🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

[🆘 People working in representation learning for general audio] we're looking for open-source, pre-trained models to test (wget appreciated). Any recommendations? Shameless plug accepted and suggested 🫣

We create breakthroughs together. ✨ Aya Expanse Ambassadors represent 45 countries and 23 languages. Before the launch of Aya Expanse, we invited 110 ambassadors to join us to shape how Aya worked for communities all over the world. 🌍

We're building a Resource Hub for SPADE 2025 Workshop at ICASSP. This collection will live on as a standalone 'awesome-' resource. 🎖️If you work on similar fields, please help us contributing by sharing your projects👇

Check it out 👀 #ICASSP2025 SPADE Workshop 2025

Off to Kolkata 🇮🇳 for tomorrow's MCMI Workshop at ICPR Conference! Eleven papers on computer vision and multimodal AI, plus an exciting keynote by Dr. Abhijit Das on learning representations 🚀

🌟Participate in a workshop at #ICASSP2025! Choose from the 15 workshops including Robust and Adaptive Artificial Intelligence for Mission Critical Applications, Radio Maps and their Applications, and more. Learn about all of the accepted workshops: hubs.la/Q02-xRdm0

🎄 Happy to share our early Christmas gift! ✨ Our work on voc2vec, a foundation model for non-verbal vocalizations, has been accepted at #ICASSP2025! Kudos to all the authors, Moreno La Quatra Marco Siniscalchi Elena Baralis 🔗 More details soon!

🦘 Hopping on board. 2 papers accepted at #ICASSP2025 🇮🇳 1️⃣ Addressing Parkinson detection by explicitly modeling speech exercises. Interesting results in cross-language 🇸🇰 / 🇨🇴🇪🇸 (w/ Marco Siniscalchi and Juan Rafael Orozco-Arroyave) -- more info soon! 👇👇👇

Happy to see our IEEE ICASSP paper finally out! 🇮🇳 We propose voc2vec, the first universal representation model for vocalization tasks👶😆 Joint work with Moreno La Quatra and Marco Siniscalchi! 🤗HF Models: shorturl.at/GLBg1 💻Github Repo: shorturl.at/oAiw5 👇Paper

ICASSP 2025 papers are available online ieeexplore.ieee.org/xpl/conhome/10…

Last week, at our PoliTO&Amazon workshop, we presented the results of our collaboration, with great interventions from #UniTO! 🤝 It's nice to see how strong the collaborations are! Excited for what’s next! ✨ Alkis Koudounas Vittorio Mazzia Manuel Giollo

Our bilingual model for Speech-based Parkinson's works on different languages using specialized task heads🎯 (... and other tweaks) Great collaboration with Marco Siniscalchi and Juan Rafael Orozco-Arroyave! 👋See you soon at Hyderabad for #ICASSP2025!

Absolutely agree — this year's organization is a mess. How are we supposed to attend if visa invitation letters arrive too late or when everything (flights, accommodation) is already too expensive? I expected better from IEEE ICASSP.

SPADE 2025 workshop IEEE ICASSP happening now in room MR1.05 (and remotely via zoom) 🔥 Join us for the amazing keynote of professor Mark Hasegawa-Johnson on ‘The Speech Accessibility Project’, followed by many interesting contributions! 🚀

After my first #NeurIPS rush 🥵, I’m super happy to share that we have two papers accepted at my first #ACL2025, both in collaboration with Amazon Science! 🔥 More details soon! Loving every bit of this final PhD year! And the best is yet to come 🚀 #StayTuned #PhDLife

``"Alexa, can you forget me?" Machine Unlearning Benchmark in Spoken Language Understanding,'' Alkis Koudounas, Claudio Savelli, Flavio Giobergia, Elena Baralis, ift.tt/AOQtymX