Name: Hui Lu
Type: User
Company: The Chinese University of Hong Kong
Bio: Final-year PhD student at the Chinese University of Hong Kong. Focus on unsupervised disentangled speech representation learning.
Location: Hong Kong SAR, China
Blog: light1726.github.io
Hui Lu's Projects
Implementation for paper "Disentangled Speech Representation Learning for One-Shot Cross-Lingual Voice Conversion Using ß-VAE"
FAIR Sequence Modeling Toolkit
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
Efficient neural speech synthesis
This is not the official kaldi repository. It is better to fork https://github.com/kaldi-asr/kaldi or https://github.com/vimalmanohar/kaldi instead.
PyTorch Implementation of Google's Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling
A WaveNet-based vocoder that converts mel-spectrogram to raw wave in parallel
make ppgs kaldi implentation
tf2.0 based voice conversion based on PPGs
pattern recognition final homework
Some basic examples of playing with RL
Self-Supervised Speech Pre-training and Representation Learning Toolkit
This repository follows papers and reports on discrete speech representation learning and speech tokenization methods for speech language modeling.
The implementation of paper "SpeechTripleNet: End-to-End Disentangled Speech Representation Learning for Content, Timbre and Prosody"
Voice Conversion Tool Kit
tensorflow implementation of tacotron2
LaTeX Thesis Template for Tsinghua University
A Flow-based Generative Network for Speech Synthesis