The PyTorch-based audio source separation toolkit for researchers || Pretrained models available

A lightweight extension for pytorch that implements complex-valued layers and bayesian sparsification for them.

Deep Complex UNet for speech enhancement, init from "https://github.com/chanil1218/DCUnet.pytorch"

Real-time GCC-NMF Blind Speech Separation and Enhancement

Unofficial PyTorch implementation of Google AI's VoiceFilter system

SincNet is a neural architecture for efficiently processing raw audio samples.

Code for the paper: Audio-Visual Scene Analysis with Self-Supervised Multisensory Features

My Blog / Jekyll Themes / PWA

Dual Attention Network for Scene Segmentation

Deep network that performs spectral clustering

Time-domain Audio Separation Network

Code for Multi Speaker Source Separation with neural networks, build with TensorFlow

Deep Neural Network for Speaker Count Estimation

This is now the official location of the Kaldi project.

Voice activity detection (VAD) toolkit including DNN, bDNN, LSTM and ACAM based VAD. We also provide our directly recorded dataset.

Neural network supported GEV beamformer

Tight integration of spatial and spectral features for BSS with Deep Clustering embeddings

This is the code&dataset for our paper [Modeling Attention and Memory for Auditory Selection in a Cocktail Party Environment. AAAI 2018]

Models and examples built with TensorFlow

A variational recurrent neural network implementation in tensorflow

Tensorflow implementation of "Speaker-independent Speech Separation with Deep Attractor Network"

Ladder network is a deep learning algorithm that combines supervised and unsupervised learning