Frederic Font
Senior Researcher at Phonos Fundació Privada
Barcelona, Catalonia, Spain
Summary
🤩
Rockstar🎓
Top SchoolFrederic Font is a Senior Researcher in Music Technology based in Barcelona with 15 years of experience applying machine listening and music information retrieval to large-scale sound collections. He leads the Freesound project—the world’s largest Creative Commons audio repository with over 600k sounds and 14M users—combining research, development and community coordination. His expertise spans audio signal processing, ML for sound classification, description and retrieval, and hands-on implementation of core algorithms (notably contributions to the Essentia library’s TempoEstimator and harmonic analysis). He coordinated the EU H2020 Audio Commons project, bridging research and industry to foster reuse of CC audio at scale. Fluent in both research and production engineering, he uniquely blends PhD-level scholarship with active open-source development and long-term platform stewardship.
15 years of coding experience
7 years of employment as a software developer
Doctor of Philosophy (PhD), Music Technology, Doctor of Philosophy (PhD), Music Technology at Universitat Pompeu FabraUPC Universitat Politècnica de CatalunyaVisiting PhD student, Music Technology, Visiting PhD student, Music Technology at Queen Mary University of London
English, Spanish, Catalan
Github Skills (8)
algorithm10
algorithms10
c-language10
cprogramming-language10
dspic10
audio-analysis10
dspace10
python3
Programming languages (9)
Github contributions (5)
MTG/essentia
Jul 2016 - May 2022
C++ library for audio and music analysis, description and synthesis, including Python bindings
Role in this project:
Back-end Developer
Back-end DeveloperContributions:17 reviews, 74 commits, 3 PRs in 5 years 10 months
Contributions summary:Frederic's primary contribution involves implementing and refining the `TempoEstimator` algorithm within the `essentia` audio analysis library. They added new parameters to various algorithms, notably `Windowing`, `UnaryOperator`, and `AutoCorrelation`, expanding their functionality. Furthermore, the user has implemented the 'EnhanceHarmonics' and 'EvaluatePulseTrains' algorithms and completed a first implementation of the complete `TempoEstimator` algorithm, demonstrating a focus on audio feature extraction and analysis.
pythoncppc-librarymidipython-bindings
ffont/Freesound-iOS
May 2014 - Oct 2015
Contributions:27 commits, 2 PRs, 2 pushes in 1 year 4 months
objective-ccocoapodsswiftiosfreesound
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.