sampleCNN

audio-pretrained-model

A collection of Audio and Speech pre-trained models.

musicTagging_MSD

DeepAudioClassification

Finding the genre of a song with Deep Learning

tensorflow-image-wavenet

This is a TensorFlow implementation of the WaveNet generative neural network architecture https:/...

deep_audio_features

Pytorch implementation of deep audio embedding calculation

audio-pipeline

CFP_NeuralNetwork

wavenet

Keras WaveNet implementation

audio_spec_vqvae

Implementation of Unsupervised Audio Spectrogram Compression using Vector Quantized Autoencoders

MC-CNN-python

a python implementation of MC-CNN

ismir2018-artist

An implementation of "Representation Learning of Music using Artist labels, ISMIR, 2018" in Keras

tensorflow-recipes

A collection of TensorFlow (Tensorpack) implementations of recent deep learning approaches includ...

CNN_sentence

CNNs for sentence classification