The current focus of the Audio Signal Processing Lab of the MTG is to combine audio signal processing methods with machine learning and semantic technologies to analyze sound and music content. We work on the creation and support of large sound and music collections with which we then extract musically relevant information. Our research is partly supported by several EU and national projects.


Xavier Serra, Faculty, Head of lab Eduardo Fonseca, PhD student
Bariş Bozkurt, Postdoc Minz Won PhD  student
Dmitry Bogdanov, Postdoc Alastair Porter, Researcher
Frederic Font, Postdoc     Andrés Ferraro, Researcher
Rafael Caro Repetto  PhD   student  Oriol Romaní, Researcher
Rong Gong  PhD   student Pablo Alonso, Researcher
Jordi Pons PhD  student  Emir Demirel, Master student
Xavier Favory   PhD    student Vsevolod Eremenko, Master student