Benckmark and experiment for WavLM in AntiSpoofing

csun22 / Synthetic-Voice-Detection-Vocoder-Artifacts

This repository is related to our Dataset and Detection code from the paper: AI-Synthesized Voice Detection Using Neural Vocoder Artifacts accepted in CVPR Workshop on Media Forensic 2023.

https://arxiv.org/abs/2304.13085

MIT License

94 stars 10 forks source link

Benckmark and experiment for WavLM in AntiSpoofing #8

Closed v-nhandt21 closed 5 months ago

v-nhandt21 commented 6 months ago

I found your paper here: https://arxiv.org/pdf/2304.13085

Thanks for your contribution!

Can you provide more detail description or sample source code for WavLM in your paper?

I have tried to reproduce it but the result seen not to be potential!

P/S: Do you know which is the best EER performing on ASVSpoof2019?

csun22 commented 5 months ago

Hi We use STOA WavLM https://huggingface.co/docs/transformers/en/model_doc/wavlm With retraining on our LibriSevoc dataset. For your question, please check the ASVspoof website: https://competitions.codalab.org/competitions/32345. Please let me know if you have any other questions.