ISCA Archive Interspeech 2021
ISCA Archive Interspeech 2021

Joint Online Multichannel Acoustic Echo Cancellation, Speech Dereverberation and Source Separation

Yueyue Na, Ziteng Wang, Zhang Liu, Biao Tian, Qiang Fu

This paper presents a joint source separation algorithm that simultaneously reduces acoustic echo, reverberation and interfering sources. Target speeches are separated from the mixture by maximizing independence with respect to the other sources. It is shown that the separation process can be decomposed into cascading sub-processes that separately relate to acoustic echo cancellation, speech dereverberation and source separation, all of which are solved using the auxiliary function based independent component/vector analysis techniques, and their solving orders are exchangeable. The cascaded solution not only leads to lower computational complexity but also better separation performance than the vanilla joint algorithm.


doi: 10.21437/Interspeech.2021-1950

Cite as: Na, Y., Wang, Z., Liu, Z., Tian, B., Fu, Q. (2021) Joint Online Multichannel Acoustic Echo Cancellation, Speech Dereverberation and Source Separation. Proc. Interspeech 2021, 1144-1148, doi: 10.21437/Interspeech.2021-1950

@inproceedings{na21_interspeech,
  author={Yueyue Na and Ziteng Wang and Zhang Liu and Biao Tian and Qiang Fu},
  title={{Joint Online Multichannel Acoustic Echo Cancellation, Speech Dereverberation and Source Separation}},
  year=2021,
  booktitle={Proc. Interspeech 2021},
  pages={1144--1148},
  doi={10.21437/Interspeech.2021-1950}
}