HAL : inria-00510392, version 1

DOI : 10.1109/TASL.2009.2038819

Voir la fiche détaillée

BibTeX,EndNote,... BibTeX - EndNote - TEI - RefWorks -

IEEE Transactions on Audio, Speech, and Language Processing 18, 6 (2010) 1643-1654

Multipitch estimation of piano sounds using a new probabilistic spectral smoothness principle

Valentin Emiya 1, Roland Badeau 2, Bertrand David 2

(16/08/2010)

A new method for the estimation of multiple concurrent pitches in piano recordings is presented. It addresses the issue of overlapping overtones by modeling the spectral envelope of the overtones of each note with a smooth autoregressive model. For the background noise, a moving-average model is used and the combination of both tends to eliminate harmonic and sub-harmonic erroneous pitch estimations. This leads to a complete generative spectral model for simultaneous piano notes, which also explicitly includes the typical deviation from exact harmonicity in a piano overtone series. The pitch set which maximizes an approximate likelihood is selected from among a restricted number of possible pitch combinations as the one. Tests have been conducted on a large homemade database called MAPS, composed of piano recordings from a real upright piano and from high-quality samples.

1 :	METISS (INRIA - IRISA)
	CNRS : UMR6074 – INRIA – Institut National des Sciences Appliquées (INSA) - Rennes – Université de Rennes 1
2 :	Laboratoire Traitement et Communication de l'Information [Paris] (LTCI)
	Télécom ParisTech – CNRS : UMR5141

Domaine

:

Informatique/Traitement du signal et de l'image Sciences de l'ingénieur/Traitement du signal et de l'image

Mots-clés : Acoustic signal analysis – audio processing – multipitch estimation – piano – transcription – spectral smoothness

inria-00510392, version 1

http://hal.inria.fr/inria-00510392

oai:hal.inria.fr:inria-00510392

Contributeur : Valentin Emiya <>

Soumis le : Mercredi 18 Août 2010, 14:15:21

Dernière modification le : Mardi 7 Décembre 2010, 12:33:10