ilaria-manco

multimodal-ml-music

List of academic resources on Multimodal ML for Music

word2wave

Word2Wave: a framework for generating short audio samples from a text prompt using WaveGAN and COALA.

muscall

Official implementation of "Contrastive Audio-Language Learning for Music" (ISMIR 2022)

muscaps

Source code for "MusCaps: Generating Captions for Music Audio" (IJCNN 2021)

song-describer

Song Describer is a data collection platform for annotating music with textual descriptions.

mulap

Official implementation of "Learning Music Audio Representations Via Weak Language Supervision" (ICASSP 2022)

music-audio-tagging-pytorch

A PyTorch implementation of the musicnn model for music audio tagging

bela-sampler

MIDI controlled sampler/sequencer on the Bela platform

mir-datasets

Simple collection of MIR datasets with metadata and links

astro-image-processing

Code for the implementation of a cluster detection algorithm to analyse an optical image and study the distribution of galaxies within it

multid-optimisation

Computational Physics project to extract the average lifetime of the D0 meson

oslo-model

Implementation, analysis and visualisation of the Oslo rice pile Model

torch-pitch-shift

Pitch-shift audio clips quickly with PyTorch (CUDA supported)! Additional utilities for searching efficient transformations are included.

awesome-livecoding

All things livecoding

c4dmpoole

caption-evaluation-tools

Tools for the evaluation of audio captioning.

complex-networks

Implementation and analysis of the Barabasi-Albert model for complex growing networks

ECS7002P-MarioAI

FDM-pendulum

Code for the Computational Physics project on a single and double pendulum's equations of motions using finite difference methods

gaussian-mixtures

Implementation of the EM algorithm for Gaussian Mixture Models

hidden-markov-models

musicnn

Pronounced as "musician", musicnn is a set of pre-trained deep convolutional neural networks for music audio tagging.