A Parse-based Framework for Coupled Rhythm Quantization and Score Structuring - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2019

A Parse-based Framework for Coupled Rhythm Quantization and Score Structuring

Abstract

We present a formal language-based framework for MIDI-to-score transcription, the problem of converting a sequence of symbolic musical events with arbitrary timestamps into a structured music score. The framework aims at solving in one pass the two subproblems of rhythm quantization and score production. It relies, throughout the process, on an apriori hierarchical model of scores given by generative grammars. We show that this coupled approach helps to make relevant and interrelated decisions, and we present an algorithm computing transcription solutions optimal with respect to both the fitness of the quantization to the input, and a measure of complexity of music notation.
Fichier principal
Vignette du fichier
springer12.pdf (492.73 Ko) Télécharger le fichier
MCM-qparse-slides.pdf (4.83 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Presentation

Dates and versions

hal-01988990 , version 1 (22-01-2019)
hal-01988990 , version 2 (18-03-2019)

Identifiers

Cite

Francesco Foscarin, Florent Jacquemard, Philippe Rigaux, Masahiko Sakai. A Parse-based Framework for Coupled Rhythm Quantization and Score Structuring. MCM 2019 - Mathematics and Computation in Music, Jun 2019, Madrid, Spain. ⟨10.1007/978-3-030-21392-3_20⟩. ⟨hal-01988990v2⟩
381 View
483 Download

Altmetric

Share

Gmail Facebook X LinkedIn More