Genís Plaja, PhD student


I am a PhD student at Music Technology Group, Universitat Pompeu Fabra, Barcelona, under the supervision of Prof. Xavier Serra. My research topics of interest are Audio Signal Processing (ASP), and Music Information Retrieval (MIR), and Machine and Deep Learning (ML & DL). Specifically, I work on vocal melody extraction, vocal source separation, automatic melodic pattern discovery, and I put special emphasis on running these MIR tasks on World traditional music repertoires, to promote the cultural diversity in MIR. I am also a musician in several bands, very passionate about hiking and travelling.

Projects I contributed to

Education and work experience

Education

  • PhD student at Music Technology Group

    (Sept. 2021 - ongoing)

  • Master in Sound and Music Computing

    (Sept. 2020 - Sept. 2021)
    Final Thesis entitled "Data-driven vocal melody detection for Indian Art Music", in which a dataset containing vocal fundamental frequency ground-truth for Carnatic Music was compiled through an Analysis/Synthesis method and used to re-train a data-driven vocal melody extraction model. State of the art results for the considered tradition were achieved.

  • International exchange program in Australia

    (Feb. 2020 - July 2020)
    One semester stay at the Royal Melboure Institute of Technology (RMIT). Passing two of the three taken Computer Science classes with distinction of excellence.

  • Bachelor's Deg. in Audiovisual Systems Engineering

    (Sept. 2016 - July 2020)
    Final Thesis entitled "Machine anomaly detection through sound using autoencoders". Based on Task 2 from DCASE2020 challenge, an anomaly detection model was trained for the GC-MS, a notably expensive machine found in chemistry laboratories.

Work experience

  • Acousting Engineering teacher

    (Sept. 2021 - ongoing)
    Given to the 3rd year of the Bachelor's Degree in Audiovisual Systems Engineering. In charge of the entire practical part of the course, and half of the seminar sessions, where conceptual and technical exercices are reviewed and discussed.

  • Research assistant internship (MTG)

    (Sept. 2020 - Aug. 2021)
    Contributing to the mirdata and soundata libraries by writing dataset loaders for relevant dataset in the MTG, also contributing to the development of the core of both libraries.

  • Research intern (MTG)

    (Nov. 2018 - Jan. 2020)
    Leading the Sounds of Science project, which is an initiative to promote research through the matter of sound. We also collected sounds from several different objects related to science departments.

Scientific publications

→ Plaja, G., 2021. ”Data-driven Vocal Pitch Extraction for Indian Art Music Melodic Analysis”. Master Thesis, Universitat Pompeu Fabra, https://doi.org/10.5281/zenodo.5554704

→ Nuttall, T., Plaja G., Pearson, L., Serra, X., 2021. “The Matrix Profile for Automated Discovery of Repeated Motifs in Audio - Indian Carnatic Music”. In: International Symposium on Computer Music Multidisciplinary Research (CMMR), Tokyo, Japan.

→ Fuentes, M., Salamon, J., Zinemanas, P., Rocamora, M., Plaja, G., Román, I.R., Miron, M., Serra, X. and Bello, J. P., 2021. “Soundata: A Python library for reproducible use of audio datasets“. arXiv e-prints, pp.arXiv-2109, https://arxiv.org/abs/2109.12690


Talks

→ "mirdata: dataset loaders for reproducible research in MIR" in the Seminar for Reproducible Research organized by GdR ISIS (France).
Genís Plaja 2021, web built upon Hassan Ali's studiorlio template