🔥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

Got a "too familiar" tune from your generative model? Try checking for musical version matching (MVM)! But MVM works with full tracks, and your tune is just a segment... Well, in our latest work we tackle precisely this issue, and achieve SOTA results even on full tracks! 1/4

I'm running a paid study on guitar timbre transfer - it should take approximately 30min 🎸 If you're interested, please reach out via DM!

If you're interested in SSL, music, or both, or none, you're very welcome to my PhD defense 🎉 🕒 Monday, March 17, 3pm CET 🧭 Télécom Paris, Palaiseau 🌐 Zoom link below Btw, it's a unique opportunity to see me wearing sth else than a black t-shirt, you shouldn't miss that 😉

Want to know if a ML model was trained on your dataset with 1 API call? See you in conferences 🙌 Excited to share that our paper Data Taggants for image data was accepted at ICLR 2025 🎉 Our follow-up on audio data, was accepted at ICASSP 2025! 🎉 Check out the details below 👇

🎉 New release Our collaboration w/ DELAURENTIS continues to come to life in a new video clip; a dialogue between #humanandmachine Together, we developed #Sinvocea, a research experiment blending AI-assisted composition & real-time generative visuals youtube.com/watch?v=bNCytB…

おれは日本語王になる男だ！

We are excited to share our recent collaboration with electronic artist DeLaurentis (delaurentis.lnk.to/Musicalism) 🎤✨, showcasing the new real-time capabilities of Alain Riou 's PESTO, a lightweight pitch estimation tool. Real-time PESTO 🚀 is now accessible to the community 🎶 :

🔉New paper out! Recent audio codecs typically learn compression and quantization jointly, limiting the choice of quantization layers, non-differentiable by definition. What if we used powerful neural quantizers like Qinco2 and trained them offline? arxiv.org/abs/2503.19597

How can we leverage naturalistic videos for visual SSL? Naturalistic, i.e. uncurated, videos are abundant and can emulate the egocentric perspective. Our paper at ICLR 2025, PooDLe🐩, proposes a new SSL method to address the challenges of learning from naturalistic videos. 🧵

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/UMR…

-------------------- 🎉 Recruiting Deep Learning Interns or RAs for Music 🎶 at Sony Computer Science Laboratories, Tokyo! 🇯🇵 sonycsl.co.jp/en/ -------------------- Work can be conducted remotely 🌍 from anywhere in the world or onsite in Tokyo 🏙️ The working period will be

``The Inverse Drum Machine: Source Separation Through Joint Transcription and Analysis-by-Synthesis,'' Bernardo Torres (S2A, IDS), Geoffroy Peeters (S2A, IDS), Gael Richard (S2A, IDS), ift.tt/mhzYvlO

I'm pleased to share my internship project Sony AI, DiffVox, a differentiable effects chain for vocals with hundreds of presets. arXiv: arxiv.org/abs/2504.14735 code: github.com/SonyResearch/d… 🤗: huggingface.co/spaces/yoyolic…

They have to work with Zakk Wylde at some point

I'm glad to share that after 3 amazing years doing my PhD at Sony, I just joined... 🥁🥁🥁 Sony! I'll be working for a couple of months at Sony AI in Barcelona with Joan Serrà, still on music-related topics 🎶🤖

With Qosmo — AI Creativity & Music Lab we put out a new Max/MSP External! Introducing pesto~, a standalone wrapper for real-time neural pitch estimation! Robust, timbre-agnostic, low-latency pitch tracking in Max! Enjoy! 🎛

PESTO è ora in Max/MSP! 🥳🥳🥳 Use directly your voice or any monophonic audio as a controller, all in real-time with almost no latency 🚀 おめでとうございます Qosmo — AI Creativity & Music Lab and Tom Baker !!! 🎶🎶

New paper on evaluating watermarking algorithms for audio and music! We uncover a number of robustness issues, and especially question the future of such algorithms under current and emerging neural codecs (including, but not limited to, generative ones). Links below ⬇️