Mapping Sounds on Images Using Binaural Spectrograms - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Mapping Sounds on Images Using Binaural Spectrograms

Résumé

We propose a novel method for mapping sound spectrograms onto images and thus enabling alignment between auditory and visual features for subsequent multimodal processing. We suggest a supervised learning approach to this audio-visual fusion problem, on the following grounds. Firstly, we use a Gaussian mixture of locally-linear regressions to learn a mapping from image locations to binaural spectrograms. Secondly, we derive a closed-form expression for the conditional posterior probability of an image location, given both an observed spectrogram, emitted from an unknown source direction, and the mapping parameters that were previously learnt. Prominently, the proposed method is able to deal with completely different spectrograms for training and for alignment. While fixed-length wide-spectrum sounds are used for learning, thus fully and robustly estimating the regression, variable-length sparse-spectrum sounds, e.g., speech, are used for alignment. The proposed method successfully extracts the image location of speech utterances in realistic reverberant-room scenarios.
Fichier principal
Vignette du fichier
Deleforge-EUSIPCO-AV.pdf (501.16 Ko) Télécharger le fichier
Vignette du fichier
VincentIsrael.png (136.79 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Format : Figure, Image
Loading...

Dates et versions

hal-01019287 , version 1 (07-07-2014)

Identifiants

  • HAL Id : hal-01019287 , version 1

Citer

Antoine Deleforge, Vincent Drouard, Laurent Girin, Radu Horaud. Mapping Sounds on Images Using Binaural Spectrograms. EUSIPCO 2014 - 22th European Signal Processing Conference, Sep 2014, Lisbonne, Portugal. pp.2470 - 2474. ⟨hal-01019287⟩
901 Consultations
647 Téléchargements

Partager

Gmail Facebook X LinkedIn More