Assiociate Professor at Telecom Paris. Working on machine listening and mixed reality
Palaiseau, France
Joined May 2019
- Tweets61
- Following233
- Followers183
- Likes119
Mathieu Fontaine retweeted
Every language in Monsoon V1, in one spin of the globe. 50 languages. 23 countries.
Spontaneous speech, not read prompts. If your ASR works in English and falls apart everywhere else, this is the data it was missing.
Mathieu Fontaine retweeted
Language modeling is ambiguous. If you ask someone to caption an image, describe an audio clip, or to translate a sentence, you’ll get several valid outputs.
In this work, we handle this with a winner-takes-all training objective that encourages diverse, plausible predictions.
1/ Multiple Choice Learning of Low-Rank Adapters for Language Modeling
TL;DR: LoRA heads + Winner-Takes-All loss → diverse, plausible LLM outputs
📄 arxiv.org/abs/2507.10419
💻 github.com/Victorletzelter/L…
@VLetzelter, H. Malard, M. Fontaine, G. Richard, S. Essid, @abursuc, @ptrkprz
Mathieu Fontaine retweeted
This is the final work from my PhD, in collaboration with @abursuc @Mldhug @MathieuFontai19 @.grichard @.slimessid @ptrkprz at @valeoai and @telecomparis
Our poster presentation is Thu, Jul 9, 2026 • 10:30 AM – 12:15 PM KST.
Check our poster in 4A-3 at #interspeech2024 on "dereverberation constrained on RIR characteristics"
Mathieu Fontaine retweeted
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]
Mathieu Fontaine retweeted
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
