Jiachen Lian's Projects
Our submission to the ASVspoof 2019: Automatic Speaker Verification Spoofing and Countermeasures Challenge
An experimental open-source attempt to make GPT-4 fully autonomous.
A self-supervised learning framework for audio-visual speech
Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc.
End-to-End Speech Processing Toolkit
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Demo for 2022 Interspeech
Config files for my GitHub profile.
Pytorch Implementation of 2021 Interspeech Paper
Pytorch Implementation of MUCKO(2020 IJCAI)
Demo for 2022 ICASSP
Phoneme segmentation using pre-trained speech models
An official reimplementation of the method described in the INTERSPEECH 2021 paper - Speech Resynthesis from Discrete Disentangled Self-Supervised Representations.
Release a public wind power dataset
In defence of metric learning for speaker recognition
A Weakly Supervised Forced Alignment for disluent speech