EMusic is a music corpus that contains 100 experimental music clips and 40 music clips from 8 musical genres. We conducted a crowdsourcing experiment to collect ground truth via ranking the valence and arousal of music clips. We designed smoothed RankSVM (SRSVM) method to predict the ranking of target music clips regarding valence and arousal. Our evaluation has shown that the SRSVM outperforms four other ranking algorithms. We also analyze the distribution of perceived emotion of experimental music against other genres to demonstrate the difference between genres.
Download Link: EMusic Dataset
Papers & Posters:
- J. Fan, K. Tatar. M. Thorogood, and P. Pasquier, “Ranking-based Emotion Recognition for Experimental Music,” Proceedings of the International Symposium on Music Information Retrieval, 2017.