Dimensional music emotion recognition by valence-arousal regression

As hot topics in current research, music emotion recognition (MER) have been addressed by different disciplines such as physiology, psychology, musicology, cognitive science, etc. In this paper, music emotions was modeled as continuous variables composed of valence and arousal values (VA values) based on Valence-Arousal model, and MER is formulated as a regression problem. 548 dimensions of music features were extracted and selected. The support vector regression, random forest regression and regression neural networks were adopted to recognize music emotion. Experimental results show that these regression algorithms achieved good regression effect. The optimal R2 statistics of values of VA values are 29.3% and 62.5%, which are achieved respectively by RFR and SVR in Relief feature space.

[1]  Paul A. Bromiley,et al.  Robust and Accurate Shape Model Matching Using Random Forest Regression-Voting , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  M. Thaut,et al.  The Oxford handbook of music psychology , 2011 .

[3]  Saidatul Rahah Hamidi,et al.  Automatic Music Emotion Classification using Artificial Neural Network based on vocal and instrumental Sound Timbres , 2014, J. Comput. Sci..

[4]  J. Sloboda,et al.  Music and emotion: Theory and research , 2001 .

[5]  Nathalie Japkowicz,et al.  Nonlinear Autoassociation Is Not Equivalent to PCA , 2000, Neural Computation.

[6]  Yi-Hsuan Yang,et al.  A Regression Approach to Music Emotion Recognition , 2008, IEEE Transactions on Audio, Speech, and Language Processing.

[7]  Yi-Hsuan Yang,et al.  1000 songs for emotional analysis of music , 2013, CrowdMM '13.

[8]  J. Russell.  A circumplex model of affect. , 1980 .

[9]  R. Thayer.  The biopsychology of mood and arousal , 1989 .

[10]  Jee-Hyong Lee,et al.  An approach of genetic programming for music emotion classification , 2013 .

[11]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.

[12]  Petri Toiviainen,et al.  MIR in Matlab (II): A Toolbox for Musical Feature Extraction from Audio , 2007, ISMIR.

[13]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[14]  Jan Larsen,et al.  Learning Combinations of Multiple Feature Representations for Music Emotion Prediction , 2015, ASM@ACM Multimedia.

[15]  Marko Robnik-Sikonja,et al.  Theoretical and Empirical Analysis of ReliefF and RReliefF , 2003, Machine Learning.