Sixth European Conference on Speech Communication and Technology
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.
Full Paper (PDF) Gnu-Zipped Postscript
Bibliographic reference. Altincay, Hakan / Demirekler, Mübeccel (1999): "On the use of supra model information from multiple classifiers for robust speaker identification", In EUROSPEECH'99, 971-974.