Category: Seminars

Oct 06

Audio-Visual Analysis for Human-Robot Interaction

Data Science Seminar Series, 12 Octobrer 2017 Radu Horaud Abstract: Robots have gradually moved from factory floors to populated spaces. Therefore, there is a crucial need to endow robots with communicative skills. One of the prerequisites of human-robot communication (or more generally, interaction) is the ability of robots to perceive their environment, to detect people, …

Continue reading »

Oct 05

Reinforcement approaches for online learning of virtual vocal conversational agents

Seminar by Fabrice Lefèvre, Université d’Avignon Room C207 9:30 – 11:00   Abstract: Stochastic techniques, supervised or not, or by reinforcement, are now largely spread on every modules intervening in academic systems of human-machine dialog. Current researches strive to improve even further their quality to reach satisfying and acceptable global performance. A major default remains …

Continue reading »

Sep 21

Multi-Microphone Speaker Localization on Manifolds: Achievements and Challenges

Multi-Microphone Speaker Localization on Manifolds: Achievements and Challenges Wednesday, September 27th 2017, 10:30 – 12:00, room F107, INRIA Montbonnot Seminar by Prof. Sharon Gannot, Bar-Ilan University, Israel joint work with Bracha Laufer-Goldshtein, Bar-Ilan University, Israel and Prof. Ronen Talmon, The Technion-IIT, Israel   Abstract: Speech enhancement is a core problem in audio signal processing, with commercial applications …

Continue reading »

Mar 10

Modeling Reverberant Mixtures for Multichannel Audio-Source Separation

Wednesday, 22 March 2017, 10:30 – 11:30 am, room F107, INRIA Montbonnot Seminar by Simon Leglaive, Telecom ParisTech, Paris   Abstract: We tackle the problem of multichannel audio-source separation in under-determined reverberant mixtures. The aim of this talk is to present source separation approaches that can take advantage of prior knowledge on the mixing filters, …

Continue reading »

Nov 28

Augmented parametric shapes for real-time dense 3D modeling using an RGB-D camera

Friday, December 9, 2016,11:00 am to 12:00 pm, room F108, INRIA Montbonnot Seminar by Diego Thomas, University of Kyushu, Fukuoka, Japan   Abstract: Consumer grade RGB-D cameras such as the Kinect camera or the Asus Xtion pro camera have become the commodity tool to build dense 3D models of indoor scenes. The volumetric Truncated Signed …

Continue reading »

Oct 13

A Hybrid Approach for Speech Enhancement Using GMM and Deep Neural Network Phoneme Classifier

Tuesday, October 18, 2016, 4:00 pm to 5:00 pm, room F108, INRIA Montbonnot Seminar by Sharon Gannot, Bar Ilan University Abstract: In this work, we propose a hybrid approach for single microphone speech enhancement, merging the generative Mixture of Gaussians (MoG) model and the discriminative deep neural network (DNN). The proposed algorithm is executed in …

Continue reading »

Sep 30

Binaural sound reproduction for the hearing impaired

Thursday, October 6, 2016, 10:00 am to 11:00 am, room F107, INRIA Montbonnot Seminar by Noam Shabtai, Ben Gourion University Abstract: In most hearing aids systems, microphone array signal processing algorithms may be employed in order to reduce the noise and enhance the signals that are arriving from specific directions. However, most noise reduction algorithms …

Continue reading »

Sep 21

Modelling face-to-face conversational interaction with robots

Thursday, October 6, 2016, 11:00 am to 12:00 am, room F107, INRIA Montbonnot Seminar by Gabriel Skantze, KTH, Stockholm, Sweden Abstract: When humans interact and collaborate with each other, they coordinate their turn-taking behaviours using verbal and non-verbal signals, expressed in the face and voice. If robots of the future are supposed to engage in social interaction with humans, it …

Continue reading »

May 25

Matrix Completion: A Vision-oriented Perspective

Friday, June 3, 2016, 10:00 am to 11:00 am, room F107, INRIA Montbonnot Seminar by Xavier Alameda-Pineda, University of Trento, Italy Abstract: Matrix completion is a generic framework aiming to recover a matrix from a limited number of (possibly noisy) entries. In this context, low-rank regularizers are often imposed so as to find matrix estimators that are …

Continue reading »

Mar 04

Guiding Robot Audition with Motor Data: A Hybrid Classifier-Dictionary Approach

Monday, March 7, 2016, 11:00 to 12:00, room F107, INRIA Montbonnot Seminar by Antoine Deleforge, PANAMA team, INRIA Rennes-Atlantique A specificity of human-robot interaction (HRI), as opposed to human-computer interaction (HCI), is the ability of a robot to perform movements. On the one hand, this ability may constitute an advantage, enabling active perception. On the …

Continue reading »