Abstract
Training datasets containing spontaneous emotional speech are often imperfect due the ambiguities and difficulties of labeling such data by human observers. In this paper, we present a Random Sampling Consensus (RANSAC) based training approach for the problem of emotion recognition from spontaneous speech recordings. Our motivation is to insert a data cleaning process to the training phase of the Hidden Markov Models (HMMs) for the purpose of removing some suspicious instances of labels that may exist in the training dataset. Our experiments using HMMs with Mel Frequency Cepstral Coefficients (MFCC) and Line Spectral Frequency (LSF) features indicate that utilization of RANSAC in the training phase provides an improvement in the unweighted recall rates on the test set. Experimental studies performed over the FAU Aibo Emotion Corpus demonstrate that decision fusion configurations with LSF and MFCC based classifiers provide further significant performance improvements.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Angelova, A., Abu-Mostafa, Y., Perona, P.: Pruning training sets for learning of object categories. In: Proc. Int. Conf. on Computer Vision and Pattern Recognition, CVPR (2005)
Barandela, R., Gasca, E.: Decontamination of training samples for supervised pattern recognition methods. In: Amin, A., Pudil, P., Ferri, F., Iñesta, J.M. (eds.) SPR 2000 and SSPR 2000. LNCS, vol. 1876, pp. 621–630. Springer, Heidelberg (2000)
Ben-Gal, I.: Outlier Detection, Data Mining and Knowledge Discovery Handbook: A Complete Guide for Practitioners and Researchers. Kluwer Academic Publishers, Dordrecht (2005)
Breiman, L.: Bagging predictors. Machine Learning 24, 123–140 (1996)
Dietterich, T.G.: Approximate statistical tests for comparing supervised classification learning algorithms. Neural Computation 7, 1895–1924 (1998)
Erzin, E., Yemez, Y., Tekalp, A.M.: Multimodal speaker identification using an adaptive classifier cascade based on modality realiability. IEEE Transactions on Multimedia 7(5), 840–852 (2005)
Fischler, M.A., Bolles, R.C.: Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Graphics and Image Processing 24 (1981)
Gu, B., Hu, F., Liu, H.: Sampling and its applications in data mining: A survey. Tech. Rep. School of Computing, National University of Singapore (2000)
Guyon, I., Matin, N., Vapnik, V.: Discovering informative patterns and data cleaning. In: Workshop on Knowledge Discovery in Databases (1994)
Itakura, F.: Line spectrum representation of linear predictive coefficients of speech signals. Journal of the Acoustical Society of America 57(1), S35 (1975)
Kuncheva, L.I.: Combining Pattern Classifiers. John Wiley and Sons, Chichester (2004)
Kwon, O., Chan, K., Hao, J., Lee, T.: Emotion recognition by speech signals. In: Proc. of Eurospeech 2003, Geneva (September 2003)
Lee, C.M., Narayanan, S.S.: Toward detecting emotions in spoken dialogs. Journal 13, 293–303 (2005)
Lee, C.M., Yildirim, S., Bulut, M., Kazemzadeh, A., Busso, C., Deng, Z., Lee, S., Narayanan, S.: Emotion recognition based on phoneme classes. In: Proc. ICSLP 2004, pp. 889–892 (2004)
Morris, R.W., Clements, M.A.: Modification of formants in the line spectrum domain. IEEE Signal Processing Letters 9(1), 19–21 (2002)
Olken, F.: Random Sampling from Databases. Ph. D. Thesis, Department of Computer Science, University of California, Berkeley (1993)
Ratsch, G., Onada, T., Muller, K.: Regularizing adaboost. Advances in Neural Information Processing Systems 11, 564–570 (2000)
Schuller, B., Rigoll, G., Lang, M.: Hidden markov model based speech emotion recognition. In: Proc. Int. Conf. Acoustics, Speech and Signal Processing, ICASSP (2003)
Schuller, B., Steidl, S., Batliner, A.: The interspeech 2009 emotion challenge. In: Interspeech (2009), ISCA. Brighton, UK (2009)
Seppi, D., Batliner, A., Schuller, B., Steidl, S., Vogt, T., Wagner, J., Devillers, L., Vidrascu, L., Amir, N., Aharonson, V.: Patterns, prototypes, performance: Classifying emotional user states. In: Interspeech (2008) ISCA (2008)
Sonka, M., Hlavac, V., Boyle, R.: Image Processing, Analysis and Machine Vision. Thomson (2008)
Wang, S., Dash, M., Chia, L., Xu, M.: Efficient sampling of training set in large and noisy multimedia data. ACM Transactions on Multimedia Computing, Communications and Applications 3 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bozkurt, E., Erzin, E., Erdem, Ç.E., Erdem, A.T. (2011). RANSAC-Based Training Data Selection on Spectral Features for Emotion Recognition from Spontaneous Speech. In: Esposito, A., Vinciarelli, A., Vicsi, K., Pelachaud, C., Nijholt, A. (eds) Analysis of Verbal and Nonverbal Communication and Enactment. The Processing Issues. Lecture Notes in Computer Science, vol 6800. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-25775-9_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-25775-9_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-25774-2
Online ISBN: 978-3-642-25775-9
eBook Packages: Computer ScienceComputer Science (R0)