Comunicación

Estimating the performance difficulty of a musical score is crucial in
music education for adequately designing the learning curriculum of the
students. Although the Music Information Retrieval community has recently
shown interest in this task, the scarce amount of annotated data as well as
their inherent subjectiveness hinder the development of the field, especially
when considering frameworks based on machine learning. In this talk I will
present the recent advances done in the field: first of all, I will present a
first approach to address this task based on machine-readable piano scores;
secondly, I will introduce an proof-of-concept work that tackles the same
problem considering printed scores; lastly, I will show some initial insights
obtained when considering audio recordings.


Pedro Ramoneda holds a BSc in Computer Science from the University of Zaragoza,
a Professional degree in Piano Performance from the Conservatory of Music in
Zaragoza, and an MSc in Sound and Music Computing from the Universitat Pompeu
Fabra. He is currently a second-year PhD student in the Music Technology Group
of the Universitat Pompeu Fabra under the supervision of Prof. Xavier Serra,
focusing on the use of technologies from the Music Information Retrieval
field for enhancing music education.