Automatic transcription of piano music based on HMM tracking of jointly-estimated pitches - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2008

Automatic transcription of piano music based on HMM tracking of jointly-estimated pitches

Abstract

This work deals with the automatic transcription of piano recordings into a MIDI symbolic file. The system consists of subsequent stages of onset detection and multipitch estimation and tracking. The latter is based on a Hidden Markov Model framework, embedding a spectral maximum likelihood method for joint pitch estimation. The complexity issue of joint estimation techniques is solved by selecting subsets of simultaneously played notes within a pre-estimated set of candidates. Tests on a large database and comparisons to state-of-the-art methods show promising results.
Fichier principal
Vignette du fichier
080825_Eusipco_emiya_final.pdf (174.5 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Loading...

Dates and versions

inria-00452620 , version 1 (02-02-2010)

Identifiers

  • HAL Id : inria-00452620 , version 1

Cite

Valentin Emiya, Roland Badeau, Bertrand David. Automatic transcription of piano music based on HMM tracking of jointly-estimated pitches. Proc. Eur. Conf. Sig. Proces. (EUSIPCO), Aug 2008, Lausanne, Switzerland. ⟨inria-00452620⟩
228 View
247 Download

Share

Gmail Facebook Twitter LinkedIn More