CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems
Interspeech 2024
TL;DR: We show that better detection of deepfake speech from codec-based TTS systems can be achieved by training models on speech re-synthesized with neural audio codecs. We also release the CodecFake dataset for this purpose.
We provide the CodecFake dataset in two forms:
-
from datasets import load_dataset a = load_dataset("rogertseng/CodecFake")
See instructions under detection for more.
TBA, see dataset_creation
CodecFake is created based on the VCTK dataset, licensed under CC-BY-4.0.