CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems
Resource type
Authors/contributors
- Wu, Haibin (Author)
- Tseng, Yuan (Author)
- Lee, Hung-yi (Author)
Title
CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems
Abstract
CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems
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. This dataset is released for this purpose.
See our paper and Github for more details on using our dataset.
Acknowledgement
CodecFake is created based on the VCTK dataset.
Citation Key
_bf
Citation
Wu, H., Tseng, Y., & Lee, H. (n.d.). CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems [Dataset]. Retrieved https://huggingface.co/datasets/rogertseng/CodecFake
Audio Data
Link to this record