Tokenization of MIDI Sequences for Transcription - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Tokenization of MIDI Sequences for Transcription

Yosuke Amagasu
  • Fonction : Auteur
  • PersonId : 1352285
Masahiko Sakai
  • Fonction : Auteur
  • PersonId : 861357

Résumé

There generally exists no simple one-to-one relationship between the events of a MIDI sequence, such as note-on and note-off messages, and the corresponding music notation elements, such as notes, rests, chords, and ornaments. We propose a method for building a formal correspondence between them through a notion of tokens in an input MIDI event sequence and an effective tokenization approach based on a hierarchical representation of music scores. Our tokenization procedure is integrated with an algorithm for music transcription based on parsing wrt a weighted tree grammar. Its effectiveness is shown on examples.

Domaines

Son [cs.SD]
Fichier principal
Vignette du fichier
main.pdf (579.43 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04458252 , version 1 (14-02-2024)

Licence

Paternité

Identifiants

  • HAL Id : hal-04458252 , version 1

Citer

Yosuke Amagasu, Florent Jacquemard, Masahiko Sakai. Tokenization of MIDI Sequences for Transcription. 9th International Conference on Technologies for Music Notation and Representation (TENOR 2024), Apr 2024, Zurich, Switzerland. ⟨hal-04458252⟩
117 Consultations
90 Téléchargements

Partager

Gmail Facebook X LinkedIn More