Open ZXY12391 opened 5 months ago
End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detection. 音频模块,请参考该论文github,我们选择去了该音频模型的前半段音频处理过程
End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detection. 音频模块,请参考该论文github,我们选择去了该音频模型的前半段音频处理 请问视觉模块呢?video_processing_model 的video_model,可以分享吗?
End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detection. 音频模块,请参考该论文github,我们选择去了该音频模型的前半段音频处理过程
end to end音频处理是 你论文里写的音频处理是这样的
这篇论文的video encoder用了这个时空提取特征模块的哪里,怎么得到512维的特征的
您好,您成功复现了吗
请问能分享完整的代码吗?