# To catch a chorus, verse, intro, or anything else: Analyzing a song with structural functions

arXiv: https://arxiv.org/abs/2205.14700 · HTML: https://mlsanity.com/paper/2205.14700/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 May 2022.

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

- [MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization](https://mlsanity.com/paper/2501.01108/) (2025)
- [StemGen: A music generation model that listens](https://mlsanity.com/paper/2312.08723/) (2023)
- [Multitrack Music Transcription with a Time-Frequency Perceiver](https://mlsanity.com/paper/2306.10785/) (2023)
- [Jointist: Joint Learning for Multi-instrument Transcription and Its Applications](https://mlsanity.com/paper/2206.10805/) (2022)
- [Cracking Double-Blind Review: Authorship Attribution with Deep Learning](https://mlsanity.com/paper/2211.07467/) (2022)
- [Jointist: Simultaneous Improvement of Multi-instrument Transcription and Music Source Separation via Joint Training](https://mlsanity.com/paper/2302.00286/) (2023)
- [Self-Similarity-Based and Novelty-based loss for music structure analysis](https://mlsanity.com/paper/2309.02243/) (2023)
- [Scaling Up Music Information Retrieval Training with Semi-Supervised Learning](https://mlsanity.com/paper/2310.01353/) (2023)
- [Do Foundational Audio Encoders Understand Music Structure?](https://mlsanity.com/paper/2512.17209/) (2025)
- [CHORDONOMICON: A Dataset of 666,000 Songs and their Chord Progressions](https://mlsanity.com/paper/2410.22046/) (2024)
- [Barwise Section Boundary Detection in Symbolic Music Using Convolutional Neural Networks](https://mlsanity.com/paper/2509.16566/) (2025)

## Abstract (arXiv)

Conventional music structure analysis algorithms aim to divide a song into segments and to group them with abstract labels (e.g., 'A', 'B', and 'C'). However, explicitly identifying the function of each segment (e.g., 'verse' or 'chorus') is rarely attempted, but has many applications. We introduce a multi-task deep learning framework to model these structural semantic labels directly from audio by estimating "verseness," "chorusness," and so forth, as a function of time. We propose a 7-class taxonomy (i.e., intro, verse, chorus, bridge, outro, instrumental, and silence) and provide rules to consolidate annotations from four disparate datasets. We also propose to use a spectral-temporal Transformer-based model, called SpecTNT, which can be trained with an additional connectionist temporal localization (CTL) loss. In cross-dataset evaluations using four public datasets, we demonstrate the effectiveness of the SpecTNT model and CTL loss, and obtain strong results overall: the proposed system outperforms state-of-the-art chorus-detection and boundary-detection methods at detecting choruses and boundaries, respectively.