Jordi Pons
@jordiponsdotme
Music and AI research at @StabilityAI. Previously at @Dolby and @MTG_UPF.
✍️New paper is out!✍️ GASS: GENERALIZING AUDIO SOURCE SEPARATION WITH LARGE-SCALE DATA We study a single general audio source separation (GASS) model trained to separate speech, music, and sound events in a supervised fashion with a large-scale dataset. arxiv.org/abs/2310.00140
Today’s uncanny AI sounds might one day be symbols of our time, potentially even nostalgic in the future. 👉 artintech.substack.com/p/ai-music-is-…
AIDA’s live-generated film follows the music—not the other way around. It’s not a live soundtrack accompanying a film—it’s a film shaped by the live performance. 👉azopera.org/performances/a…
Most artists already know how to make music—they're not looking for AI to do it for them. 👉 artintech.substack.com/p/ai-music-is-…
📢 Excited to share our new publication: "Why technology needs artists"! Explore how artists drive tech advancement. 📖 This new report features 56 leaders from across 24 countries and five continents, read it here: britishcouncil.org/research-insig… @BritishArts
Who's out there using Stable Audio Open? Would love to keep all the community projects on my radar. - sao huggingface.co/stabilityai/st… - sao-small huggingface.co/stabilityai/st…
There are 3 alternatives: live music, recorded music & generative music. Generative music enjoys some of the benefits of both its ancestors. Like live music, it is always different. Like recorded music, it is free of time-and-place limitations — Brian Eno zenodo.org/records/6767436
What’s an artistic medium? It’s the thing artists use to make art. Like canvas for painters. Clay for sculptors. Video for directors. Or recordings for musicians. In this post I explore how to use generative AI as an artistic medium. artintech.substack.com/p/ai-as-an-art…
Stable Audio Open Small is accepted at #WASPAA2025 @IEEE_WASPAA ! Can't wait to share the latest in blazingly fast, on-device text-to-audio in Lake Tahoe 🏞️
Stability AI just dropped Stable Audio Open Small on Hugging Face Fast Text-to-Audio Generation with Adversarial Post-Training
We’ve achieved AGI: Artificial Gastro Intelligence. Today we’re publicly launching Epicure, the world’s most advanced culinary AI, powered by actual science of how food ingredients are paired. Our PhD @jaklerad has refined the dataset and created a 300-dimensional,…
I’ve been studying AI and gastronomy—sharing my learnings here: artintech.substack.com/p/ai-makes-din… Delicioso Algoritmo (Delicious Algorithm) by Eneko Axpe gives a nice overview of the field. Know any other books, papers or blogposts? I'm having trouble finding beginner-friendly resources.
I'm pleased to have an opportunity to give a talk at the Music Technology Group of UPF! Wed, June 11, 3PM (CET) (Thank you @jordiponsdotme for the intro!) upf.edu/web/mtg/home/-…
Lately, I’ve been learning to mix music. And it feels overwhelming when you are a beginner. Following this checklist helped me. With this list you don’t need to remember everything. Just need to do what’s next. Details and a PDF of the checklist in: artintech.substack.com/p/mixing-music…
Landed a feature in stable audio tools that should make it easier to fine-tune your own custom text to music models - especially if you're GPU poor. Pre-encoding latents ahead of time reduces GPU memory + helps keep your GPU hot🔥 Documentation here: github.com/Stability-AI/s…
Next Monday Hanoi will be presenting at @aimusicmeetup. Join us :) will be fun! It's a community-based event and tickets are free. Thanks @BMAT for the venue ♥️
🎧 BAMM v3.0 is happening June 9 at @BMAT (7pm)! Join @yaboihanoi for a hybrid talk + performance: Fusing Thai and AI Music: Reimagining Culture with Machine Learning AI meets Thai bass music. Don’t miss this. 🎟️ RSVP now → eventbrite.com/e/bamm-v30-fus…
You ever search "AI music" on YouTube? Top results: “AI Drake,” “Beatles clone,” “24-hour lo-fi generators”. Noise, novelty, clickbait. Looking 4 Artists using AI to explore identity, tradition, and sound in wild new ways? BAMM v3.0 – June 9, 19h 🔗 tinyurl.com/BAMMv3