contaminated with airport, babble, restaurant, and train-station noise.

Paper Details

Date Published: 9 September 2015
PDF: 6 pages
Proc. SPIE 9598, Optics and Photonics for Information Processing IX, 959813 (9 September 2015); doi: 10.1117/12.2188408
Show Author Affiliations
Yuma Sandoval-Ibarra, Ctr. de Investigación y Desarrollo de Tecnología Digital (Mexico)
Victor H. Diaz-Ramirez, Ctr. de Investigación y Desarrollo de Tecnología Digital (Mexico)
Vitaly Kober, Ctr. de Investigación Científica y de Educación Superior de Ensenada B.C. (Mexico)
Chelyabinsk State Univ. (Russian Federation)

Published in SPIE Proceedings Vol. 9598:
Optics and Photonics for Information Processing IX
Abdul A. S. Awwal; Khan M. Iftekharuddin; Mohammad A. Matin; Mireya García Vázquez; Andrés Márquez, Editor(s)

© SPIE. Terms of Use
Back to Top