Automatic Estimation of Harmonic Tension by Distributed Representation of Chords

Abstract

The buildup and release of a sense of tension is one of the most essential aspects of the process of listening to music. A veridical computational model of perceived musical tension would be an important ingredient for many music informatics applications [27]. The present paper presents a new approach to modelling harmonic tension based on a distributed representation of chords. The starting hypothesis is that harmonic tension as perceived by human listeners is related, among other things, to the expectedness of harmonic units (chords) in their local harmonic context. We train a word2vec-type neural network to learn a vector space that captures contextual similarity and expectedness, and define a quantitative measure of harmonic tension on top of this. To assess the veridicality of the model, we compare its outputs on a number of welldefined chord classes and cadential contexts to results from pertinent empirical studies in music psychology. Statistical analysis shows that the model's predictions conform very well with empirical evidence obtained from human listeners.

Reinforcement Learning Jazz Improvisation: When Music Meets Game Theory

“…However, future models may still benefit from establishing a cutoff (possibly gradual based on how long ago a note was played) of remembering notes and relevant payoffs. Such quantitative gradual memory-based models have been used to model harmonic tension via weighting functions and could be applied to a mathematical game [34]. It should also be taken into account that jazz musicians and improvisers tend to have stronger auditory working memory than non-musicians and even other musicians [8,35,36].…”