jordipons

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

music-audio-tagging-at-scale-models. Tensorflow implementation of the models used in "End-to-end learning for music audio tagging at scale"

sklearn-audio-transfer-learning. A didactic toolkit to rapidly prototype audio classifiers with pre-trained Tensorflow models and Scikit-learn

neural-classifiers-with-few-audio. Training neural audio classifiers with few data − https://arxiv.org/abs/1810.10274

musicnn-training. Tensorflow code for training deep convolutional neural networks for music audio tagging

DRNN4ASS. Deep Recurrent Neural Network for Audio Source Separation

EUSIPCO2017. Music auto-tagging experiments for the paper entitled "Timbre Analysis of Music Audio Signals with Convolutional Neural Networks".

source-separation-wavenet. A neural network for end-to-end music source separation

elmarc. Repository containg experiments with Extreme Learning Machines And Reservoir Computing, ELMARC.

AudioSetOntologyTree. Tree visualization of the AudioSet Ontology - https://github.com/audioset/ontology

ICASSP2017. Designing efficient architectures for modeling temporal features with convolutional neural networks

CBMI2016. Experimenting with musically motivated convolutional neural networks

ai-music-artistic-trends. A collection (337 artworks) of AI music released before July 31, 2025.

ChordProfiles. A Matlab function that provides a SIMPLE framework where ALL the binary chord profiles are properly defined.