Speech Emotion Recognition Based on SVM and ANN

Abstract—Speech emotion recognition mainly includes emotion feature extraction, feature reduction and speech emotion recognition model. This paper chooses valid emotional features and extracts the statistical values of the emotional features. Speech emotion recognition model are constructed respectively based on SVM and ANN and the recognition effect of feature reduction respectively on two types of models are compared. The experimental results show that, based on emotion features which is extracted by CASIA emotion corpus, feature reduction can improve recognition accuracy and the recognition effect of speech recognition model based on SVM is better than ANN.

[1]  Peng Song,et al.  Cross-corpus speech emotion recognition based on transfer non-negative matrix factorization , 2016, Speech Commun..

[2]  Masato Akagi,et al.  Optimizing Fuzzy Inference Systems for Improving Speech Emotion Recognition , 2016, AISI.

[3]  Zied Lachiri,et al.  Multi-class SVM for stressed speech recognition , 2016, 2016 2nd International Conference on Advanced Technologies for Signal and Image Processing (ATSIP).

[4]  Tao Jianhua.  Bimodal emotion recognition based on adaptive weights , 2008 .

[5]  Cai Lianhong,et al.  Speech emotion recognition using acoustic features , 2006 .

[6]  Björn W. Schuller,et al.  Emotion in the singing voice—a deeperlook at acoustic features in the light ofautomatic classification , 2015, EURASIP J. Audio Speech Music. Process..

[7]  Björn W. Schuller,et al.  Hidden Markov model-based speech emotion recognition , 2003, 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698).

[8]  Björn W. Schuller,et al.  Timing levels in segment-based speech emotion recognition , 2006, INTERSPEECH.

[9]  Han Wen.  Review on Speech Emotion Recognition , 2014 .

[10]  Monji Kherallah,et al.  Offline Arabic Handwritten recognition system with dropout applied in Deep networks based-SVMs , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[11]  Y. X. Zou,et al.  An experimental study of speech emotion recognition based on deep convolutional neural networks , 2015, 2015 International Conference on Affective Computing and Intelligent Interaction (ACII).

[12]  Yang Yong,et al.  Speech emotion recognition based on MFCC , 2008 .

[13]  Erik Marchi,et al.  Real-time robust recognition of speakers' emotions and characteristics on mobile platforms , 2015, 2015 International Conference on Affective Computing and Intelligent Interaction (ACII).

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

[15]  Björn W. Schuller,et al.  The Geneva Minimalistic Acoustic Parameter Set (GeMAPS) for Voice Research and Affective Computing , 2016, IEEE Transactions on Affective Computing.