aishinchi's repositories
Cone-of-Silence
The Cone of Silence:
Comparison-of-Blind-Source-Separation-techniques
Compare AIRES BSS with TRINICON, ILRMA and AuxIVA (online and offline versions)
Components-Loss
Components loss for neural networks in mask-based speech enhancement
Conv-TasNet
A PyTorch implementation of Conv-TasNet described in "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation" with Permutation Invariant Training (PIT).
DNS-Challenge
This repo contains the scripts, models, and required files for the ICASSP 2021 Deep Noise Suppression (DNS) Challenge.
Dual-Path-RNN-Pytorch
Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation implemented by Pytorch
dual-path-RNNs-DPRNNs-based-speech-separation
A PyTorch implementation of dual-path RNNs (DPRNNs) based speech separation described in "Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation".
ganhacks
starter from "How to Train a GAN?" at NIPS2016
HelloWorld3
试试c++同步
kaldi
This is now the official location of the Kaldi project.
Keras-GAN
Keras implementations of Generative Adversarial Networks.
Leetcode
my leetcode
libri_css
Libri-CSS: dataset and evaluation pipeline
MetricGAN
MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement (ICML 2019, with Travel awards)
MetricGAN_v1
Our implement of MetricGAN.
ProgrammingQuestion
IT Company
speechbrain
A PyTorch-based Speech Toolkit
SpEx_Plus
SpEx+(tied) source code
TAC
transform-average-concatenate (TAC) method for end-to-end microphone permutation and number invariant ad-hoc beamforming.
tensorflow
Computation using data flow graphs for scalable machine learning
Wave-U-Net-for-Speech-Enhancement
Implement [Wave-U-Net](https://arxiv.org/abs/1806.03185) by PyTorch, and migrate it to the speech enhancement area.