Sangwook Han's repositories
Factorized-TDNN
PyTorch implementation of the Factorized TDNN (TDNN-F) from "Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks" and Kaldi
pytorch_xvectors
Deep speaker embeddings in PyTorch, including x-vectors. Code used in this work: https://arxiv.org/abs/2007.16196
attention-is-all-you-need-pytorch
A PyTorch implementation of the Transformer model in "Attention is All You Need".
byol-pytorch
Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in Pytorch
Conference-Acceptance-Rate
Statistics of acceptance rate for the main AI conference
Conv-TasNet-1
A PyTorch implementation of Conv-TasNet described in "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation" with Permutation Invariant Training (PIT).
Conv-TasNet-3
Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation Pytorch's Implement
Dual-Path-RNN-Pytorch
Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation implemented by Pytorch
ECANet
Code for ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
keras-attention-mechanism
Attention mechanism Implementation for Keras.
keras-tcn
Keras Temporal Convolutional Network.
meta-SR
Pytorch implementation of Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs (Interspeech, 2020)
meta-tasnet
A PyTorch implementation of Meta-TasNet from "Meta-learning Extractors for Music Source Separation
pase
Problem Agnostic Speech Encoder
pyannote-audio
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, speaker embedding
pytorch-gradual-warmup-lr
Gradually-Warmup Learning Rate Scheduler for PyTorch
pytorch-kaldi
pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.
pytorch-kaldi-neural-speaker-embeddings
A light weight neural speaker embeddings extraction based on Kaldi and PyTorch.
pytorch-loss
label-smooth, amsoftmax, focal-loss, triplet-loss. Maybe useful
RawNet
Reproducing RawNet paper with Keras and additional experiments with PyTorch.
Res2Net-PretrainedModels
(ImageNet pretrained models) The official pytorch implemention of the TPAMI paper "Res2Net: A New Multi-scale Backbone Architecture"
Speech-Transformer
A PyTorch implementation of Speech Transformer, an End-to-End ASR with Transformer network on Mandarin Chinese.
TDNN-1
Time delay neural network (TDNN) implementation in Pytorch using unfold method
the-incredible-pytorch
The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.
torch-plda
PyTorch implementation of PLDA as described in https://ravisoji.com/assets/papers/ioffe2006probabilistic.pdf
voxceleb_trainer
In defence of metric learning for speaker recognition