Analyzing Byte-Pair Encoding on Monophonic and Polyphonic Symbolic Music: A Focus on Musical Phrase Segmentation - Archive ouverte HAL
Communication Dans Un Congrès Année : 2024

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

Résumé

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.
Fichier non déposé

Dates et versions

hal-04710532 , version 1 (26-09-2024)

Identifiants

  • HAL Id : hal-04710532 , version 1

Citer

Dinh-Viet-Toan Le, Louis Bigo, Mikaela Keller. Analyzing Byte-Pair Encoding on Monophonic and Polyphonic Symbolic Music: A Focus on Musical Phrase Segmentation. 3rd Workshop on NLP for Music and Audio (NLP4MusA), Nov 2024, San Francisco, United States. ⟨hal-04710532⟩
23 Consultations
0 Téléchargements

Partager

More