# SurpriseNet: Melody Harmonization Conditioning on User-controlled Surprise Contours

arXiv: https://arxiv.org/abs/2108.00378 · HTML: https://mlsanity.com/paper/2108.00378/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Aug 2021.

## Built on by (most cited first, 9 of 9)

- [Anticipatory Music Transformer](https://mlsanity.com/paper/2306.08620/) (2023)
- [Melody transcription via generative pre-training](https://mlsanity.com/paper/2212.01884/) (2022)
- [Emotion-Driven Melody Harmonization via Melodic Variation and Functional Representation](https://mlsanity.com/paper/2407.20176/) (2024)
- [Choir Transformer: Generating Polyphonic Music with Relative Attention on Transformer](https://mlsanity.com/paper/2308.02531/) (2023)
- [Emotion-Conditioned Melody Harmonization with Hierarchical Variational Autoencoder](https://mlsanity.com/paper/2306.03718/) (2023)
- [Incorporating Structure and Chord Constraints in Symbolic Transformer-based Melodic Harmonization](https://mlsanity.com/paper/2512.07627/) (2025)
- [Relating Human Perception of Musicality to Prediction in a Predictive Coding Model](https://mlsanity.com/paper/2210.16587/) (2022)
- [MIDI-Draw: Sketching to Control Melody Generation](https://mlsanity.com/paper/2305.11605/) (2023)
- [Pay (Cross) Attention to the Melody: Curriculum Masking for Single-Encoder Melodic Harmonization](https://mlsanity.com/paper/2601.16150/) (2026)

## Abstract (arXiv)

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.