Moplast

TasNet-tensorflow

A tensorflow implementation of TasNet (ICASSP 2018)

moplast.github.io

TASNET

Time-domain Audio Separation Network

3d.github.io

ASAM

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

asru2021.github.io

3D spatial features

asteroid

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

CountNet

Deep Neural Network for Speaker Count Estimation

cplxmodule

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

DANet

Dual Attention Network for Scene Segmentation

DaNet-Tensorflow

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

dc_integration

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

gcc-nmf

Real-time GCC-NMF Blind Speech Separation and Enhancement

hopcs

huxpro.github.io

My Blog / Jekyll Themes / PWA

InnerSelf

Experiments & Papers & Research tips

kaldi

This is now the official location of the Kaldi project.

ladder

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

Machine-Learning-Ex

My first machine learning exercise.

models

Models and examples built with TensorFlow

multisensory

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

Nabu-MSSS

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

nn-gev

Neural network supported GEV beamformer

SE_DCUNet

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

SincNet

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

SpectralNet

Deep network that performs spectral clustering

tensorflow-vrnn

A variational recurrent neural network implementation in tensorflow

VAD

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

voicefilter

Unofficial PyTorch implementation of Google AI's VoiceFilter system