Mathematics and Signal Processing in Acoustics
Tel. +43 51581-2554
Andrés Marafioti studied audio engineering at the National University of Tres de Febrero (UNTREF), Buenos Aires, Argentina. He graduated with the Master's thesis entitled "Automatic identification of acoustical musical instruments", in which he developed a system that uses machine-learning techniques to identify which out of 21 different instruments is the main one in an audio file.
Since September 2017 he is part of the Acoustic Research Institute's workgroup "Mathematics and Signal Processing in Acoustics", where he works on sound generation and restoration for the project "Modern methods for the restoration of lost information in digital signals" (MERLIN).
His main interests include intelligence augmentation, music computing, object oriented programming, and signal processing, in particular for audio applications.
- AutoEncoders applied to audio inpainting of short gaps.
- Generalized methods for audio inpainting of long gaps.
- Generative Adversarial Networks applied to audio.