Feature vector classification by threshold for speaker identification

Sang-min Yoon, Kyung-mi Park, Jae-Hyun Bae, Yung-hwan Oh

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.

Cite as: Yoon, S.-m., Park, K.-m., Bae, J.-H., Oh, Y.-h. (2008) Feature vector classification by threshold for speaker identification. Proc. The Speaker and Language Recognition Workshop (Odyssey 2008), paper 06

@inproceedings{yoon08_odyssey,
  author={Sang-min Yoon and Kyung-mi Park and Jae-Hyun Bae and Yung-hwan Oh},
  title={{Feature vector classification by threshold for speaker identification}},
  year=2008,
  booktitle={Proc. The Speaker and Language Recognition Workshop (Odyssey 2008)},
  pages={paper 06}
}