Sparse representations for modeling environmental acoustic scenes, application to train stations soundscapes - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Sparse representations for modeling environmental acoustic scenes, application to train stations soundscapes

Résumé

Our daily life happens in a world of dense acoustic environments. This is especially the case in train stations, where soundscapes are usually very complex. In this paper, we will investigate how Non Negative Matrix Factorization methods can be used to obtain a low rank spectrogram approximation, composed of spectral templates that be related to some salients events like footsteps, whistles, etc. We thus assume here that the scene can be characterized by a few salient events that occur several times within the scene. We also assume that even if the acoustic realizations of those events cannot be considered in isolation, those realizations have similar spectro-temporal properties. We here consider 66 recordings made in French train stations, where individual salient events have been manually annotated. We then assess the ability of the methods to extract meaningful components by comparing the activations of those components within the scene to the manually annotated ones. Experiments demonstrate that enforcing sparsity on the activations, i.e. constraining that only a few components is active at a time, has a positive effect.
Fichier principal
Vignette du fichier
hal-00810774.pdf (573.38 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-00810774 , version 1 (23-04-2012)

Identifiants

  • HAL Id : hal-00810774 , version 1

Citer

Benjamin Cauchi, Mathieu Lagrange, Nicolas Misdariis, Arshia Cont. Sparse representations for modeling environmental acoustic scenes, application to train stations soundscapes. Acoustics 2012, Apr 2012, Nantes, France. ⟨hal-00810774⟩
319 Consultations
127 Téléchargements

Partager

Gmail Facebook X LinkedIn More