Skip to Main content Skip to Navigation
Conference papers

Mapping Sounds on Images Using Binaural Spectrograms

Antoine Deleforge 1, * Vincent Drouard 1 Laurent Girin 2 Radu Horaud 1
* Corresponding author
1 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : 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.
Complete list of metadatas

Cited literature [18 references]  Display  Hide  Download


https://hal.archives-ouvertes.fr/hal-01019287
Contributor : Team Perception <>
Submitted on : Monday, July 7, 2014 - 10:45:42 AM
Last modification on : Wednesday, May 13, 2020 - 4:22:02 PM
Document(s) archivé(s) le : Tuesday, October 7, 2014 - 11:52:51 AM

Files

Deleforge-EUSIPCO-AV.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01019287, version 1

Citation

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

Share

Metrics

Record views

1932

Files downloads

829