Matteo Fabbri's Projects
Web-app for automatic generation and computer-assisted manipulation of melodic and rhythmic musical patterns, with built-in synthesisers, transport and BPM controls.
Material and assignments of the 'Audio Signal Processing for Music Applications' course by Xavier Serra at the Sound and Music Computing Master of the Music Technology Group, UPF, Barcelona.
Quantitative analysis of pitch and rhythmic similarity between arbitrary .xml scores ; correlation analysis in the Jingju Music repertoire, as degree of heterophony between different Banshis. Using the Music21 python library (http://web.mit.edu/music21/).
Gender Classification from audio files using the LibriSpeech dataset
Max 4 Live device generating melodies and exposing several ways of controls over probabilities and numerical ranges of pitches, harmonies and rhythms. Inspired from Patter by Adam Florin
Convolutional-based supervised regression task for extracting high level timbral features from drums sound files, useful to condition a real time Neural Sound Synthesiser on continuous intuitive controls.
A system for generating music playlists based on the results of audio content analysis. The MusAV dataset is used as a music audio collection, music descriptors are extracted using Essentia, and a simple user interface is used to generate playlists based on these descriptors.
A model which can identify similar musical artists based on user listening history from ListenBrainz.
Config files for my GitHub profile.
Multi-tier conditioning RNN for audio texture generation. Used in the SMC_thesis/Conditioned_neural_Audio_synthesis Project repository.
Pure Data GUI and python/pytorch backend, neural MIDI Drum patterns generator capable of interpolating between specific sets of latent variables. From the 2023 course 'Computational Music Creativity' of the Sound and Music Computing Master at UPF University in Barcelona.
Various Neural Network Architectures for Supervised Tonic classification using the mridangam_stroke dataset, and supervised instrument classification on the TinySOL dataset.
Synthetic sounds datasets and real sounds datasets of waterflow sounds for the repo 'Neural-Texture-Sound-Synthesis-with-physically-driven-continuous-controls'.
PyTorch-based trained Neural Networks for the Neural-Texture-Sound-Synthesis-with-physically-driven-continuous-controls project
Neural Texture Sound Synthesis exposing physically-driven continuous controls using synthetic-to-real unsupervised Domain Adaptation
Polyphonic Karplus Strong synthesiser and 2 tracks 32 steps sequencer implemented with Pure Data.
Chatbot assistant for the DTIC Department of Pompeu Fabra University in Barcelona, implemented using RASA
Research MATLAB Project which analyses Inharmonic sounds, tries to find its most likely fundamental frequency and harmonic template, and performs spectral mapping to make it sound more harmonic while retaining most of its sound quality.
A Max MSP-based video sonifier, mapping RGB pixel values to DSP parameters. Used by Sound Designer Matteo Bendinelli for PhACES, a crowdsourcing interactive exhibit by Alessandro Cracolici (https://www.phest.info/alessandro-cracolici), for the 2022 edition of the PhEST International Festival of Art and Photography of Monopoli, Puglia, Italy.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent