# Musical Composition Style Transfer via Disentangled Timbre Representations

arXiv: https://arxiv.org/abs/1905.13567 · HTML: https://mlsanity.com/paper/1905.13567/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 May 2019.

## Built on by (most cited first, 11 of 11)

- [ReconVAT: A Semi-Supervised Automatic Music Transcription Framework for Low-Resource Real-World Data](https://mlsanity.com/paper/2107.04954/) (2021)
- [DadaGP: A Dataset of Tokenized GuitarPro Songs for Sequence Models](https://mlsanity.com/paper/2107.14653/) (2021)
- [Loop Copilot: Conducting AI Ensembles for Music Generation and Iterative Editing](https://mlsanity.com/paper/2310.12404/) (2023)
- [Is Disentanglement enough? On Latent Representations for Controllable Music Generation](https://mlsanity.com/paper/2108.01450/) (2021)
- [Audio-to-symbolic Arrangement via Cross-modal Music Representation Learning](https://mlsanity.com/paper/2112.15110/) (2021)
- [DisMix: Disentangling Mixtures of Musical Instruments for Source-level Pitch and Timbre Manipulation](https://mlsanity.com/paper/2408.10807/) (2024)
- [Evaluation of Latent Space Disentanglement in the Presence of Interdependent Attributes](https://mlsanity.com/paper/2110.05587/) (2021)
- [Revisiting Your Memory: Reconstruction of Affect-Contextualized Memory via EEG-guided Audiovisual Generation](https://mlsanity.com/paper/2412.05296/) (2024)
- [Can Machines Generate Personalized Music? A Hybrid Favorite-aware Method for User Preference Music Transfer](https://mlsanity.com/paper/2201.08526/) (2022)
- [Music Style Transfer With Diffusion Model](https://mlsanity.com/paper/2404.14771/) (2024)
- [Device-Guided Music Transfer](https://mlsanity.com/paper/2511.17136/) (2025)

## Abstract (arXiv)

Music creation involves not only composing the different parts (e.g., melody, chords) of a musical work but also arranging/selecting the instruments to play the different parts. While the former has received increasing attention, the latter has not been much investigated. This paper presents, to the best of our knowledge, the first deep learning models for rearranging music of arbitrary genres. Specifically, we build encoders and decoders that take a piece of polyphonic musical audio as input and predict as output its musical score. We investigate disentanglement techniques such as adversarial training to separate latent factors that are related to the musical content (pitch) of different parts of the piece, and that are related to the instrumentation (timbre) of the parts per short-time segment. By disentangling pitch and timbre, our models have an idea of how each piece was composed and arranged. Moreover, the models can realize "composition style transfer" by rearranging a musical piece without much affecting its pitch content. We validate the effectiveness of the models by experiments on instrument activity detection and composition style transfer. To facilitate follow-up research, we open source our code at https://github.com/biboamy/instrument-disentangle.