To Catch A Chorus, Verse, Intro, Or Anything Else: Analyzing A Song With Structural Functions

Abstract

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 sy

Stats

• citations20
• S2 citations—
• github stars0
• HF likes0
• heat score9.92
• arxiv keywang2022to

Related papers

• Pitchclass2vec: Symbolic Music Structure Segmentation With Chord Embeddings (2023)0.00
• Supervised Metric Learning For Music Structure Features (2021)0.00
• Segtune: Structured And Fine-grained Control For Song Generation (2025)0.00
• Convolutive Block-matching Segmentation Algorithm With Application To Music Structure Analysis (2022)0.00
• Songprep: A Preprocessing Framework And End-to-end Model For Full-song Structure Parsing And Lyrics Transcription (2025)0.00
• Exploring Single-song Autoencoding Schemes For Audio-based Music Structure Analysis (2021)0.00
• Songformer: Scaling Music Structure Analysis With Heterogeneous Supervision (2025)4.25
• Mesostructures: Beyond Spectrogram Loss In Differentiable Time-frequency Analysis (2023)6.77