# Generating Music with a Self-Correcting Non-Chronological Autoregressive Model

arXiv: https://arxiv.org/abs/2008.08927 · HTML: https://mlsanity.com/paper/2008.08927/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Aug 2020.

## Built on by (most cited first, 5 of 5)

- [Variable-Length Music Score Infilling via XLNet and Musically Specialized Positional Encoding](https://mlsanity.com/paper/2108.05064/) (2021)
- [A Comprehensive Survey for Evaluation Methodologies of AI-Generated Music](https://mlsanity.com/paper/2308.13736/) (2023)
- [A Survey of Music Generation in the Context of Interaction](https://mlsanity.com/paper/2402.15294/) (2024)
- [Music Proofreading with RefinPaint: Where and How to Modify Compositions given Context](https://mlsanity.com/paper/2407.09099/) (2024)
- [Generating Music with Structure Using Self-Similarity as Attention](https://mlsanity.com/paper/2406.15647/) (2024)

## Abstract (arXiv)

We describe a novel approach for generating music using a self-correcting, non-chronological, autoregressive model. We represent music as a sequence of edit events, each of which denotes either the addition or removal of a note---even a note previously generated by the model. During inference, we generate one edit event at a time using direct ancestral sampling. Our approach allows the model to fix previous mistakes such as incorrectly sampled notes and prevent accumulation of errors which autoregressive models are prone to have. Another benefit is a finer, note-by-note control during human and AI collaborative composition. We show through quantitative metrics and human survey evaluation that our approach generates better results than orderless NADE and Gibbs sampling approaches.