Towards morphological sound description using segmental models

Julien Bloit (1, 2) , Nicolas Rasamimanana (1, 2) , Frédéric Bevilacqua (1, 2)

1 Equipe Interactions musicales temps-réel
2 Analyse et synthèse sonores [Paris]

We present an approach to model the temporal evolution of audio descriptors using Segmental Models (SMs). This method allows to segment a signal as a sequence of primitives, constituted by a set of trajectories defined by the user. This allows one to explicitly model the time duration of primitives, and to take into account the time dependence between successive signal frames, contrary to standard Hidden Markov Models. We applied this approach to a database of violin playing. Various types of glissando and dynamics variations were specifically recorded. Our results shows that our approach using Segmental Models provides a segmentation that can be easily interpreted. Quantitatively, the Segmental Models performed better than standard implementation of Hidden Markow Models.

Mots clés: violon; segmental HMM; morphologie; trajectoire

Mots clés: Informatique musicale

Domaines: Son [cs.SD]; Interface homme-machine [cs.HC]; Musique, musicologie et arts de la scène; Acoustique [physics.class-ph]; Neurosciences; Traitement du signal et de l'image [eess.SP]; Apprentissage [cs.LG]; Intelligence artificielle [cs.AI]; Ingénierie assistée par ordinateur; Multimédia [cs.MM]; Vision par ordinateur et reconnaissance de formes [cs.CV]; Autre [cs.OH]; Traitement du signal et de l'image [eess.SP]

Julien Bloit, Nicolas Rasamimanana, Frédéric Bevilacqua. Towards morphological sound description using segmental models. DAFX, Sep 2009, Milan, Italie, France. pp.1-1. ⟨hal-01161223⟩