Multiple pitch transcription using DBN-based musicological models - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2010

Multiple pitch transcription using DBN-based musicological models

Abstract

We propose a novel approach to solve the problem of estimating pitches of notes present in an audio signal. We have developed a probabilistically rigorous model that takes into account temporal dependencies between musical notes and between the underlying chords, as well as the instantaneous dependencies between chords, notes and the observed note saliences. We investigated its modeling ability by measuring the cross-entropy with symbolic (MIDI) data and then proceed to observe the model's performance in multiple pitch estimation of audio data.
Fichier principal
Vignette du fichier
raczynski_ISMIR10.pdf (524.17 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Loading...

Dates and versions

inria-00544064 , version 1 (07-12-2010)

Identifiers

  • HAL Id : inria-00544064 , version 1

Cite

Stanislaw A. Raczynski, Emmanuel Vincent, Frédéric Bimbot, Shigeki Sagayama. Multiple pitch transcription using DBN-based musicological models. 2010 Int. Society for Music Information Retrieval Conf. (ISMIR), Aug 2010, Utrecht, Netherlands. pp.363--368. ⟨inria-00544064⟩
260 View
145 Download

Share

Gmail Facebook X LinkedIn More