Name: Riccardo Miccini
Type: User
Company: GN Audio / Technical University of Denmark
Bio: PhD student at GN Audio / Technical University of Denmark, researching noise suppression and speech quality estimation using deep learning.
Location: Copenhagen, Denmark
Blog: https://miccio-dk.github.io/
Riccardo Miccini's Projects
Read data from the last.fm APIs
Leslie speaker simulator, made in FAUST + JUCE
read from MPU6050 Gyro + Accelerometer and MA3-P12 Magnetic shaft encoder using an LPC11C24
read from MPU6050 Gyro + Accelerometer and MA3-P12 Magnetic shaft encoder using an LPC11C24
Documentation for AAU's Machine Learning workstation
Boilerplate for writing a paper with Markdown/Latex and Pandoc
Project for "Deep Learning for Music Information Retrieval @ CCRMA" 2022
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment
OpenVINO™ Toolkit repository
My pandoc-based project skeleton.
Toolbox of models, callbacks, and datasets for AI/ML researchers.
Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset
personal sleep data visualisation and analysis
Attempt to make a sequencer/drum machine/synth with the STM32F746 Discovery board.
DTU Diplom '15 - SUSIE Class - Web interface for reading sensors data from a XBee network
Arduino-based drum machine and master keyboard, with MIDI support and sound synthesis
Arduino library for generating plots on a TFT_eSPI display object (e.g. ESP32 T-Display board)
Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.
Small python HTTP server for remotely controlling mechanical apparatus (VIKING Dataset, 2019)
Physical model of "The Voice of the Dragon"
A Python Compiler Design Toolkit
XRT: eXpressive Rotational Tool