Table 6 SNR of the hidden representation ha for each SNR of the input audio signal
From: Unsupervised domain adaptation for lip reading based on cross-modal knowledge distillation
| SNR of audio signal | 30dB | 20dB | 10dB | 0dB |
|---|---|---|---|---|
| SNR of ha | 14.14dB | 7.23dB | 2.69dB | -0.14dB |