Browsing by Author "Font, Frederic"

Sort by: Order: Results:

  • FSD50K: an open dataset of human-labeled sound events
    Fonseca, Eduardo; Favory, Xavier; Pons, Jordi; Font, Frederic; Serra, Xavier (Institute of Electrical and Electronics Engineers (IEEE), 2022)
    Most existing datasets for sound event recognition (SER) are relatively small and/or domain-specific, with the exception of AudioSet, based on over 2 M tracks from YouTube videos and encompassing over 500 sound classes. ...
  • SOURCE: a Freesound community music sampler
    Font, Frederic (ACM Association for Computer Machinery, 2021)
    SOURCE is an open-source hardware music sampler powered by Freesound’s collection of near 500k Creative Commons sounds contributed by a community of thousands of people around the world. SOURCE provides a hardware ...
  • Toward interpretable polyphonic sound event detection with attention maps based on local prototypes
    Zinemanas, Pablo; Rocamora, Martín; Fonseca, Eduardo; Font, Frederic; Serra, Xavier (Universitat Pompeu Fabra. Music Technology Group, 2021)
    Understanding the reasons behind the predictions of deep neural networks is a pressing concern as it can be critical in several application scenarios. In this work, we present a novel interpretable model for polyphonic ...
  • Training sound event classifiers using different types of supervision
    Fonseca, Eduardo (Universitat Pompeu Fabra, 2021-12-01)
    The automatic recognition of sound events has gained attention in the past few years, motivated by emerging applications in fields such as healthcare, smart homes, or urban planning. When the work for this thesis started, ...