Paper Info
Title
An Efficient Feature Selection Method for Speaker Recognition
Abstract
In this paper, a new feature selection method for speaker recognition is proposed to keep the high quality speech frames for speaker modelling and to remove noisy and corrupted speech frames. In order to obtain robust voice activity detection in variety of acoustic conditions, the spectral subtraction algorithm is adopted to estimate the frame power. An energy based frame selection algorithm is then applied to indicate the speech activity at the frame level. The eigenchannel based GMM-UBM speaker recognition system is used to evaluate this proposed method. The experiments are conducted on the 2006 NIST Speaker Recognition Evaluation core test condition (telephone channel) as well as microphone channel test condition. It demonstrates that this approach can provide an efficient way to select high quality speech frames in the noisy environment for speaker recognition.
Year
DOI
Venue
2008
10.1109/CHINSL.2008.ECP.57
ISCSLP
Keywords
Field
DocType
gmm-ubm speaker recognition system,speaker modelling,robust voice activity detection,speaker recognition,feature extraction,gaussian processes,feature selection,signal to noise ratio,speech,nist,noise measurement,voice activity detection,noise
Pattern recognition,Feature selection,Computer science,Voice activity detection,Selection algorithm,Feature extraction,Speech recognition,Speaker recognition,NIST,Artificial intelligence,Speaker diarisation,Microphone
Conference
ISBN
Citations 
PageRank 
978-1-4244-2943-1
5
0.55
References 
Authors
5
3
Name
Order
Citations
PageRank
Hanwu Sun19814.15
Bin Ma260047.26
Haizhou Li33678334.61