Characterisation of Acoustic Scenes using a Temporally Constrained Shit-Invariant Model - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Characterisation of Acoustic Scenes using a Temporally Constrained Shit-Invariant Model

Résumé

In this paper, we propose a method for modeling and classifying acoustic scenes using temporally-constrained shift-invariant probabilistic latent component analysis (SIPLCA). SIPLCA can be used for extracting time-frequency patches from spectrograms in an unsupervised manner. Component-wise hidden Markov models are incorporated to the SIPLCA formulation for enforcing temporal constraints on the activation of each acoustic component. The time-frequency patches are converted to cepstral coefficients in order to provide a compact representation of acoustic events within a scene. Experiments are made using a corpus of train station recordings, classified into 6 scene classes. Results show that the proposed model is able to model salient events within a scene and outperforms the non-negative matrix factorization algorithm for the same task. In addition, it is demonstrated that the use of temporal constraints can lead to improved performance.
Fichier principal
Vignette du fichier
index.pdf (158.53 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01126770 , version 1 (09-03-2015)

Identifiants

  • HAL Id : hal-01126770 , version 1

Citer

Emmanouil Benetos, Mathieu Lagrange, Simon Dixon. Characterisation of Acoustic Scenes using a Temporally Constrained Shit-Invariant Model. DAFx, Sep 2012, York, United Kingdom. ⟨hal-01126770⟩
314 Consultations
253 Téléchargements

Partager

Gmail Facebook X LinkedIn More