Audio-WestlakeU / FullSubNet

PyTorch implementation of "FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement."
https://fullsubnet.readthedocs.io/en/latest/
MIT License
553 stars 157 forks source link

有关look-ahead的疑问 #59

Open LXP-Never opened 2 years ago

LXP-Never commented 2 years ago

hi,我理解的look-ahead是使用多少未来帧,可是我在看您代码的过程中发现是在后面补两帧0,noisy_mag = F.pad(noisy_mag, [0, self.look_ahead]),最后只取第二帧之后的数据output = sb_mask[:, :, :, self.look_ahead:]

是不是在推理的过程中,不需要补0,而是直接处理3帧,结果出一帧(output = sb_mask[:, :, :, self.look_ahead:])之后,然后流式的一帧进 一帧出