Odyssey 2008: The Speaker and Language Recognition Workshop
Stellenbosch, South Africa
This paper describes a new feature vector classification method for speaker identification. Purpose of this paper is constructing robust speaker models which only use meaningful feature vectors and discard confusing feature vectors. To construct robust speaker model, proposed method classifies feature vectors using log-likelihood estimation. Experimental results, with various segments ranging from 0.5 to 5s, showed that our method outperforms previous method.
Bibliographic reference. Yoon, Sang-min / Park, Kyung-mi / Bae, Jae-Hyun / Oh, Yung-hwan (2008): "Feature vector classification by threshold for speaker identification", In Odyssey-2008, paper 006.