Audio Noise Filter using Cycle Consistent Adversarial Network - CycleGAN ANF

Nam Son Nguyen, Tengpeng Li, Xiaoqian Zhang, Bo Sheng, Teng Wang, Jiayin Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish
Title of host publication2019 IEEE 5th International Conference on Computer and Communications, ICCC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages884-888
Number of pages5
ISBN (Electronic)9781728147437
DOIs
StatePublished - Dec 2019
Event5th IEEE International Conference on Computer and Communications, ICCC 2019 - Chengdu, China
Duration: 6 Dec 20199 Dec 2019

Publication series

Name2019 IEEE 5th International Conference on Computer and Communications, ICCC 2019

Conference

Conference5th IEEE International Conference on Computer and Communications, ICCC 2019
CountryChina
CityChengdu
Period6/12/199/12/19

Keywords

  • ASR
  • Deep Neural Network
  • IoT
  • NLP

Fingerprint Dive into the research topics of 'Audio Noise Filter using Cycle Consistent Adversarial Network - CycleGAN ANF'. Together they form a unique fingerprint.

  • Cite this

    Nguyen, N. S., Li, T., Zhang, X., Sheng, B., Wang, T., & Wang, J. (2019). Audio Noise Filter using Cycle Consistent Adversarial Network - CycleGAN ANF. In 2019 IEEE 5th International Conference on Computer and Communications, ICCC 2019 (pp. 884-888). [9064433] (2019 IEEE 5th International Conference on Computer and Communications, ICCC 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCC47050.2019.9064433