Giters

breizhn / DTLN

Tensorflow 2.x implementation of the DTLN real time speech denoising model. With TF-lite, ONNX and real-time audio processing support.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Is it necessary to apply a window after fft?

shawnyxf opened this issue · comments

commented

Hi, i noticed that there isn't any window applied after fft or ifft process. Is this unnecessary for this model?

commented

necessary，不然会有频谱泄露