Nonlinear Residual Echo Suppression Based on Multi-Stream Conv-TasNet

Hongsheng Chen, Teng Xiang, Kai Chen, Jing Lu


Acoustic echo cannot be entirely removed by linear adaptive filters due to the nonlinear relationship between the echo and far-end signal. Usually a post processing module is required to further suppress the echo. In this paper, we propose a residual echo suppression method based on the modification of fully convolutional time-domain audio separation network (Conv-TasNet). Both the residual signal of the linear acoustic echo cancellation system, and the output of the adaptive filter are adopted to form multiple streams for the Conv-TasNet, resulting in more effective echo suppression while keeping a lower latency of the whole system. Simulation results validate the efficacy of the proposed method in both single-talk and double-talk situations.


 DOI: 10.21437/Interspeech.2020-2234

Cite as: Chen, H., Xiang, T., Chen, K., Lu, J. (2020) Nonlinear Residual Echo Suppression Based on Multi-Stream Conv-TasNet. Proc. Interspeech 2020, 3959-3963, DOI: 10.21437/Interspeech.2020-2234.


@inproceedings{Chen2020,
  author={Hongsheng Chen and Teng Xiang and Kai Chen and Jing Lu},
  title={{Nonlinear Residual Echo Suppression Based on Multi-Stream Conv-TasNet}},
  year=2020,
  booktitle={Proc. Interspeech 2020},
  pages={3959--3963},
  doi={10.21437/Interspeech.2020-2234},
  url={http://dx.doi.org/10.21437/Interspeech.2020-2234}
}