yuhogun0908 / complex_pf Goto Github PK

In this repository you will find exemplary results from our ICASSP paper Combining Adaptive Filtering and Complex-valued Deep Postfiltering for Acoustic Echo Cancellation.

In addition, you can access our implementation of the proposed complex-valued postfilter in the folder source_code.

Here you will find five different examples produced using the synthetic test dataset provided as part of the ICASSP 2021 AEC Challenge:

https://github.com/microsoft/AEC-Challenge

You can download individual audio examples by clicking on the respective download buttons or by using left click then save link as.

Unprocessed microphone signal	Residual signal after linear adaptive filter	Real-valued Postfilter	Complex-valued Postfilter

Unprocessed microphone signal	Residual signal after linear adaptive filter	Real-valued Postfilter	Complex-valued Postfilter

Unprocessed microphone signal	Residual signal after linear adaptive filter	Real-valued Postfilter	Complex-valued Postfilter

Unprocessed microphone signal	Residual signal after linear adaptive filter	Real-valued Postfilter	Complex-valued Postfilter

Unprocessed microphone signal	Residual signal after linear adaptive filter	Real-valued Postfilter	Complex-valued Postfilter

Please cite our work as

@INPROCEEDINGS{,

title={Combining Adaptive Filtering and Complex-valued Deep Postfiltering for Acoustic Echo Cancellation},

booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing},

author={Halimeh, Mhd Modar and Haubner, Thomas and Briegleb, Annika and Schmidt, Alexander and Kellermann, Walter},

year={2021},

month={June},

}

M. M. Halimeh, T. Haubner, A. Briegleb, A. Schmidt, and W. Kellermann, "Combining Adaptive Filtering and Complex-valued Deep Postfiltering for Acoustic Echo Cancellation," IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, Canada, June, 2021.

TY - CONF

TI - Combining Adaptive Filtering and Complex-valued Deep Postfiltering for Acoustic Echo Cancellation

T2 - IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

AU - M. M. Halimeh

AU - T. Haubner

AU - A. Briegleb

AU - A. Schmidt

AU - W. Kellermann

PY - 2021

JO - IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Y1 - June 2021