论文信息 - RANSAC-Based Training Data Selection for Speaker State Recognition

RANSAC-Based Training Data Selection for Speaker State Recognition

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 Subchallenges, where each sub-challenge 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 Sub-challenge, respectively and a slight improvement on the Intoxication Subchallenge performance. Index Terms: Speaker State Challenge, Intoxication, Sleepiness, RANSAC

A. Tanju Erdem | Engin Erzin | Çigdem Eroglu Erdem | Elif Bozkurt

[1] Min Xu,et al. Efficient sampling of training set in large and noisy multimedia data , 2007, TOMCCAP.

[2] Gunnar Rätsch,et al. Regularizing AdaBoost , 1998, NIPS.

[3] Frank Olken,et al. Random Sampling from Databases , 1993 .

[4] Chih-Jen Lin,et al. LIBSVM: A library for support vector machines , 2011, TIST.

[5] Milan Sonka,et al. Image Processing, Analysis and Machine Vision , 1993, Springer US.

[6] Björn W. Schuller,et al. The INTERSPEECH 2011 Speaker State Challenge , 2011, INTERSPEECH.

[7] Pietro Perona,et al. Pruning training sets for learning of object categories , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[8] Takio Kurita,et al. RANSAC-SVM for large-scale datasets , 2008, 2008 19th International Conference on Pattern Recognition.

[9] Leo Breiman,et al. Bagging Predictors , 1996, Machine Learning.

[10] Eduardo Gasca,et al. Decontamination of Training Samples for Supervised Pattern Recognition Methods , 2000, SSPR/SPR.

[11] N. Mati,et al. Discovering Informative Patterns and Data Cleaning , 1996 .

[12] Robert C. Bolles,et al. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.