Communication Dans Un Congrès Année : 2025

Evaluating Interval-based Tokenization for Pitch Representation in Symbolic Music Analysis

Résumé

Symbolic music analysis tasks are often performed by models originally developed for Natural Language Processing, such as Transformers. Such models require the input data to be represented as sequences, which is achieved through a process of tokenization. Tokenization strategies for symbolic music often rely on absolute MIDI values to represent pitch information. However, music research largely promotes the benefit of higher-level representations such as melodic contour and harmonic relations for which pitch intervals turn out to be more expressive than absolute pitches. In this work, we introduce a general framework for building interval-based tokenizations. By evaluating these tokenizations on three music analysis tasks, we show that such interval-based tokenizations improve model performances and facilitate their explainability.
Fichier principal
Vignette du fichier
main.pdf (299) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04877659 , version 1 (09-01-2025)

Identifiants

Citer

Dinh-Viet-Toan Le, Louis Bigo, Mikaela Keller. Evaluating Interval-based Tokenization for Pitch Representation in Symbolic Music Analysis. Artificial Intelligence for Music Workshop at AAAI 2025, Mar 2025, Philadelphia, United States. ⟨hal-04877659⟩
4 Consultations
2 Téléchargements

Altmetric

Partager

More