KUN's repositories
IRM-based-Speech-Enhancement-using-LSTM
Ideal Ratio Mask (IRM) Estimation based Speech Enhancement using LSTM
segan-pytorch
SEGAN pytorch implementation https://arxiv.org/abs/1703.09452
segan_pytorch
Speech Enhancement Generative Adversarial Network in PyTorch
text-detection-ctpn
text detection mainly based on ctpn model in tensorflow, id card detect, connectionist text proposal network
AudioVerification
CCU DeepLearning Final Project
Autoregressive-Predictive-Coding
Autoregressive Predictive Coding: An unsupervised autoregressive model for speech representation learning
deepspeech.pytorch
Speech Recognition using DeepSpeech2.
DNS-Challenge
This repo contains the scripts, models, and required files for the Deep Noise Suppression (DNS) Challenge.
End-to-end-ASR-Pytorch
This is an open source project (formerly named Listen, Attend and Spell - PyTorch Implementation) for end-to-end ASR implemented with Pytorch, the well known deep learning toolkit.
LAS_Mandarin_PyTorch
Listen, attend and spell Model and a Chinese Mandarin Pretrained model (中文-普通话 ASR模型)
Listen-Attend-Spell
A PyTorch implementation of Listen, Attend and Spell (LAS), an End-to-End ASR framework.
LPS_extraction
The script is to extract log-power-spectrum features for speech enhancement and bandwidth extension.
malaya-speech
Speech Toolkit for bahasa Malaysia, https://malaya-speech.readthedocs.io/
ML2021-Spring
**Official** 李宏毅 (Hung-yi Lee) 機器學習 Machine Learning 2021 Spring
Mockingjay-Speech-Representation
Official Implementation of Mockingjay in Pytorch
Model-Attacking-Defending
In this project, I implemented FGSM and the basic iterative method to attack a pre-trained model. Then I tried to protect my model by doing randomization to the images before I feed them into my model.
self-supervised-speech-recognition
speech to text with self-supervised learning based on wav2vec 2.0 framework
softer-NMS
Softer-NMS: Rethinking Bounding Box Regression for Accurate Object Detection
speech_feature_extractor
Some useful features of speech process, such as MFCC, gammatone filterbank, GFCC, spectrum(power spectrum and log-power spectrum), Amplitude Modulation Spectrum(AMS) and so on.