Curriculum vitae

Things I have been doing

Work History

Sound and Music Understanding Team, RIKEN AIP

Rennes, France
September 2021 - Present

Postoctoral Researcher — Physics-Informed Neural Networks for Speech Enhancement

Supervisors: Kazuyoshi Yoshii

LETG (UMR 6554), CNRS

Rennes, France
May 2021 - July 2022

Postoctoral Researcher — Physics-Informed Neural Networks for Geophysics

Supervisors: Thomas Corpetti

Multispeech Team, INRIA

Nancy, France
October 2016 - May 2017

Research Internship (Erasmus Program) — Developing algorithms for Music Interference Reduction from a Guassian Process perspective. This method consider the case of full-length concert recordings.

Supervisors: Antoine Liuktus.

Zamperla s.r.l

Vicenza, Italy
October 2014 - January 2016

R&D Engineer — Virtual reality on amusements rides and PC-to-PLC communication

Supervisors: Francesco DeLuca.

Acropark

Trento, Italy
Summers 2009 - 2014

Rescuer and Instructors — (Summer work) rope climbing guide and animator

Education

Ph.D. in Signal Processing

INRIA, Rennes, France, 2020.
Thesis: Echo-aware Signal Processing for Audio Scene Analysis
Supervisors: Antoine Deleforge, Nancy Bertin.
Keywords: Acoustic Echoes, Audio scene analysis, Room impulse response, Channel estimation, Supervised learning, Deep Neural Networks.

Exchange Program

Bar-Ilan University, Tel Aviv, Isreal, 2019.
3-month visiting
Supervisors: Sharon Gannot, Pinchas Tandeitnik.

M.Sc. in Computer Engineering

Universitá degli Studi di Padova, Padova, Italy, 2017.
Thesis: Gaussian Processes for Music Interference Reduction
Supervisors: Antoine Liuktus, Nicola Orio.

Erasmus exchange

Inria, Nancy, France, 2017.
6-months of Erasums+ Traineeship program where worked on my M.Sc Thesis.
Supervisors: Antoine Liuktus.

Erasmus exchange

Aalborg Universitet, Copenhagen, Denmark, 2016.
6-months of Erasmus+ for Studying program where I attended course of the M.Sc in Sound and Music Computing.
Supervisors: Federico Avanzini, Stefania Serafin.

B.Sc. in Information Engineering

Universitá degli Studi di Padova, Padova, Italy, 2014.
Thesis: Sequential Feature Selection: Algorithms And Applications For Audio Information Retrieval
Supervisors: Antonio Rodá.

Skills

Languages

  • Italian (Native)
  • English (Fluent)
  • French (Conversational)
  • Japanese (Beginner)

Expertise

    Machine and Deep Learning, Audio Signal Processing, Signal processing, Optimization, Algorithms, Stochastic modeling, Probability theory, Information theory

Programming

    Python, MATLAB, Latex, git, Liquid/HTML, Java, Android, PureData, Processing, Arduino.

IDE, Tools

    Jupyter Notebooks, Pytorch, Weka, VSCode, Sublime and Atom, Vim and Tmux, Unity.

Operating Systems and Applications

    Linux, Windows and Office Suite, OAR Clusters, Prezi, Slides and Beamer, Gimp/Draw.io.

DAW and Music Tools

    Ableton, Reaper, PureData, Sonic Visualizer and Audacity, Renoise.
my 2-page curriculum vitae is available [here](http://diegodicarlo.com/pdf/cv.pdf).