# Learning to Traverse Latent Spaces for Musical Score Inpainting

arXiv: https://arxiv.org/abs/1907.01164 · HTML: https://mlsanity.com/paper/1907.01164/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2019.

## Built on by (most cited first, 24 of 24)

- [Anticipatory Music Transformer](https://mlsanity.com/paper/2306.08620/) (2023)
- [The Piano Inpainting Application](https://mlsanity.com/paper/2107.05944/) (2021)
- [The Ethical Implications of Generative Audio Models: A Systematic Literature Review](https://mlsanity.com/paper/2307.05527/) (2023)
- [MusIAC: An extensible generative framework for Music Infilling Applications with multi-level Control](https://mlsanity.com/paper/2202.05528/) (2022)
- [Variable-Length Music Score Infilling via XLNet and Musically Specialized Positional Encoding](https://mlsanity.com/paper/2108.05064/) (2021)
- [BERT-like Pre-training for Symbolic Piano Music Classification Tasks](https://mlsanity.com/paper/2107.05223/) (2021)
- [Survey on the Evaluation of Generative Models in Music](https://mlsanity.com/paper/2506.05104/) (2025)
- [Composer's Assistant: An Interactive Transformer for Multi-Track MIDI Infilling](https://mlsanity.com/paper/2301.12525/) (2023)
- [Exploring XAI for the Arts: Explaining Latent Space in Generative Music](https://mlsanity.com/paper/2308.05496/) (2023)
- [Is Disentanglement enough? On Latent Representations for Controllable Music Generation](https://mlsanity.com/paper/2108.01450/) (2021)
- [Learning long-term music representations via hierarchical contextual constraints](https://mlsanity.com/paper/2202.06180/) (2022)
- [Composer's Assistant 2: Interactive Multi-Track MIDI Infilling with Fine-Grained User Control](https://mlsanity.com/paper/2407.14700/) (2024)
- [Melody Infilling with User-Provided Structural Context](https://mlsanity.com/paper/2210.02829/) (2022)
- [Exploring how a Generative AI interprets music](https://mlsanity.com/paper/2308.00015/) (2023)
- [Exploring Variational Auto-Encoder Architectures, Configurations, and Datasets for Generative Music Explainable AI](https://mlsanity.com/paper/2311.08336/) (2023)
- [Exploring the Needs of Practising Musicians in Co-Creative AI Through Co-Design](https://mlsanity.com/paper/2502.09055/) (2025)
- [A Contextual Latent Space Model: Subsequence Modulation in Melodic Sequence](https://mlsanity.com/paper/2111.11703/) (2021)
- [JAZZVAR: A Dataset of Variations found within Solo Piano Performances of Jazz Standards for Music Overpainting](https://mlsanity.com/paper/2307.09670/) (2023)
- [Adaptable Symbolic Music Infilling with MIDI-RWKV](https://mlsanity.com/paper/2506.13001/) (2025)
- [An Autoethnographic Exploration of XAI in Algorithmic Composition](https://mlsanity.com/paper/2308.06089/) (2023)
- [Hidden Biases in Conditioning Autoregressive Models](https://mlsanity.com/paper/2604.07855/) (2026)
- [DeformTune: A Deformable XAI Music Prototype for Non-Musicians](https://mlsanity.com/paper/2508.00160/) (2025)
- [Pay (Cross) Attention to the Melody: Curriculum Masking for Single-Encoder Melodic Harmonization](https://mlsanity.com/paper/2601.16150/) (2026)
- [MI-MIDI: Mechanistic Interpretability of Text-to-MIDI Generation Models via Probing, Lenses and Steering](https://mlsanity.com/paper/2608.06638/) (2026)

## Abstract (arXiv)

Music Inpainting is the task of filling in missing or lost information in a piece of music. We investigate this task from an interactive music creation perspective. To this end, a novel deep learning-based approach for musical score inpainting is proposed. The designed model takes both past and future musical context into account and is capable of suggesting ways to connect them in a musically meaningful manner. To achieve this, we leverage the representational power of the latent space of a Variational Auto-Encoder and train a Recurrent Neural Network which learns to traverse this latent space conditioned on the past and future musical contexts. Consequently, the designed model is capable of generating several measures of music to connect two musical excerpts. The capabilities and performance of the model are showcased by comparison with competitive baselines using several objective and subjective evaluation methods. The results show that the model generates meaningful inpaintings and can be used in interactive music creation applications. Overall, the method demonstrates the merit of learning complex trajectories in the latent spaces of deep generative models.