ISCA Archive Interspeech 2021
ISCA Archive Interspeech 2021

TeCANet: Temporal-Contextual Attention Network for Environment-Aware Speech Dereverberation

Helin Wang, Bo Wu, Lianwu Chen, Meng Yu, Jianwei Yu, Yong Xu, Shi-Xiong Zhang, Chao Weng, Dan Su, Dong Yu

In this paper, we exploit the effective way to leverage contextual information to improve the speech dereverberation performance in real-world reverberant environments. We propose a temporal-contextual attention approach on the deep neural network (DNN) for environment-aware speech dereverberation, which can adaptively attend to the contextual information. More specifically, a FullBand based Temporal Attention approach (FTA) is proposed, which models the correlations between the fullband information of the context frames. In addition, considering the difference between the attenuation of high frequency bands and low frequency bands (high frequency bands attenuate faster than low frequency bands) in the room impulse response (RIR), we also propose a SubBand based Temporal Attention approach (STA). In order to guide the network to be more aware of the reverberant environments, we jointly optimize the dereverberation network and the reverberation time (RT60) estimator in a multi-task manner. Our experimental results indicate that the proposed method outperforms our previously proposed reverberation-time-aware DNN and the learned attention weights are fully physical consistent. We also report a preliminary yet promising dereverberation and recognition experiment on real test data.


doi: 10.21437/Interspeech.2021-481

Cite as: Wang, H., Wu, B., Chen, L., Yu, M., Yu, J., Xu, Y., Zhang, S.-X., Weng, C., Su, D., Yu, D. (2021) TeCANet: Temporal-Contextual Attention Network for Environment-Aware Speech Dereverberation. Proc. Interspeech 2021, 1109-1113, doi: 10.21437/Interspeech.2021-481

@inproceedings{wang21l_interspeech,
  author={Helin Wang and Bo Wu and Lianwu Chen and Meng Yu and Jianwei Yu and Yong Xu and Shi-Xiong Zhang and Chao Weng and Dan Su and Dong Yu},
  title={{TeCANet: Temporal-Contextual Attention Network for Environment-Aware Speech Dereverberation}},
  year=2021,
  booktitle={Proc. Interspeech 2021},
  pages={1109--1113},
  doi={10.21437/Interspeech.2021-481}
}