Contact: jordi < dot > pons < at > upf < dot > edu
Links:    LinkedIN
   Curriculum vitae (September 2018)    GitHub
   Twitter    Google Scholar
  1. PhD candidate  2015 – till date (Barcelona)
      Deep learning for (music) audio modeling.
  2. Telefónica Research Internship      Summer 2018 (Barcelona)
      Deep learning for sound event recognition.
  3. Pandora Radio Internship  Summer 2017 (USA, Oakland – Bay Area)
      Leveraging the Music Genome Project with deep learning techniques.
  4. German Hearing Center  Summer 2015 (Hannover)
      Improving cochlear implant users music
    perception using source separation.

  5. Master in Sound & Music Computing
      2014 – 2015 (Barcelona)
      UPF – Music Technology Group.
  6. IRCAM Internship  Sept. 2013 – Aug. 2014 (Paris)
      Source separation for drums transcription.
  7. Telecommunications Engineer  2009 – 2014 (Barcelona)
      Universitat Politècnica de Catalunya.
  8. Conservatory  2002 – 2006 (Girona)
      Piano, clarinet & harmony studies.


  • Best student paper award for End-to-end learning for music audio tagging at scale in the 19th International Society for Music Information Retrieval Conference (ISMIR, 2018).
  • AI Grant Fellowship (2017) for the creation of the Freesound Datasets.
  • Machine Learning award for the poster Towards a grounded deep learning paradigm for music modeling in the 5th DTIC-UPF Doctoral Student Workshop (2017).
  • Best paper award for Experimenting with Musically Motivated Convolutional Neural Networks in the 14th International Workshop on Content-Based Multimedia Indexing (CBMI, 2016).

Jordi Pons is a telecommunications engineer specialized in audiovisual systems (Universitat Politècnica de Catalunya, Barcelona), and he holds an M.S. in sound and music computing (Music Technology Group – Universitat Pompeu Fabra, Barcelona). Jordi did his first internship at IRCAM (Paris) where he wrote his undergraduate thesis on source separation for drums transcription. Later on, he did an internship in the German Hearing Center (Hannover) where he developed his master’s thesis on how to improve the perception of music in cochlear implant users using source separation. Currently, he is pursuing a PhD in music technology, large-scale audio collections, and deep learning at the Music Technology Group (Universitat Pompeu Fabra, Barcelona) under the supervision of his director Xavier Serra. During his PhD thesis, Jordi carried out two summer internships: one at Pandora Radio (USA, Bay Area) – where he studied how several deep architectures for music auto-tagging perform at scale; and another at Telefónica Research (Barcelona) – where he studied how to learn audio representations that generalize from small audio datasets.