INTERSPEECH 2011 12th Annual Conference of the International Speech Communication Association Florence, Italy August 27-31. 2011

RANSAC-Based Training Data Selection for Speaker State Recognition

Elif Bozkurt (1), Engin Erzin (1), Çiğdem Eroğlu Erdem (2), A. Tanju Erdem (3)

(1) Koç Üniversitesi, Turkey
(2) Bahçeşehir Üniversitesi, Turkey
(3) Özyeğin Üniversitesi, Turkey

We present a Random Sampling Consensus (RANSAC) based training approach for the problem of speaker state recognition from spontaneous speech. Our system is trained and tested with the INTERSPEECH 2011 Speaker State Challenge corpora that includes the Intoxication and the Sleepiness Sub-challenges, where each subchallenge defines a two-class classification task. We aim to perform a RANSAC-based training data selection coupled with the Support Vector Machine (SVM) based classification to prune possible outliers, which exist in the training data. Our experimental evaluations indicate that utilization of RANSAC-based training data selection provides 66.32% and 65.38% unweighted average (UA) recall rate on the development and test sets for the Sleepiness Subchallenge, respectively and a slight improvement on the Intoxication Sub-challenge performance.

Full Paper

Bibliographic reference.  Bozkurt, Elif / Erzin, Engin / Erdem, Çiğdem Eroğlu / Erdem, A. Tanju (2011): "RANSAC-based training data selection for speaker state recognition", In INTERSPEECH-2011, 3293-3296.