Title :

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

Author(s) :

Le, Dinh-Viet-Toan [Auteur]
Université de Lille
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Algomus
Machine Learning in Information Networks [MAGNET]
Bigo, Louis [Auteur]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Studio de Création et de Recherche en Informatique et Musique Électroacoustique [SCRIME]
Keller, Mikaela [Auteur]
Université de Lille
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Machine Learning in Information Networks [MAGNET]

Conference title :

3rd Workshop on NLP for Music and Audio (NLP4MusA)

City :

San Francisco

Country :

Etats-Unis d'Amérique

Start date of the conference :

2024-11-15

English keyword(s) :

Music Information Retrieval
Natural language Processing
Symbolic Music Analysis
Deep Learning

HAL domain(s) :

Informatique [cs]

English abstract : [en]

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 ...
Show more >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.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL