Every month, the joint laboratory invites outside speakers to take part in seminars for its partners.

Jordi Pons (Stability AI): Stable Audio

Abstract: Stable Audio’s research has focused on the efficient generation of long-form, variable-length stereo music and sounds at 44.1kHz using text prompts with generative models. In this presentation we’ll discuss its latest developments, and we’ll see go through our recent contributions on improved musicality, controllability and evaluation.
Bio: Jordi Pons is a researcher at Stability AI working on generative models for audio and music. Previously, he was a staff researcher at Dolby Laboratories and received a PhD in music technology, large-scale audio collections, and deep learning at the Music Technology Group (Universitat Pompeu Fabra, Barcelona). He also recieved a MSc in sound and music computing (Universitat Pompeu Fabra, Barcelona), and his BSc was in telecommunications engineering (Universitat Politècnica de Catalunya, Barcelona). He also interned at IRCAM (Paris), at the German Hearing Center (Hannover), at Pandora Radio (USA, Bay Area), and at Telefónica Research (Barcelona).


  • https://www.jordipons.me/