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

TL;DR

This paper introduces a flexible interval-based tokenization framework for symbolic music analysis, demonstrating that such representations enhance model performance and interpretability across multiple tasks.

Contribution

The work presents a novel, general approach to interval-based tokenization, moving beyond absolute pitch representations in symbolic music analysis.

Findings

Interval-based tokenizations improve model accuracy.

They enhance the explainability of music analysis models.

The framework is applicable across various music analysis tasks.

Abstract

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.