Academic Journals Database
Disseminating quality controlled scientific knowledge

Improvement of minimum tracking in Minimum Statistics noise estimation method

ADD TO MY LIST
 
Author(s): Hassan Farsi

Journal: Signal Processing : An International Journal
ISSN 1985-2339

Volume: 4;
Issue: 1;
Start page: 17;
Date: 2010;
Original page

Keywords: End point Detection | Distributed Speech Recognition | Voice activity detection | Zero Cross Rating | Robust speech recognition | Volume

ABSTRACT
Noise spectrum estimation is a fundamental component of speech enhancement and speech recognition systems. In this paper we propose a new method for minimum tracking in Minimum Statistics (MS) noise estimation method. This noise estimation algorithm is proposed for highly nonstationary noise environments. This was confirmed with formal listening tests which indicated that the proposed noise estimation algorithm when integrated in speech enhancement was preferred over other noise estimation algorithms.
Affiliate Program     

Tango Jona
Tangokurs Rapperswil-Jona