Demo Cases
Below are some examples of synthesized audio corresponding to different scenarios and different schemes of Voice Clone attacks mentioned in the paper.
Watermark Fidelity
| File Name | LJ001-0001.wav | LJ001-0002.wav | LJ001-0003.wav | LJ001-0004.wav | LJ001-0005.wav |
| Original Audio | |
|
|
|
|
| wm-1 | |
|
|
|
|
| wm-2 | |
|
|
|
|
Voice Clone
Fastspeech2_tuned_Hifi-GAN_wm-1
| File Name | 1.wav | 2.wav | 3.wav | 4.wav | 5.wav |
| Pretrained | |
|
|
|
|
| Watermarked | |
|
|
|
|
Fastspeech2_tuned_Hifi-GAN_wm-2
| File Name | 1.wav | 2.wav | 3.wav | 4.wav | 5.wav |
| Pretrained | |
|
|
|
|
| Watermarked | |
|
|
|
|
Fastspeech2_pre-trained_Hifi-GAN
| File Name | 1.wav | 2.wav | 3.wav | 4.wav | 5.wav |
| Pretrained | |
|
|
|
|
| wm-1 | |
|
|
|
|
| wm-2 | |
|
|
|
|
Fastspeech2_Griffin-Lim
| File Name | 1.wav | 2.wav | 3.wav | 4.wav | 5.wav |
| Pretrained | |
|
|
|
|
| wm-1 | |
|
|
|
|
| wm-2 | |
|
|
|
|
Tacotron2_tuned_Hifi-GAN_wm-1
| File Name | 1.wav | 2.wav | 3.wav | 4.wav | 5.wav |
| Pretrained | |
|
|
|
|
| Watermarked | |
|
|
|
|
Tacotron2_tuned_Hifi-GAN_wm-2
| File Name | 1.wav | 2.wav | 3.wav | 4.wav | 5.wav |
| Pretrained | |
|
|
|
|
| Watermarked | |
|
|
|
|
Tacotron2_pre-trained_Hifi-GAN
| File Name | 1.wav | 2.wav | 3.wav | 4.wav | 5.wav |
| Pretrained | |
|
|
|
|
| wm-1 | |
|
|
|
|
| wm-2 | |
|
|
|
|
Tacotron2_Griffin-Lim
| File Name | 1.wav | 2.wav | 3.wav | 4.wav | 5.wav |
| Pretrained | |
|
|
|
|
| wm-1 | |
|
|
|
|
| wm-2 | |
|
|
|
|
VITS
| File Name | 1.wav | 2.wav | 3.wav | 4.wav | 5.wav |
| Pretrained | |
|
|
|
|
| wm-1 | |
|
|
|
|
| wm-2 | |
|
|
|
|
| Mp3 Compression 8 kbps | |
|
|
|
|
| Low Pass Filtering 2 kHz | |
|
|
|
|
| Harmful Combined | |
|
|
|
|
| Resampling 16K | |
|
|
|
|
| Mp3 Compression 64 kbps | |
|
|
|
|
| Regular Combined | |
|
|
|
|
| FSVC | |
|
|
|
|
| RFDLM | |
|
|
|
|
| FSVC Overwriting | |
|
|
|
|
| RFDLM Overwriting | |
|
|
|
|
| The Proposed Overwriting | |
|
|
|
|
| The Proposed* Overwriting | |
|
|
|
|
| Trained with Domain Loss | |
|
|
|
|
| Mask Position2 | |
|
|
|
|
| Mask Position3 | |
|
|
|
|
PaddleSpeech-English
| File Name | 1.wav | 2.wav | 3.wav | 4.wav | 5.wav | 6.wav | 7.wav | 8.wav | 9.wav | 10.wav |
| p225 | |
|
|
|
|
|
|
|
|
|
| p226 | |
|
|
|
|
|
|
|
|
|
| p227 | |
|
|
|
|
|
|
|
|
|
| p228 | |
|
|
|
|
|
|
|
|
|
| p229 | |
|
|
|
|
|
|
|
|
|
| p230 | |
|
|
|
|
|
|
|
|
|
PaddleSpeech-Chinese
| File Name | 1.wav | 2.wav | 3.wav | 4.wav | 5.wav | 6.wav | 7.wav | 8.wav | 9.wav | 10.wav |
| D11 | |
|
|
|
|
|
|
|
|
|
| D12 | |
|
|
|
|
|
|
|
|
|
| D4 | |
|
|
|
|
|
|
|
|
|
| D6 | |
|
|
|
|
|
|
|
|
|
| D7 | |
|
|
|
|
|
|
|
|
|
| D8 | |
|
|
|
|
|
|
|
|
|
Voice-Clone-App
| File Name | 1.wav | 2.wav | 3.wav | 4.wav | 5.wav | 6.wav | 7.wav | 8.wav | 9.wav | 10.wav |
| p225 | |
|
|
|
|
|
|
|
|
|
| p226 | |
|
|
|
|
|
|
|
|
|
| p227 | |
|
|
|
|
|
|
|
|
|
| p228 | |
|
|
|
|
|
|
|
|
|
| p229 | |
|
|
|
|
|
|
|
|
|
| p230 | |
|
|
|
|
|
|
|
|
|
so-vits-svc
| Right Here Waiting |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| Converted |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
VAE Reconstruction
| File Name | LJ001-0001.wav | LJ001-0002.wav | LJ001-0003.wav | LJ001-0004.wav | LJ001-0005.wav |
| Watermarked | |
|
|
|
|
| MelVAE | |
|
|
|
|
| VAE of AudioLDM | |
|
|
|
|