# What is missing in deep music generation? A study of repetition and structure in popular music

arXiv: https://arxiv.org/abs/2209.00182 · HTML: https://mlsanity.com/paper/2209.00182/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Sep 2022.

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

- [ChatMusician: Understanding and Generating Music Intrinsically with LLM](https://mlsanity.com/paper/2402.16153/) (2024)
- [ComposerX: Multi-Agent Symbolic Music Composition with LLMs](https://mlsanity.com/paper/2404.18081/) (2024)
- [Compose & Embellish: Well-Structured Piano Performance Generation via A Two-Stage Approach](https://mlsanity.com/paper/2209.08212/) (2022)
- [Learning Musical Representations for Music Performance Question Answering](https://mlsanity.com/paper/2502.06710/) (2025)
- [Survey on the Evaluation of Generative Models in Music](https://mlsanity.com/paper/2506.05104/) (2025)
- [SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition](https://mlsanity.com/paper/2402.17645/) (2024)
- [From Words to Music: A Study of Subword Tokenization Techniques in Symbolic Music Generation](https://mlsanity.com/paper/2304.08953/) (2023)
- [F-StrIPE: Fast Structure-Informed Positional Encoding for Symbolic Music Generation](https://mlsanity.com/paper/2502.10491/) (2025)
- [Motif-Centric Representation Learning for Symbolic Music](https://mlsanity.com/paper/2309.10597/) (2023)
- [TOMI: Transforming and Organizing Music Ideas for Multi-Track Compositions with Full-Song Structure](https://mlsanity.com/paper/2506.23094/) (2025)
- [Barwise Section Boundary Detection in Symbolic Music Using Convolutional Neural Networks](https://mlsanity.com/paper/2509.16566/) (2025)

## Abstract (arXiv)

Structure is one of the most essential aspects of music, and music structure is commonly indicated through repetition. However, the nature of repetition and structure in music is still not well understood, especially in the context of music generation, and much remains to be explored with Music Information Retrieval (MIR) techniques. Analyses of two popular music datasets (Chinese and American) illustrate important music construction principles: (1) structure exists at multiple hierarchical levels, (2) songs use repetition and limited vocabulary so that individual songs do not follow general statistics of song collections, (3) structure interacts with rhythm, melody, harmony, and predictability, and (4) over the course of a song, repetition is not random, but follows a general trend as revealed by cross-entropy. These and other findings offer challenges as well as opportunities for deep-learning music generation and suggest new formal music criteria and evaluation methods. Music from recent music generation systems is analyzed and compared to human-composed music in our datasets, often revealing striking differences from a structural perspective.