Headband Research

Laboratoires.Ecoles, Collège et Formation doctorales 

Stratégie. Séminaires, colloques. Sciences et société

Réseaux et pôles d'excellence. Investissements d'avenir (Labex)


Headband GRICAD

GRICAD (Grenoble Alpes Recherche Infrastructure de Calcul Intensif et de Données) est une Unité d'Appui à la Recherche (UAR 3758) sous la tutelle du CNRS (INSMI), de l’Université Grenoble Alpes, de Grenoble-INP et de INRIA, pour répondre aux besoins relatifs au calcul et à la donnée des chercheurs du site grenoblois.
Dans ce cadre GRICAD organise régulièrement des journées de formation et d'animation.

Creative Commons license Reconnaissances de scènes audio par architecture profonde / Mise en oeuvre du Deep Learning au CRIANN [Jan. 30, 2017]



Machines can now watch and interpret images, recognize speech and music genres, yet they are hardly capable of understanding daily life sound events e.g the sounds that occur in a kitchen at morning. 
Today's researches dealing with audio scene understanding are mostly limited to the problem of categorization and localization of few tens of sound event classes and environmental contexts. While such tasks are useful, the ultimate goal of audio scene understanding goes far beyond the assignment of labels to few kinds of sound events. Instead, it aims at developing machines that fully understand audio input. However, before making sense from audio, it is necessary to be able to recognize these audio contexts. 
In this talk, we present the results we achieved by performing representation learning (using deep learning) for classifying audio scenes.

Tags: gricad



Video file(s):

Audio file:


Check the box to autoplay the video.
Check the box to loop the video.
Check the box to indicate the beginning of playing desired.
 Embed in a web page
 Share the link
Comments have been disabled for this video.