Evaluating Interval-based Tokenization for Pitch Representation in Symbolic Music Analysis
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| 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 |