# Generative Melody Composition with Human-in-the-Loop Bayesian Optimization

arXiv: https://arxiv.org/abs/2010.03190 · HTML: https://mlsanity.com/paper/2010.03190/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2020.

## Built on by (most cited first, 6 of 6)

- [A Survey of Human-in-the-loop for Machine Learning](https://mlsanity.com/paper/2108.00941/) (2021)
- [The Ethical Implications of Generative Audio Models: A Systematic Literature Review](https://mlsanity.com/paper/2307.05527/) (2023)
- [EXPObench: Benchmarking Surrogate-based Optimisation Algorithms on Expensive Black-box Functions](https://mlsanity.com/paper/2106.04618/) (2021)
- [IteraTTA: An interface for exploring both text prompts and audio priors in generating music with text-to-audio models](https://mlsanity.com/paper/2307.13005/) (2023)
- [SwipeGANSpace: Swipe-to-Compare Image Generation via Efficient Latent Space Exploration](https://mlsanity.com/paper/2404.19693/) (2024)
- [GimmBO: Interactive Generative Image Model Merging via Bayesian Optimization](https://mlsanity.com/paper/2601.18585/) (2026)

## Abstract (arXiv)

Deep generative models allow even novice composers to generate various melodies by sampling latent vectors. However, finding the desired melody is challenging since the latent space is unintuitive and high-dimensional. In this work, we present an interactive system that supports generative melody composition with human-in-the-loop Bayesian optimization (BO). This system takes a mixed-initiative approach; the system generates candidate melodies to evaluate, and the user evaluates them and provides preferential feedback (i.e., picking the best melody among the candidates) to the system. This process is iteratively performed based on BO techniques until the user finds the desired melody. We conducted a pilot study using our prototype system, suggesting the potential of this approach.