Title :
A robust clustering approach to fuzzy Gaussian mixture models for speaker identification
Author :
Tran, Dat ; Wagner, Michael
Author_Institution :
Human-Comput. Commun. Lab., Canberra Univ., ACT, Australia
Abstract :
The Gaussian mixture model (GMM) is a currently used method for speaker recognition. The fuzzy GMM (FGMM) proposed in previous work (D. Tran et al., 1998) is a fuzzy clustering based modification of the GMM. Although both the FGMM and the GMM are capable of achieving high identification accuracy, they have a common disadvantage in the problem of sensitivity to outliers. The paper presents an improvement for the FGMM to handle this problem. Experimental results on 16 speakers using the TI46 database are also reported
Keywords :
Gaussian processes; fuzzy set theory; knowledge based systems; pattern clustering; speaker recognition; FGMM; TI46 database; fuzzy GMM; fuzzy Gaussian mixture models; fuzzy clustering based modification; identification accuracy; outliers; robust clustering approach; speaker identification; speaker recognition; Australia; Automatic speech recognition; Clustering algorithms; Databases; Iterative algorithms; Laboratories; Robustness; Speaker recognition; Speech processing; System testing;
Conference_Titel :
Knowledge-Based Intelligent Information Engineering Systems, 1999. Third International Conference
Conference_Location :
Adelaide, SA
Print_ISBN :
0-7803-5578-4
DOI :
10.1109/KES.1999.820192
