Two nonnegative matrix factorization methods for polyphonic pitch transcription - Archive ouverte HAL Access content directly
Other Publications Year : 2007

Two nonnegative matrix factorization methods for polyphonic pitch transcription

(1) , (2) , (2)
1
2
Nancy Bertin
Roland Badeau

Abstract

Polyphonic pitch transcription consists of estimating the onset time, duration and pitch of each note within a music signal. Adaptive signal models such as Nonnegative Matrix Factorization (NMF) appear well suited to this task, since they can provide a meaningful representation whatever instruments are playing. In this paper, we propose a simple transcription method using minimum residual loudness NMF, harmonic comb-based pitch identification and threshold-based onset/offset detection, and investigate a second method incorporating harmonicity constraints in the NMF model. Both methods are evaluated in the framework of MIREX 2007.
Fichier principal
Vignette du fichier
vincent_MIREX07.pdf (70.71 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Loading...

Dates and versions

inria-00544213 , version 1 (07-12-2010)

Identifiers

  • HAL Id : inria-00544213 , version 1

Cite

Emmanuel Vincent, Nancy Bertin, Roland Badeau. Two nonnegative matrix factorization methods for polyphonic pitch transcription. 2007. ⟨inria-00544213⟩
324 View
376 Download

Share

Gmail Facebook Twitter LinkedIn More