xmpx's repositories
SFANC-Window
Real-time Implementation of CNN-based selective fixed-filter active noise control and effectiveness analysis using explainable AI
asteroid_gan_exps
GAN experiments with Asteroid
awesome-speech-enhancement
speech enhancement\speech seperation\sound source localization
bob-plugin-openai-translator
基于 ChatGPT API 的文本翻译、文本润色、语法纠错 Bob 插件,让我们一起迎接不需要巴别塔的新时代!
bottleneck-transformer-pytorch
Implementation of Bottleneck Transformer in Pytorch
BottleneckTransformers
Bottleneck Transformers for Visual Recognition
ConferencingSpeech2022
Non-intrusive Objective Speech Quality Assessment (NISQA) Challenge in Online Conferencing Applications
Conformer
Official code for Conformer: Local Features Coupling Global Representations for Visual Recognition
deeplearningsourceseparation
Deep Recurrent Neural Networks for Source Separation
EEND
End-to-End Neural Diarization
involution
[CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator
Knowledge-Distillation-Zoo
Pytorch implementation of various Knowledge Distillation (KD) methods.
ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
openspeech
Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.
pytorch-image-models
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
SoundSourceSeparation
The code for multi-channel speech enhancement and source separation such as MNMF, MNMF_DP, ILRMA, ILRMA_DP, FastMNMF, FastMNMF_DP, FCA, FastFCA
speechbrain
A PyTorch-based Speech Toolkit
SSL-pretraining-separation
Official repository of our paper: https://arxiv.org/pdf/2010.15366.pdf
Swin-Transformer
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
Tutorial_Separation
This repo summarizes the tutorials, datasets, papers, codes and tools for speech separation and speaker extraction task. You are kindly invited to pull requests.