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

Dinh-Viet-Toan Le, Louis Bigo, Mikaela Keller


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.
Anthology ID:
2024.nlp4musa-1.12
Volume:
Proceedings of the 3rd Workshop on NLP for Music and Audio (NLP4MusA)
Month:
November
Year:
2024
Address:
Oakland, USA
Editors:
Anna Kruspe, Sergio Oramas, Elena V. Epure, Mohamed Sordo, Benno Weck, SeungHeon Doh, Minz Won, Ilaria Manco, Gabriel Meseguer-Brocal
Venues:
NLP4MusA | WS
SIG:
Publisher:
Association for Computational Lingustics
Note:
Pages:
69–74
Language:
URL:
https://aclanthology.org/2024.nlp4musa-1.12/
DOI:
Bibkey:
Cite (ACL):
Dinh-Viet-Toan Le, Louis Bigo, and Mikaela Keller. 2024. Analyzing Byte-Pair Encoding on Monophonic and Polyphonic Symbolic Music: A Focus on Musical Phrase Segmentation. In Proceedings of the 3rd Workshop on NLP for Music and Audio (NLP4MusA), pages 69–74, Oakland, USA. Association for Computational Lingustics.
Cite (Informal):
Analyzing Byte-Pair Encoding on Monophonic and Polyphonic Symbolic Music: A Focus on Musical Phrase Segmentation (Le et al., NLP4MusA 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.nlp4musa-1.12.pdf