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.
Type de document :
Communication dans un congrès
Proc. Eur. Conf. Sig. Proces. (EUSIPCO), Aug 2008, Lausanne, Switzerland. 2008, 〈http://www.eurasip.org/Proceedings/Eusipco/Eusipco2008/papers/1569102202.pdf〉
Liste complète des métadonnées

Littérature citée [16 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00452620
Contributeur : Valentin Emiya <>
Soumis le : mardi 2 février 2010 - 17:04:00
Dernière modification le : jeudi 11 janvier 2018 - 06:23:38
Document(s) archivé(s) le : vendredi 18 juin 2010 - 18:27:05

Fichier

080825_Eusipco_emiya_final.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

  • HAL Id : inria-00452620, version 1

Citation

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. 2008, 〈http://www.eurasip.org/Proceedings/Eusipco/Eusipco2008/papers/1569102202.pdf〉. 〈inria-00452620〉

Partager

Métriques

Consultations de la notice

318

Téléchargements de fichiers

268