Robust estimators for speech enhancement in real environments

Yuma Sandoval-Ibarra, Victor H. Diaz-Ramirez, Vitaly Kober

Producción científica: Capítulo del libro/informe/acta de congresoContribución a la conferenciarevisión exhaustiva

Resumen

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.

Idioma originalInglés
Título de la publicación alojadaOptics and Photonics for Information Processing IX
EditoresMohammad A. Matin, Abdul A. S. Awwal, Andres Marquez, Mireya Garcia Vazquez, Khan M. Iftekharuddin, Mireya Garcia Vazquez, Khan M. Iftekharuddin, Abdul A. S. Awwal, Mohammad A. Matin, Andres Marquez
EditorialSPIE
ISBN (versión digital)9781628417647, 9781628417647
DOI
EstadoPublicada - 2015
Evento9th Conference of Optics and Photonics for Information Processing - San Diego, Estados Unidos
Duración: 10 ago. 201512 ago. 2015

Serie de la publicación

NombreProceedings of SPIE - The International Society for Optical Engineering
Volumen9598
ISSN (versión impresa)0277-786X
ISSN (versión digital)1996-756X

Conferencia

Conferencia9th Conference of Optics and Photonics for Information Processing
País/TerritorioEstados Unidos
CiudadSan Diego
Período10/08/1512/08/15

Huella

Profundice en los temas de investigación de 'Robust estimators for speech enhancement in real environments'. En conjunto forman una huella única.

Citar esto