Simon Leglaive
@sleglaive.bsky.social
Tenured Assistant Professor at CentraleSupélec.
Signal processing and machine learning for speech and audio.
sleglaive.github.io
Signal processing and machine learning for speech and audio.
sleglaive.github.io
Reposted by Simon Leglaive
Our team is hiring a postdoc in Audio AI!
What: speech, music, bioacoustics
How: multiresolution neural networks in the raw waveform
Where: Nantes, France (audio.ls2n.fr)
When: negotiable
How long: 12 months, renewable
Apply before May 10: emploi.cnrs.fr/Offres/CDD/U...
Please share the news
What: speech, music, bioacoustics
How: multiresolution neural networks in the raw waveform
Where: Nantes, France (audio.ls2n.fr)
When: negotiable
How long: 12 months, renewable
Apply before May 10: emploi.cnrs.fr/Offres/CDD/U...
Please share the news
April 23, 2025 at 11:03 PM
Our team is hiring a postdoc in Audio AI!
What: speech, music, bioacoustics
How: multiresolution neural networks in the raw waveform
Where: Nantes, France (audio.ls2n.fr)
When: negotiable
How long: 12 months, renewable
Apply before May 10: emploi.cnrs.fr/Offres/CDD/U...
Please share the news
What: speech, music, bioacoustics
How: multiresolution neural networks in the raw waveform
Where: Nantes, France (audio.ls2n.fr)
When: negotiable
How long: 12 months, renewable
Apply before May 10: emploi.cnrs.fr/Offres/CDD/U...
Please share the news
Check out MEGA, a masked generative model for human mesh recovery from RGB images 📷
MEGA will be presented at #CVPR2025, huge congratulations to @gfiche.bsky.social 🎉👏
MEGA will be presented at #CVPR2025, huge congratulations to @gfiche.bsky.social 🎉👏
Reconstructing 3D humans from a single image is highly ambiguous: many 3D poses can explain the same 2D view. Yet, most HMR methods predict a single mesh! 🤯
At #CVPR2025, we present MEGA, a new approach that tackles this challenge. 🧵👇 (1/6)
At #CVPR2025, we present MEGA, a new approach that tackles this challenge. 🧵👇 (1/6)
March 20, 2025 at 6:38 AM
Check out MEGA, a masked generative model for human mesh recovery from RGB images 📷
MEGA will be presented at #CVPR2025, huge congratulations to @gfiche.bsky.social 🎉👏
MEGA will be presented at #CVPR2025, huge congratulations to @gfiche.bsky.social 🎉👏
Reposted by Simon Leglaive
I’ve put together a short list of opportunities for early career academics willing to come to Europe: www.cvernade.com/miscellaneou...
This mostly covers France and Germany for now but I’m willing to extend it. I build on @ellis.eu resources and my own knowledge of these systems.
This mostly covers France and Germany for now but I’m willing to extend it. I build on @ellis.eu resources and my own knowledge of these systems.
Claire Vernade - European career opportunities
European Academic Career Opportunities in 2025
www.cvernade.com
March 11, 2025 at 9:19 AM
I’ve put together a short list of opportunities for early career academics willing to come to Europe: www.cvernade.com/miscellaneou...
This mostly covers France and Germany for now but I’m willing to extend it. I build on @ellis.eu resources and my own knowledge of these systems.
This mostly covers France and Germany for now but I’m willing to extend it. I build on @ellis.eu resources and my own knowledge of these systems.
Reposted by Simon Leglaive
AnCoGen, a masked autoencoder, unified speech analysis, control, and generation; estimated attributes like pitch and SNR, enabling modification and resynthesis.
AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder
Samir Sadok, Simon Leglaive, Laurent Girin, Gaël Richard, Xavier Alameda-Pineda
arxiv.org
January 10, 2025 at 11:21 AM
AnCoGen, a masked autoencoder, unified speech analysis, control, and generation; estimated attributes like pitch and SNR, enabling modification and resynthesis.
Reposted by Simon Leglaive
au micro de @francemusique.fr, j'ai parlé de paréidolie, de temps réel, de robots quadrupèdes et d'Edgard Varèse : "je rêve d'instruments obéissant à la pensée qui [...] se plient à l'exigence de mon rythme intérieur"
pour ce podcast à plusieurs voix signé Pierre-Yves Georges
heureuse écoute ! 🎙️⤵️
pour ce podcast à plusieurs voix signé Pierre-Yves Georges
heureuse écoute ! 🎙️⤵️
L’intelligence artificielle est partout, y compris dans le domaine musical. Les usages sont nombreux et les inquiétudes aussi. Voici notre nouveau podcast "Musique et IA", en 8 épisodes, à écouter dès maintenant @francemusique.fr
▶️ www.radiofrance.fr/francemusiqu...
▶️ www.radiofrance.fr/francemusiqu...
January 15, 2025 at 9:21 AM
au micro de @francemusique.fr, j'ai parlé de paréidolie, de temps réel, de robots quadrupèdes et d'Edgard Varèse : "je rêve d'instruments obéissant à la pensée qui [...] se plient à l'exigence de mon rythme intérieur"
pour ce podcast à plusieurs voix signé Pierre-Yves Georges
heureuse écoute ! 🎙️⤵️
pour ce podcast à plusieurs voix signé Pierre-Yves Georges
heureuse écoute ! 🎙️⤵️
Reposted by Simon Leglaive
Anne Gagneux, Ségolène Martin, @quentinbertrand.bsky.social Remi Emonet and I wrote a tutorial blog post on flow matching: dl.heeere.com/conditional-... with lots of illustrations and intuition!
We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423
We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423
November 27, 2024 at 9:00 AM
Anne Gagneux, Ségolène Martin, @quentinbertrand.bsky.social Remi Emonet and I wrote a tutorial blog post on flow matching: dl.heeere.com/conditional-... with lots of illustrations and intuition!
We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423
We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423
Reposted by Simon Leglaive
I initiated a starter pack for Audio ML. Let me know if you'd like to be added/removed.
go.bsky.app/LGmct4z
go.bsky.app/LGmct4z
November 18, 2024 at 4:46 AM
I initiated a starter pack for Audio ML. Let me know if you'd like to be added/removed.
go.bsky.app/LGmct4z
go.bsky.app/LGmct4z
Reposted by Simon Leglaive
The #SANE2024 talks are up on YouTube! Feat. Quan Wang, @gretatuckute.bsky.social, Mark Hamilton, Bhuvana Ramabhadran, Zhiyao Duan, Chris Donahue.
Binge watching playlist⬇️
youtube.com/playlist?lis...
Binge watching playlist⬇️
youtube.com/playlist?lis...
SANE 2024 @ Google Cambridge - YouTube
SANE 2024, a one-day event gathering researchers and students in speech and audio from the Northeast of the American continent, was held on Thursday October ...
youtube.com
November 23, 2024 at 4:25 AM
The #SANE2024 talks are up on YouTube! Feat. Quan Wang, @gretatuckute.bsky.social, Mark Hamilton, Bhuvana Ramabhadran, Zhiyao Duan, Chris Donahue.
Binge watching playlist⬇️
youtube.com/playlist?lis...
Binge watching playlist⬇️
youtube.com/playlist?lis...