Paper year
2025
Paper dossier
Symbolic music structure analysis with graph representations and changepoint detection methods
Detail viewSimilarity handoff
Review source metadata, abstract, authors, topics, and local similarity context before moving into explanation and ranking views.
Citations
0
Authors
0
Topic labels
0
Source readout
Source and corpus status
Venue
Unknown venue
Source slug
unknown
Corpus placement
Controlled edge slice
Similarity rows
Not available yet
Ranking readout
Where this paper lands in the current run
Ranking details could not be loaded (API 503).
Abstract
Music Structure Analysis (MSA), particularly symbolic music boundary detection, is crucial for understanding and creating music, yet segmenting music structure at various hierarchical levels remains an open challenge. In this work, we propose three methods for symbolic music boundary detection: Norm, an adapted feature-based approach, and two novel graph-based algorithms, G-PELT and G-Window. Our graph representations offer a powerful way to encode symbolic music, enabling effective structure analysis without explicit feature extraction. We conducted an extensive ablation study using three public datasets, Schubert Winterreise (SWD), Beethoven Piano Sonatas (BPS) and Essen Folk Dataset, which feature diverse musical forms and instrumentation. This allowed us to compare the methods, optimize their parameters for different music styles, and evaluate performance across low, mid, and high structural levels. Our findings demonstrate that our graph-based approaches are highly effective; for instance, the online and unsupervised G-PELT method achieved an F1-score of 0.5640 with a 1-bar tolerance on the SWD dataset. We further illustrate how algorithm parameters can be adjusted to target specific structural granularities. To promote reproducibility and usability, we have integrated the best-performing methods and their optimal parameters for each structural level into musicaiz, an open-source Python package. We anticipate these methods will benefit various Music Information Retrieval (MIR) tasks, including structure-aware music generation, classification, and key change detection.
Authors
No authors available.
Neighborhood labels
Topics
0 labels
Topic labels are imported metadata and can be noisy; use them as coarse navigation hints, not authoritative classifications.
Neighbor surface
Similar papers
Similar papers use a separately configured neighbor embedding; it may differ from the embedding version used by the current ranked run.
No embedding-backed neighbors available for this paper/version yet.
Next handoff
Best next moves from here
01
Check recommendation families
Use Recommended to see whether this paper behaves like an emerging or undercited signal in the current ranked feed, or how it appears on the bridge preview / diagnostics view.
02
Inspect nearby topics
Use Trends to understand whether its attached labels are heating up or cooling down inside the curated corpus.
03
Cross-check evaluation baselines
Use Evaluation to compare the dossier readout against citation and recency baselines for the same resolved family run.