musique contemporaine

Ircam - articles scientifiques notice originale

Modeling and segmentation of audio descriptor profiles with Segmental Models

Type

text
 

Genre(s)

article
 

Forme(s)

document numérique
 

Accès sur site

  • Version numérique intégrale de l'article
 

Cette ressource est disponible chez l'organisme suivant : Ircam - Centre Pompidou

Identification

Titre

Modeling and segmentation of audio descriptor profiles with Segmental Models
 

Nom(s)

Bloit, Julien (auteur)
 
Rasamimanana, Nicolas (auteur)
 
Bevilacqua, Frédéric (auteur)
 

Publication

2010
 

Description

Sujet(s)

Hidden Markov Models   Segmental Models   Segmentation   Audio Descriptors   Profiles   Primitives   Music
 

Résumé

We present a method to model sound descriptor temporal profiles using Segmental Models. Unlike standard HMM, such an approach allows for the modeling of fine structures of temporal profiles with a reduced number of states. These states, we called primitives, can be chosen by the user using prior knowledge, and assembled to model symbolic musical elements. In this paper, we describe this general methodology and evaluate it on a dataset made of of violin recording containing crescendo/decrescendo, glissando and sforzando. The results show that, in this context, the segmental model can segment and recognize these different musical elements with a satisfactory level.
 

Note(s)

Article paru dans : Pattern Recognition Letters
 

Localisation

Envoyer la notice

Bookmark and Share 
 

Identifiant OAI

 

Date de la notice

2014-10-31 01:00:00
 

Identifiant portail

 

Contact