@inproceedings{921f4d48199143368f96dc06bff84a1e,
title = "Convolutional-Recurrent Neural Networks for Speech Enhancement",
abstract = "We propose an end-to-end model based on convolutional and recurrent neural networks for speech enhancement. Our model is purely data-driven and does not make any assumptions about the type or the stationarity of the noise. In contrast to existing methods that use multilayer perceptrons (MLPs), we employ both convolutional and recurrent neural network architectures. Thus, our approach allows us to exploit local structures in both the frequency and temporal domains. By incorporating prior knowledge of speech signals into the design of model structures, we build a model that is more data-efficient and achieves better generalization on both seen and unseen noise. Based on experiments with synthetic data, we demonstrate that our model outperforms existing methods, improving PESQ by up to 0.6 on seen noise and 0.64 on unseen noise.",
keywords = "Convolutional neural networks, Recurrent neural networks, Regression model, Speech enhancement",
author = "Han Zhao and Shuayb Zarar and Ivan Tashev and Lee, \{Chin Hui\}",
note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 ; Conference date: 15-04-2018 Through 20-04-2018",
year = "2018",
month = sep,
day = "10",
doi = "10.1109/ICASSP.2018.8462155",
language = "English (US)",
isbn = "9781538646588",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2401--2405",
booktitle = "2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings",
address = "United States",
}