search

fjiang9 / NKF-AEC

Acoustic Echo Cancellation with Nerual Kalman Filtering
239 stars 60 forks source link

More exact model for frequency-domain forward pass #3

Closed tomato18463 closed 2 years ago

tomato18463 commented 2 years ago

Hi,

Thank you for your great project. I have a question about the frequency-domain forward pass in your paper/code. I note your model simply multiplies stft of input signal and filter weights, and the result is an approximation of time-domain convolution. I wonder if you have tried any exact frequency-domain forward pass models, such as overlap saving? And if yes, what's its effect on the performance?

Thanks

fjiang9 commented 2 years ago

@tomato18463 Thanks for your attention. I've also briefly tried the partitioned-block-based frequency-domain Kalman filtering (PBFDKF) based NKF-AEC, but could only get much worse results than the NKF reported in our paper. Maybe you can do such experiments by yourself, and don't forget to tell me your findings : )