In this paper, we propose a text-independent speaker identification (SI) scheme under uncertainty. In this scheme, extraction of supra model information about probability distributions in the feature space is proposed. Supra modeling is a model cluster-ing technique which groups the speaker models into model sets where the speakers in these sets have similar properties. The scheme uses the Dempster-Shafer (D-S) theory of evidence to combine the model sets of two classifiers which are thought to provide complementary information about the speaker identity. A dependency analysis of classifiers to be combined is presented and it is shown to be effective in avoiding wrong decisions. Ex-perimental results of the classifier combination system is given at the end of the paper.
Cite as: Altincay, H., Demirekler, M. (1999) On the use of supra model information from multiple classifiers for robust speaker identification. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 971-974, doi: 10.21437/Eurospeech.1999-237
@inproceedings{altincay99_eurospeech, author={Hakan Altincay and Mübeccel Demirekler}, title={{On the use of supra model information from multiple classifiers for robust speaker identification}}, year=1999, booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)}, pages={971--974}, doi={10.21437/Eurospeech.1999-237} }