SurpriseNet: Melody Harmonization Conditioning on User-controlled Surprise Contours
This work addresses the problem of generating harmonically varied and user-controlled music for composers or AI music systems, though it is incremental as it builds on existing CVAE methods.
The authors tackled melody harmonization by introducing a user-controllable framework based on surprise contours derived from information theory, achieving chord progressions that match given surprise contours with statistical significance and performance comparable to state-of-the-art models on the Hooktheory dataset.
The surprisingness of a song is an essential and seemingly subjective factor in determining whether the listener likes it. With the help of information theory, it can be described as the transition probability of a music sequence modeled as a Markov chain. In this study, we introduce the concept of deriving entropy variations over time, so that the surprise contour of each chord sequence can be extracted. Based on this, we propose a user-controllable framework that uses a conditional variational autoencoder (CVAE) to harmonize the melody based on the given chord surprise indication. Through explicit conditions, the model can randomly generate various and harmonic chord progressions for a melody, and the Spearman's correlation and p-value significance show that the resulting chord progressions match the given surprise contour quite well. The vanilla CVAE model was evaluated in a basic melody harmonization task (no surprise control) in terms of six objective metrics. The results of experiments on the Hooktheory Lead Sheet Dataset show that our model achieves performance comparable to the state-of-the-art melody harmonization model.