ISmallFish's Projects
Repo for counting stars and contributing. Press F to pay respect to glorious developers.
Implement A Convolutional Recurrent Neural Network for Real-Time Speech Enhancement by PyTorch.
The PyTorch-based audio source separation toolkit for researchers
A curated list of awesome Speaker Diarization papers, libraries, datasets, and other resources.
A comprehensive list of pytorch related content on github,such as different models,implementations,helper libraries,tutorials etc.
simple delaysum, MVDR and CGMM-MVDR
Implementation of the CGMM-MVDR beamforming
multi-channel target speech extraction with channel decorrelation and target speaker adaptation
Code for synchronising all CHiME-5 audio signals for use in CHiME-6
Conferencing Speech Challenge
A PyTorch implementation of Conv-TasNet described in "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation" with Permutation Invariant Training (PIT).
A PyTorch implementation of "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation"
Communication-Cost Aware Microphone Selection For Neural Speech Enhancement with Ad-hoc Microphone Arrays
Deep Neural Network for Speaker Count Estimation
Code examples in pyTorch and Tensorflow for CS230
A tensorflow implementation of "Deep Convolutional Generative Adversarial Networks"
A tensorflow implementation for Deep clustering: Discriminative embeddings for segmentation and separation
deep clustering method for single-channel speech separation
Distributed semi-constrained microphone arrays
Code for the book Deep Learning with PyTorch by Eli Stevens, Luca Antiga, and Thomas Viehmann.
This repo contains the scripts, models, and required files for the Deep Noise Suppression (DNS) Challenge.
Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation implemented by Pytorch
Pytorchππ is delicious, just eat it! ππ
End-to-End Speech Processing Toolkit
up to date simple useragent faker with real world database
Python library for Room Impulse Response (RIR) simulation with GPU acceleration
This script can separate from mixed audio file contains multiple voices to separated audio file on each voice.
Ideal Ratio Mask (IRM) Estimation based Speech Enhancement using LSTM
Config files for my GitHub profile.