We investigate the automatic recognition of emotions in the singing voice and study the worth and role of a variety of\nrelevant acoustic parameters. The data set contains phrases and vocalises sung by eight renowned professional opera\nsingers in ten different emotions and a neutral state. The states are mapped to ternary arousal and valence labels. We\npropose a small set of relevant acoustic features basing on our previous findings on the same data and compare it\nwith a large-scale state-of-the-art feature set for paralinguistics recognition, the baseline feature set of the Interspeech\n2013 Computational Paralinguistics ChallengE (ComParE). A feature importance analysis with respect to classification\naccuracy and correlation of features with the targets is provided in the paper. Results show that the classification\nperformance with both feature sets is similar for arousal, while the ComParE set is superior for valence. Intra singer\nfeature ranking criteria further improve the classification accuracy in a leave-one-singer-out cross validation\nsignificantly.
Loading....