8th Annual Conference of the International Speech Communication Association

Antwerp, Belgium
August 27-31, 2007

Speaker Verification with Multiple Classifier Fusion Using Bayes Based Confidence Measure

Fernando Huenupán, Nestor Becerra Yoma, Carlos Molina, Claudio Garreton

Universidad de Chile, Chile

A novel framework based on Bayes-based confidence measure (BBCM) for Multiple Classifier System (MCS) fusion is proposed. As shown here, BBCM based MCS combination scheme corresponds to the ordinary Bayes fusion weighted by the reliability of each individual classifier. BBCM provides a formal model for heuristic weighting functions employed elsewhere. When compared with the ordinary Bayesian fusion, the proposed method leads to reductions as high as 20% and 50% in EER and the area below the ROC curve, respectively, in speaker verification.

Full Paper

Bibliographic reference.  Huenupán, Fernando / Yoma, Nestor Becerra / Molina, Carlos / Garreton, Claudio (2007): "Speaker verification with multiple classifier fusion using Bayes based confidence measure", In INTERSPEECH-2007, 2041-2044.