Analyzing Byte-Pair Encoding on Monophonic and Polyphonic Symbolic Music: A Focus on Musical Phrase Segmentation

Dinh-Viet-Toan Le, Louis Bigo, Mikaela Keller
10/2/2024
cs.IRcs.CLcs.SD

No official code found. Best implementation: dinhviettoanle/musicbpe-mono-poly (2 stars, last commit 2025-01-17).

Abstract

Byte-Pair Encoding (BPE) is an algorithm commonly used in Natural Language Processing to build a vocabulary of subwords, which has been recently applied to symbolic music. Given that symbolic music can differ significantly from text, particularly with polyphony, we investigate how BPE behaves with different types of musical content. This study provides a qualitative analysis of BPE's behavior across various instrumentations and evaluates its impact on a musical phrase segmentation task for both monophonic and polyphonic music. Our findings show that the BPE training process is highly dependent on the instrumentation and that BPE "supertokens" succeed in capturing abstract musical content. In a musical phrase segmentation task, BPE notably improves performance in a polyphonic setting, but enhances performance in monophonic tunes only within a specific range of BPE merges.

View on arXivView PDF

Code Implementations(1)

dinhviettoanle/musicbpe-mono-polyCommunity100%

Repository for "Analyzing Byte-Pair Encoding on Monophonic and Polyphonic Symbolic Music: A Focus on Musical Phrase Segmentation" (NLP4MusA 2024)

20Python, Jupyter NotebookSep 3, 20241 years ago

Similar Papers

From Words to Music: A Study of Subword Tokenization Techniques in Symbolic Music Generation

88% match2023

Byte Pair Encoding for Symbolic Music

84% match2 repos8842023

Large Language Models' Internal Perception of Symbolic Music

78% match2025

Nested Music Transformer: Sequentially Decoding Compound Tokens in Symbolic Music and Audio Generation

78% match1 repo152024

Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Survey

78% match1 repo312024

Musical Phrase Segmentation via Grammatical Induction

77% match2024

Cite this paper

@article{le2024analyzing,
  title  = {Analyzing Byte-Pair Encoding on Monophonic and Polyphonic Symbolic Music: A Focus on Musical Phrase Segmentation},
  author = {Dinh-Viet-Toan Le and Louis Bigo and Mikaela Keller},
  year   = {2024},
  eprint = {2410.01448},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.01448v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.01448.svg)](https://codeofpaper.com/paper/2410.01448)

Discussion