1) For training, the RNN needs to be fed a full sequence so that it can backpropagate through time. When we actually use the RNN, we also feed a sequence, but we do it one frame at a time because we want the algorithm to be real-time (for batch denoising, we could feed the sequence all at once)
2) Yes, we use a frame size of 20 ms, with 10 ms overlap.
![[personal profile]](https://www.dreamwidth.org/img/silk/identity/user.png)
timeasmymeasure
Re: Input and output data dimensions
Date: 2018-11-08 02:18 pm (UTC)2) Yes, we use a frame size of 20 ms, with 10 ms overlap.