Jordi Pons

Research Scientist at Stability AI

Barcelona, Catalonia, Spain
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

👤
Senior
🎓
Top School
Jordi Pons is a research scientist based in Barcelona with 11 years of experience specializing in music, audio, and deep learning. He holds a PhD in Music Technology and has driven research at Stability AI and Dolby Labs on audio source separation, speech enhancement, and generative audio models. His background blends academic rigor—from teaching signal processing and working with large-scale music collections—to industry impact, applying neural representations to real-world audio products. Jordi’s work frequently bridges perceptual problems (e.g., cochlear implant listeners) and cutting-edge ML, reflecting both engineering pragmatism and musical sensitivity. He writes about the intersection of art and technology and brings a rare combination of formal music training (piano, clarinet, harmony) and telecom/engineering foundations. Colleagues describe him as a researcher who turns scientific insight into practical systems for creative audio applications.
code11 years of coding experience
job6 years of employment as a software developer
bookTelecommunication Engineering, Audiovisual Systems, Telecommunication Engineering, Audiovisual Systems at UPC - ETSETB TelecomBCN
bookDoctor of Philosophy (Ph.D.), Music Technology, Cum Laude, Doctor of Philosophy (Ph.D.), Music Technology, Cum Laude at Universitat Pompeu Fabra
bookPiano, Clarinet and Harmony studies, Piano, Clarinet and Harmony studies at Conservatori de Girona
languagesSpanish, Catalan, English, French
github-logo-circle

Github Skills (40)

tensorflow-model10
convolutional-neural-networks10
classifiers10
audio10
crowdsourcing9
denoising9
scikit-learn9
music-information-retrieval9
music9
generative-model8
tensorflow8
audio-processing8
speech8
speech-processing7
musicbrainz7

Programming languages (5)

C++TeXHTMLJupyter NotebookPython

Github contributions (5)

github-logo-circle
A didactic toolkit to rapidly prototype audio classifiers with pre-trained Tensorflow models and Scikit-learn
Contributions:157 commits, 1 PR, 104 pushes in 9 months
audioclassifiersscikit-learntensorflow-model
jordipons/elmarc

Dec 2017 - Apr 2018

Contributions:33 commits in 4 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial