Starting a new event series called Beyond 2045 with @daitomanabe — exploring AI and the future of music.
First event: Nov 19 (Wed)
Guest: yaboihanoi @yaboihanoi
Talk, performance, @neutone_ai demo, and a special guest DJs.
Application form 👇
https://t.co/f8o6l7dW8v
Welcome to @ISMIRConf#ismir2025 ! We've arrived in Daejeon and excited to meet all those attending! We'll be showcasing our latest research on Latent Granular Synthesis and will be hanging out at the Neutone booth all day tomorrow. Please come say hi!
@naotokui_en and I wrote a short paper on (mis)using neural audio codecs for some zero-shot timbre transfer / latent level granular resynth weirdness.
📖 Please give it a read and see you all at ISMIR!
We have contributed a late breaking demo paper to ISMIR!
By exploiting the compressed information dense latents of Neural Audio Codecs, we can perform zero-shot ‘timbre transfer’ using as little as a single source audio sample for reference. 🔥
During his internship with @SonyCSLMusic, Tom just made possible cheap and controllable music generation 🎶🎶
Have a look if your generation is frustrated to be poor and out of control
��️⏬️⏬️
We show that cloning entire encoders isn't essential for control signals - leveraging frozen encoder blocks with adaptation layers works equally well!
paper: https://t.co/1mkcWJW9Pn
audio examples: https://t.co/bcsyOZJRHW
@latentspaces@SonyCSLMusic@SonyCSLParis
Hey! Our paper, 🌸 “LiLAC: A Lightweight Latent ControlNet for Musical Audio Generation” got accepted as ISMIR 2025!
It presents a novel control paradigm for audio diffusion models with greatly reduced parameters, encouraging users to train individual, modular models.
With @qosmo_inc 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! 🎛
Put together a neat little Max external for very quick and lightweight neural pitch estimation using @howariou's PESTO model.
It's open-source so If you're into live audio/visual stuff, please check it out!
🌿 Introducing pesto~ for Max/MSP!
A standalone wrapper for real-time neural pitch estimation powered by Sony CSL's PESTO deep learning model. Get robust, timbre-agnostic, low-latency (<5ms) pitch tracking with confidence & amplitude outputs in your Max patches.
Hey musicians / ML audio people! 🎶
Please help with my research by taking a listening test to help improve generative models!
2 parts, ~10 mins each:
🔊 Audio Quality Test
🎼 Chord Adherence (tricky but fun!)
Headphones recommended →https://t.co/THBnVIkFzY
Thanks again!
What an astonishingly terrible take. He misses the entire point of creative practice.
Accessibility and mastery are not opposed, they're two ends of the same personal creative journey.
Great tools help people start that journey (accessible), but also provide challenges that beg you to dig deeper, and reward you for your struggle with unique and personal expression (mastery).
Those are the technologies that we have always strived to build. Reduce the barriers to entry, but simultaneously raise the ceiling for new expression.