Skip to Main content Skip to Navigation
New interface
Conference papers

Multipitch estimation by joint modeling of harmonic and transient sounds

Jun Wu 1 Emmanuel Vincent 2 Stanislaw A. Raczynski 1 Takuya Nishimoto 1 Nobutaka Ono 1 Shigeki Sagayama 1 
2 METISS - Speech and sound data modeling and processing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : Multipitch estimation techniques are widely used for music transcription and acquisition of musical data from digital signals. In this paper, we propose a flexible harmonic temporal timbre model to decompose the spectral energy of the signal in the time-frequency domain into individual pitched notes. Each note is modeled with a 2-dimensional Gaussian mixture. Unlike previous approaches, the proposed model is able to represent not only the harmonic partials but also the inharmonic attack of each note. We derive an Expectation-Maximization (EM) algorithm to estimate the parameters of this model and illustrate the higher performance of the proposed algorithm than NMF algorithm and HTC algorithm for the task of multipitch estimation over synthetic and real-world data.
Complete list of metadata
Contributor : Emmanuel Vincent Connect in order to contact the contributor
Submitted on : Friday, February 18, 2011 - 3:54:08 PM
Last modification on : Tuesday, August 2, 2022 - 3:57:10 AM
Long-term archiving on: : Thursday, March 30, 2017 - 7:04:19 AM


Files produced by the author(s)


  • HAL Id : inria-00567175, version 1


Jun Wu, Emmanuel Vincent, Stanislaw A. Raczynski, Takuya Nishimoto, Nobutaka Ono, et al.. Multipitch estimation by joint modeling of harmonic and transient sounds. 2011 IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), May 2011, Prague, Czech Republic. pp.25 - 28. ⟨inria-00567175⟩



Record views


Files downloads