@inproceedings{4edfe83c2cb44cf7aa2cd5e250235c39,
title = "Audio Noise Filter using Cycle Consistent Adversarial Network - CycleGAN ANF",
abstract = "Speech enhance methods base on traditional digital signal processing (DSP) algorithms or adaptive filters can effectively suppress stationary noises. However, they don't provide viable solution for the variety of non-stationary noises that exist in our everyday life. Smart voice assistants such as Google Home and Alexa deteriorate their performance mostly due to non-stationary noises. In this paper we introduce CycleGAN ANF, a neural network approach that can learn to reduce both stationary and non-stationary noises, totally unsupervised. CycleGAN ANF is capable of reducing undesired interference by reading in a raw audio sample from a set X (speech mixed with noises) and transforming it so that it sound as if it belongs in set Y (clean speech). Our experiments demonstrate that without labels and when trained on unparalleled; relatively small vocabulary of speech datasets, CycleGAN ANF can achieve significant improvements without the ground assumptions of nature and form of the noise.",
keywords = "ASR, Deep Neural Network, IoT, NLP",
author = "Nguyen, {Nam Son} and Tengpeng Li and Xiaoqian Zhang and Bo Sheng and Teng Wang and Jiayin Wang",
note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 5th IEEE International Conference on Computer and Communications, ICCC 2019 ; Conference date: 06-12-2019 Through 09-12-2019",
year = "2019",
month = dec,
doi = "10.1109/ICCC47050.2019.9064433",
language = "English",
series = "2019 IEEE 5th International Conference on Computer and Communications, ICCC 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "884--888",
booktitle = "2019 IEEE 5th International Conference on Computer and Communications, ICCC 2019",
}