🎉 New paper published in Neural Networks (Elsevier)!
We propose MDVAE, a multimodal and dynamical variational autoencoder applied to representation learning in audiovisual speech.
arxiv.org/abs/2305.03582
Thread ⬇️
This is wild:
DraGAN: Interactive point-based manipulation of images using AI.
This gives you controllability of the pose, shape, expression, and layout of the objects in your images.
We created data2vec, the first general high-performance self-supervised algorithm for speech, vision, and text. When applied to different modalities, it matches or outperforms the best self-supervised algorithms. Read more and get the code:
ai.facebook.com/blog/the-first…
WTF. This is the most impressive thing I have ever seen in computer vision. Absolutely incredible. I knew it was going to happen, nevertheless seeing it here is something else. The video is synthetic from a few pictures 🤯
But there is more re where this can go 1/
WTF. This is the most impressive thing I have ever seen in computer vision. Absolutely incredible. I knew it was going to happen, nevertheless seeing it here is something else. The video is synthetic from a few pictures 🤯
But there is more re where this can go 1/
1K Followers 1K FollowingAn International journal covering all areas of mathematical methods and their applications to a wide range of different fields; operated by @tomcuchta
4.3M Followers 3 FollowingOpenAI’s mission is to ensure that artificial general intelligence benefits all of humanity. We’re hiring: https://t.co/dJGr6Lg202
84K Followers 702 FollowingDirector, Max Planck Institute for Intelligent Systems (@MPI_IS). Chief Scientist @meshcapade. Building 3D digital humans using vision, graphics, and learning.
195 Followers 432 FollowingCEO @Sonaid - Give ears to IoT devices to make people safe.
🚀 Deep tech startup - SaaaS Sound alerts as a service.
🗨️ sharing about tech and startups.
2K Followers 2K FollowingOpen access journal publishing research in all areas of mathematics. Indexed in the Web of Science (Q1-ranked, Mathematics), Scopus, and the DOAJ.
916 Followers 197 FollowingFull professor at Telecom Paris, Institut Polytechnique de Paris (audio signal processing, deep learning, music information retrieval)
4K Followers 362 FollowingI'm working at CMU (2021-). I was working at NTT (2001-2011), MERL (2012-2017), and JHU (2017-2020). Speech and Audio Processing is my main research topic.
3K Followers 860 FollowingCentre @Inria de l’@univbordeaux : les sciences et technologies du numérique en #NouvelleAquitaine
#Recherche #Innovation #Numerique #Sciences
5K Followers 1 FollowingIEEE International Conference on Acoustics, Speech, and Signal Processing. #ICASSP2026 will be held 4-8 May 2026 in Barcelona, Spain.
46K Followers 2K FollowingInstitut national de #recherche en sciences et technologies du #numérique 🚀 La recherche de rang mondial et l’#innovation technologique constituent notre ADN.
2K Followers 0 FollowingThe official(ish) account of the Auditory-VIsual Speech Association (AVISA) AV 👄👓speech references, but mostly what interests me
3K Followers 425 FollowingCentre @Inria de l'Université Grenoble Alpes : les sciences et technologies du numérique en #Isère
#recherche #numérique #innovation
62 Followers 141 FollowingAssociate Professor in Computer Science - Université de Lorraine
Focusing mainly on Multimodal Speech Synthesis, Lipsync, Coarticulation, Human centered AI
1.4M Followers 1K FollowingBuilding @EurekaLabsAI. Previously Director of AI @ Tesla, founding team @ OpenAI, CS231n/PhD @ Stanford. I like to train large deep neural nets.
1.4M Followers 570 FollowingThe Massachusetts Institute of Technology is a world leader in research and education. Related accounts: @MITevents @MITstudents @MIT_alumni
4K Followers 149 FollowingWelcome to the 26th Interspeech Conference, the premier global event on spoken language processing technology, held in August 17-21, 2025, in Rotterdam, NL.
636 Followers 497 FollowingACM Multimedia 2022, Lisbon, Portugal. The worldwide premier conference and a key world event to display scientific achievements and innovation in multimedia!
79K Followers 1 FollowingDemocratizing AI research, education, and technologies. Learn how to build with AI in our new AI Academy: https://t.co/zQXQt0Pem8