A Deep Learning Approach to Active Noise Control

Hao Zhang, DeLiang Wang


We formulate active noise control (ANC) as a supervised learning problem and propose a deep learning approach, called deep ANC, to address the nonlinear ANC problem. A convolutional recurrent network (CRN) is trained to estimate the real and imaginary spectrograms of the canceling signal from the reference signal so that the corresponding anti-noise can eliminate or attenuate the primary noise in the ANC system. Large-scale multi-condition training is employed to achieve good generalization and robustness against a variety of noises. The deep ANC method can be trained to achieve active noise cancellation no matter whether the reference signal is noise or noisy speech. In addition, a delay-compensated strategy is introduced to address the potential latency problem of ANC systems. Experimental results show that the proposed method is effective for wide-band noise reduction and generalizes well to untrained noises. Moreover, the proposed method can be trained to achieve ANC within a quiet zone.


 DOI: 10.21437/Interspeech.2020-1768

Cite as: Zhang, H., Wang, D. (2020) A Deep Learning Approach to Active Noise Control. Proc. Interspeech 2020, 1141-1145, DOI: 10.21437/Interspeech.2020-1768.


@inproceedings{Zhang2020,
  author={Hao Zhang and DeLiang Wang},
  title={{A Deep Learning Approach to Active Noise Control}},
  year=2020,
  booktitle={Proc. Interspeech 2020},
  pages={1141--1145},
  doi={10.21437/Interspeech.2020-1768},
  url={http://dx.doi.org/10.21437/Interspeech.2020-1768}
}