DocumentCode :
1857969
Title :
A syntactic approach to automatic lip feature extraction for speaker identification
Author :
Wark, T. ; Sridharan, S.
Author_Institution :
Queensland Univ. of Technol., Brisbane, Qld., Australia
Volume :
6
fYear :
1998
fDate :
12-15 May 1998
Firstpage :
3693
Abstract :
This paper presents a novel technique for the tracking and extraction of features from lips for the purpose of speaker identification. In noisy or other adverse conditions, identification performance via the speech signal can significantly reduce, hence additional information which can complement the speech signal is of particular interest. In our system, syntactic information is derived from chromatic information in the lip region. A model of the lip contour is formed directly from the syntactic information, with no minimization procedure required to refine estimates. Colour features are then extracted from the lips via profiles taken around the lip contour. Further improvement in lip features is obtained via linear discriminant analysis (LDA). Speaker models are built from the lip features based on the Gaussian mixture model (GMM). Identification experiments are performed on the M2VTS database, with encouraging results
Keywords :
Gaussian processes; edge detection; feature extraction; image colour analysis; image segmentation; speaker recognition; tracking; Gaussian mixture model; M2VTS database; automatic lip feature extraction; chromatic information; colour features; experiments; facial image; facial skin area segmentation; identification performance; linear discriminant analysis; lip contour; noisy conditions; speaker identification; speaker models; speech signal; syntactic approach; syntactic information; Active shape model; Authentication; Data mining; Feature extraction; Laboratories; Linear discriminant analysis; Lips; Signal processing; Skin; Speech processing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on
Conference_Location :
Seattle, WA
ISSN :
1520-6149
Print_ISBN :
0-7803-4428-6
Type :
conf
DOI :
10.1109/ICASSP.1998.679685
Filename :
679685
Link To Document :
بازگشت