Suchalongtime

SPMamba

CTCNet

An Audio-Visual Speech Separation Model Inspired by Cortico-Thalamo-Cortical Circuits

LRS3-For-Speech-Separation

Multi-modal speech separation task data generation script on LRS3 data set.

hello-algo

《Hello 算法》：动画图解、一键运行的数据结构与算法教程，支持 Java, C++, Python, Go, JS, TS, C#, Swift, Rust, Dart, Zig 等语言。

NASS

Noise-Aware Speech Separation with Contrastive Learning

gae-pytorch

Graph Auto-Encoder in PyTorch

diffusion-separation

Single channel speech source separation by diffusion process (ICASSP 2023)

Unified-Enhance-Separation

Code for paper "Unifying Speech Enhancement and Separation with Gradient Modulation for End-to-End Noise-Robust Speech Separation"

OCD

Official PyTorch Implementation

LibriMix

An open source dataset for source separation

1d_channel-spatial_se_layers

PyTorch implementation of 1D Channel/Spatial Squeeze and Excitation layers for convnets