🔥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

If you are a musician in the Boston area using AI in anyway in your process I would love to hear from you. DMs open.

KEYNOTE: Foundation Models Don’t Understand Me - Lessons From AI Lutherie for Live Performances - by manaswi mishra youtube.com/watch?v=SnbJpv… #Coding #Liveperformance #Programming #audioprogrammer

Here is the slide from my talk at yesterday's Tokyo Music AI Gathering 🎶🤖🎤. speakerdeck.com/ta/tokyo-music… In my talk, I discussed the future prospects and key challenges in Music AI 🚀, our strategy and concept 💡, as well as specific research papers 📄, social implementations 🌍,

I'm interviewing Suno CEO Mikey tomorrow for a video podcast episode. What questions should I ask him about AI, music, the music industry, transformers, building an AI startup, capital, etc?

Edit has a fresh UI! ✨You now have Replace, Extend, and Crop all in one place for easier control. Plus, we’ve added Fade Out for a polished track finish. NEW: ✅ Fade Out—a new way to create seamless track endings ✅ A fresh UI—your edit tools, all in one streamlined space ✅

We open-sourced NablAFx. A Framework for differentiable black-box and gray-box audio effects modeling. Nabla (∇) + Audio Effects (AFx) = NablAFx [∇f(x)] 📜: arxiv.org/abs/2502.11668 💻: github.com/mcomunita/nabl…

Who’s out there making interesting new sound art w/ machine learning

AI is a tool real human subjects wield to do stuff. Problem solved.

CFG is just a hack to get conditioning to work. It comes with side effects like over-saturation. If you train your model right you don’t need it. But I still like to crank it as an effect, especially in genres like tearout

"signal processing meets neural nets" is probably my favourite genre of paper, two great examples: Making Convolutional Networks Shift-Invariant Again by Richard Zhang arxiv.org/abs/1904.11486 Alias-Free Generative Adversarial Networks by Karras et al. arxiv.org/abs/2106.12423

"Audio Signal Processing in the Artificial Intelligence Era: Challenges and Directions" A good review paper on the status of ML for various audio tasks, and the major open problems. aes2.org/publications/e…

Introducing v4.5+ New ways to create. Unlock 4.5+ and push your sound further. Swap vocals, flip instrumentals, or spark a song from any playlist—it’s creativity, upgraded.

I’m pleased to share my internship work at Sony AI, Fx-Encoder++, a representation for audio effects at mixture-level and instrument-wise level. Arxiv: arxiv.org/abs/2507.02273 Code: github.com/SonyResearch/F…

great work in audio effects representation learning

I just published the world's fastest EBU-compliant audio loudness meter as a Python package. The underlying C++ code was developed and generously open-sourced by Nomono, and has been battle-tested in production for a long time. It is just a `pip install loudness` away!

Excited to share our beta release of Music Arena, a live evaluation platform for state-of-the-art AI music generation models! 🎧 Listen to the latest models and 🗳️ vote for your favorite ⚔️ music-arena.org ⭐️ github.com/gclef-cmu/musi… 📜 arxiv.org/abs/2507.20900