Heng-Jui Chang's Projects
π» Solutions to the three programming assignments of the course Algorithms 2019 Fall, NTU EE.
A curated list of awesome self-supervised methods
A comprehensive list of awesome self-supervised speech representation learning papers.
A command line tool that helps use the "Zero Ressource Challenge" benchmarks
A simple website for visualizing course maps ππΊ.
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.
Joint CTC-Attention End-to-end Speech Recognition - PyTorch Implementation (Deep Learning for Human Language Processing Special Project)
End-to-End Speech Processing Toolkit
Easy to use scripts for evaluating word vectors on a variety of tasks.
π§π»π¨πΌπ±πΎββοΈπΆπ» Face Image Morphing: an OpenCV and NumPy Implementation
Final Project of Data Structure and Programming 2018 Fall, NTUEE
Demo of Deep Learning-based Image Geometric Rectification
π¨ HW1 (shading and transformation) of the course Interactive Computer Graphics, NTU CSIE.
Mandarin Medical Dialogue Analysis with Pytorch.
A mini, simple, and fast end-to-end automatic speech recognition toolkit.
Machine Learning Spring 2019, NTUEE
Phoneme segmentation using pre-trained speech models
A simple receptive field calculator for convolutional neural networks (CNN).
Self-Supervised Speech Pre-training and Representation Learning Toolkit.
Preprocessing and downloading scripts for the Santa Barbara Corpus of Spoken American English (SBCSAE).
Competition for best expository article on cutting-edge ML research
This is the code for the SpeechTokenizer presented in the SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models. Samples are presented on
Official code for Interspeech 2023 paper "Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clustering"
Utilities for preprocessing the Switchboard and WSJ corpora in Python3
Taiwan Mahjong Game - Final Project of Computer Programming 2017 Fall, NTUEE
Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes