Dans cette thèse, nous traitons le problème de la séparation de sources audio multicanale par réseaux de neurones profonds (deep neural networks, DNNs). Notre approche se base sur le cadre classique de séparation par algorithme espérance-maximisation (EM) basé sur un modèle gaussien multicanal, dans lequel les sources sont caractérisées par leurs spectres de puissance à court terme et leurs matrices de covariance spatiales. Nous explorons et optimisons l'usage des DNNs pour estimer ces paramètres spectraux et spatiaux. À partir des paramètres estimés, nous calculons un filtre de Wiener multicanal variant dans le temps pour séparer chaque source. Nous étudions en détail l'impact de plusieurs choix de conception pour les DNNs spectraux et spa...
International audienceOver the past decade deep learning has become the state-of-the-art in many app...
Ph. D. Thesis.Monaural speech separation and enhancement aim to remove noise interference from the n...
Comunicació presentada a la 12th ITG Conference on Speech Communication, celebrada els dies 5 a 7 d'...
This thesis addresses the problem of multichannel audio source separation by exploiting deep neural ...
International audienceThis chapter presents a multichannel audio source separation framework where d...
International audienceThis article addresses the problem of multichannel audio source separation. We...
In this paper, we compare different deep neural networks (DNN) in extracting speech signals from com...
International audienceThis article addresses the problem of multichannel music separation. We propos...
Speech source separation aims to estimate one or more individual sources from mixtures of multiple s...
La localisation de sources sonores est une sous-tâche de l'analyse de scènes sonores qui a défié les...
Deep neural networks (DNNs) are often used to tackle the single channel source separation (SCSS) pro...
Sound source localization (SSL) is a subtask of audio scene analysis that has challenged researchers...
The sources separated by most single channel audio source separation techniques are usually distorte...
Audio source separation is the task of estimating the individual signals of several sound sources wh...
Comunicació presentada a 13th International Conference on Latent Variable Analysis and Signal Separa...
International audienceOver the past decade deep learning has become the state-of-the-art in many app...
Ph. D. Thesis.Monaural speech separation and enhancement aim to remove noise interference from the n...
Comunicació presentada a la 12th ITG Conference on Speech Communication, celebrada els dies 5 a 7 d'...
This thesis addresses the problem of multichannel audio source separation by exploiting deep neural ...
International audienceThis chapter presents a multichannel audio source separation framework where d...
International audienceThis article addresses the problem of multichannel audio source separation. We...
In this paper, we compare different deep neural networks (DNN) in extracting speech signals from com...
International audienceThis article addresses the problem of multichannel music separation. We propos...
Speech source separation aims to estimate one or more individual sources from mixtures of multiple s...
La localisation de sources sonores est une sous-tâche de l'analyse de scènes sonores qui a défié les...
Deep neural networks (DNNs) are often used to tackle the single channel source separation (SCSS) pro...
Sound source localization (SSL) is a subtask of audio scene analysis that has challenged researchers...
The sources separated by most single channel audio source separation techniques are usually distorte...
Audio source separation is the task of estimating the individual signals of several sound sources wh...
Comunicació presentada a 13th International Conference on Latent Variable Analysis and Signal Separa...
International audienceOver the past decade deep learning has become the state-of-the-art in many app...
Ph. D. Thesis.Monaural speech separation and enhancement aim to remove noise interference from the n...
Comunicació presentada a la 12th ITG Conference on Speech Communication, celebrada els dies 5 a 7 d'...