31.08.2011

Soundtracks datasets for music and emotion

Film soundtrack stimuli for music and emotion studies

Background

One drawback in music and emotion research has been the choice, quality, and amount of musical examples used as stimuli. Too often the previous studies have utilized well-known excerpts of Western classical music, which have been chosen arbitrarily by the researchers. Moreover, the stimuli have mostly been highly typical exemplars of the chosen emotions even if the underlying emotion model does not imply that emotions are structured around specific categories.

Selection film soundtracks as stimulus sets

The datasets we refer to "Soundtracks" are designed to overcome at least some of the above-mentioned problems since they contain not that well known examples (although some could be identified by film aficionados), the selection of the excerpts has been done in terms of dimensional and discrete emotion model (see the paper for details) and evaluated by pilot study and a larger scale study. The soundtracks are short (approx. 15 second) excerpts from film soundtracks. The details of the stimulus selection and evaluation are available in a paper:

  • Eerola, T. & Vuoskoski, J. K. (2011). A comparison of the discrete and dimensional models of emotion in music. Psychology of Music, 39(1), 18-49. [link to full paper]

Release of stimulus sets

The full datasets (audio files, documentation, and behavioural ratings) are provided here in order to share the stimulus materials for academic research. The audio files have been compressed to MP3 files using moderate quality compression.


Proceed to the download form

 

Stimulus set for emotion induction

A subset of the full dataset (described above) is also available. This small set (16 one-minute examples) is intended for induction of emotions by music. 

 

Dataset has been used in the following studies

  • Eerola, T., Lartillot, O., & Toiviainen, P. (2009). Prediction of multidimensional emotional ratings in music from audio using multivariate regression models. In Proceedings of 10th International Conference on Music Information Retrieval (ISMIR 2009), pages 621–626.
  • Vuoskoski, J. K. & Eerola, T. (2011). The role of mood and personality in the perception of emotions represented by music. Cortex, 47(9), 1099-1106. [link to full paper]
  • Vuoskoski, J. K. & Eerola, T. (2011). Measuring music-induced emotion: A comparison of emotion models, personality biases, and intensity of experiences. Musicae Scientiae, 15(2), 159-173. [link to full paper]
  • Punkanen, M., Eerola, T., & Erkkilä, J. (2010). Biased emotional recognition in depression: Perception of emotions in music by depressed patients. Journal of Affective Disorders, 130(1-2), 118-126. [link to full paper]
  • Punkanen, M., Eerola, T., & Erkkilä, J. (2011). Biased emotional preferences in depression: Decreased liking of angry and energetic music by depressed patients. Music and Medicine, 3(2), 114-120. [link to full paper]
  • Laurier, C., Lartillot, O., Eerola, T., & Toiviainen, P. (2009). Exploring relationships between audio features and emotion in music. In Louhivuori, J., Eerola, T., Saarikallio, S., Himberg, T., and Eerola, P.-S., editors, Proceedings of the 7th Triennal Conference of European Society for Cognitive Sciences of Music (ESCOM 2009) Jyväskylä, Finland, pages 260–264, Jyväskylä, Finland. European Society for Cognitive Sciences of Music.
  • Vuoskoski, J. K. & Eerola, T.  (2010). Domain-Specific or Not? The Applicability of Different Emotion Models in the Assessment of Music-Induced Emotions.  In Proceedings of the 10th International Conference on Music Perception and Cognition (ICMPC10) (pp. 196-199).  University of Washington, US.
  • Saari, P., Eerola, T., and Lartillot, O. (2010). Generalizability and simplicity as criteria in feature selection: Application to mood classification in music. IEEE Transactions on Audio, Speech, and Language Processing, 19(6), 1802-1812. [link to full paper]
  •