DocumentCode :
3193868
Title :
A new group delay-based feature for robust speech recognition
Author :
Loweimi, Erfan ; Ahadi, Seyed Mohammad
Author_Institution :
Speech Processing Research Laboratory, Electrical Engineering Department, Amirkabir University of Technology, Hafez Ave., Tehran 15914, Iran
fYear :
2011
fDate :
11-15 July 2011
Firstpage :
1
Lastpage :
5
Abstract :
In this paper we present a novel feature extraction algorithm based on group delay function for robust speech recognition. The modified group delay function (MODGDF) is the main feature extraction method based on group delay function, generally used for robust speech recognition. The recognition tests indicate this feature does not provide notably better results in the presence of additive noise in comparison with MFCC. In the presence of convolutional noise, the performance of MODGDF is considerably lower than MFCC. The method proposed in this paper is simple and makes more efficient utilization of the high resolution property of GDF. It is formed from three main parts which are signal modeling, GDF computation based on extracted model, and compression. The recognition results obtained over AURORA 2.0 task indicate its superior performance in comparison with MODGDF and MFCC.
Keywords :
Robust speech recognition; compression; group delay function; signal modeling;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multimedia and Expo (ICME), 2011 IEEE International Conference on
Conference_Location :
Barcelona, Spain
ISSN :
1945-7871
Print_ISBN :
978-1-61284-348-3
Electronic_ISBN :
1945-7871
Type :
conf
DOI :
10.1109/ICME.2011.6011884
Filename :
6011884
Link To Document :
بازگشت