Yuankun Xie

Codecfake. This is the official repo of our work titled "The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio".

All-Type-ADD. This is the repo of our work titled “Detect All-Type Deepfake Audio: Wavelet Prompt Tuning for Enhanced Auditory Perception”

FSD-Dataset. This repository presents FSD dataset for song deepfake detection.

TDL-ADD. This is the pytorch implementation of our work titled "An Efficient Temporary Deepfake Location Approach Based Embeddings for Partially Spoofed Audio Detection”.

AT-ADD-Baseline. Python

ALLM-ADD-FT-GRPO. Python

REFD. This is the pytorch implementation of our work titled "Generalized Source Tracing: Detecting Novel Audio Deepfake Algorithm with Real Emphasis and Fake Dispersion Strategy”.

VITS-chinese-finetune. 语音合成VITS 纯中文微调

ST-Codecfake. This is the repo of our work titled “Neural Codec Source Tracing: Toward Comprehensive Attribution in Open-Set Condition”.

ALM-ADD. This is the repository of our work titled “Does Current Deepfake Audio Detection Model Effectively Detect ALM-based Deepfake Audio?”

ADD-W2V2-LCNN-19LA0.6. Audio deepfake detection model train on 19LA, EER = 0.63%

FSW. This is the dataset repo of our work titled “Fake Speech Wild: Detecting Deepfake Speech on Social Media Platform”.