Mathieu Fontaine

Check our poster in 4A-3 at #interspeech2024 on "dereverberation constrained on RIR characteristics"

Interested in ill-posed learning tasks, uncertainty prediction, conditional density estimation or multi-head deep neural networks ? In our new paper, accepted at #ICML24, we tackle these challenges by exploring the Winner-Takes-All (WTA) training scheme. [1/n]

Our paper entitled "Neural Blind Source Separation and Diarization for Distant Speech Recognition" is accepted to Interspeech 2024! Our neural FCASA is a method to jointly separate and diarize speech mixtures without supervision by isolated signals. arxiv.org/abs/2406.08396

INTERSPEECH paper for @tp_adasp: # 5 - RIR-in-a-Box: Estimating Room Acoustics from 3D Mesh Data through Shoebox Approximation, Liam Kelley, Diego Di Carlo, Mathieu Fontaine, Aditya Arie Nugraha, Yoshiaki Bando

INTERSPEECH paper for @tp_adasp: # 4 - Speech dereverberation constrained on room impulse response characteristics, Louis Bahrman, Mathieu Fontaine, Jonathan Le Roux, Gaël Richard

ICML paper for @tp_adasp: # 3 - Winner-takes-all learners are geometry-aware conditional density estimators

EUSIPCO papers for @tp_adasp: #2 - A. Emelchenkov, M. Fontaine, Y. Grenier, H. Mahé, F. Roueff; Multifrequency highly oscillating aperiodic amplitude estimation for nonlinear chirp signal

EUSIPCO 2024 at @tp_adasp: #1 - B. Giniès, X. Bie, O. Fercoq, G. Richard, Using Random Codebooks for Audio Neural AutoEncoders #audio #ai

ADASP presentation at ICASSP #3 @tp_adasp #Audio Anyways, proud of them ;)

ADASP poster at ICASSP #2 @tp_adasp #Audio

ADASP posters at ICASSP #1. @tp_adasp #Audio

@adasp group from ⁦⁦@telecomparis⁩ @ieeeICASSP⁩ 2014, Seoul, Korea

3 accepted papers for ICASSP. See you in South Korea !

Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis by @VLetzelter @MathieuFontai19 @Mickael_Chen P. Pérez, S. Essid, G. Richard tl;dr: extend MCL for cond. distrib. estimation in regression #neurips2023 arxiv.org/abs/2311.01052

Today, we announce Ego-Exo4D, the largest and most diverse multi-view dataset, showing human experts around the world performing a core set of skilled activities, w/ unprecedented multi-modality, novel new video-language resources, and rich annotations