Is it necessary to apply a window after fft?

breizhn / DTLN

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

MIT License

585 stars 161 forks source link

Open shawnyxf opened 1 year ago

shawnyxf commented 1 year ago

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

zqlsnr commented 1 year ago

necessary，不然会有频谱泄露