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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Le, Dinh-Viet-Toan, Bigo, Louis, Keller, Mikaela
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909451711152128
author Le, Dinh-Viet-Toan
Bigo, Louis
Keller, Mikaela
author_facet Le, Dinh-Viet-Toan
Bigo, Louis
Keller, Mikaela
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_04630
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Evaluating Interval-based Tokenization for Pitch Representation in Symbolic Music Analysis
Le, Dinh-Viet-Toan
Bigo, Louis
Keller, Mikaela
Information Retrieval
Sound
Audio and Speech Processing
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.
title Evaluating Interval-based Tokenization for Pitch Representation in Symbolic Music Analysis
topic Information Retrieval
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2501.04630