# Expressive Music Data Processing and Generation

arXiv: https://arxiv.org/abs/2503.11896 · HTML: https://mlsanity.com/paper/2503.11896/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 14 Mar 2025.

## Builds on (most cited first, 8 of 8)

- [SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient](https://mlsanity.com/paper/1609.05473/) (2016)
- [A Comprehensive Survey on Deep Music Generation: Multi-level Representations, Algorithms, Evaluations, and Future Directions](https://mlsanity.com/paper/2011.06801/) (2020)
- [Deep Learning Techniques for Music Generation -- A Survey](https://mlsanity.com/paper/1709.01620/) (2017)
- [Deep Music Analogy Via Latent Representation Disentanglement](https://mlsanity.com/paper/1906.03626/) (2019)
- [Multitrack Music Transformer](https://mlsanity.com/paper/2207.06983/) (2022)
- [AI Methods in Algorithmic Composition: A Comprehensive Survey](https://mlsanity.com/paper/1402.0585/) (2014)
- [Deep Music Information Dynamics](https://mlsanity.com/paper/2102.01133/) (2021)
- [Expressive MIDI-format Piano Performance Generation](https://mlsanity.com/paper/2408.00900/) (2024)

## Abstract (arXiv)

Musical expressivity and coherence are indispensable in music composition and performance, while often neglected in modern AI generative models. In this work, we introduce a listening-based data-processing technique that captures the expressivity in musical performance. This technique derived from Weber's law reflects the human perceptual truth of listening and preserves musical subtlety and expressivity in the training input. To facilitate musical coherence, we model the output interdependencies among multiple arguments in the music data such as pitch, duration, velocity, etc. in the neural networks based on the probabilistic chain rule. In practice, we decompose the multi-output sequential model into single-output submodels and condition previously sampled outputs on the subsequent submodels to induce conditional distributions. Finally, to select eligible sequences from all generations, a tentative measure based on the output entropy was proposed. The entropy sequence is set as a criterion to select predictable and stable generations, which is further studied under the context of informational aesthetic measures to quantify musical pleasure and information gain along the music tendency.