Onset detection by means of transient peak classification in harmonic bands

Axel Roebel (1)

1 Analyse et synthèse sonores [Paris]

The extended abstract describes an onset detection algorithm that is based on a classification of spectral peaks into transient and non-transient peaks and a statistical model of the classification results to prevent detection of random transient peaks due to noise. Compared to the version used for MIREX 2007 this algorithm focuses on the improvment of the detection of onsets of pitched notes.

Mots clés: transient; onset; MIREX; spectral peak; Evaluation

Mots clés: Informatique musicale

Domaines: Acoustique [physics.class-ph]; Traitement du signal et de l'image [eess.SP]; Neurosciences

Axel Roebel. Onset detection by means of transient peak classification in harmonic bands. MIREX/ISMIR, Oct 2009, Kobe, Japan. pp.1-1. ⟨hal-01161234⟩