LDCCRN: Robust Deep Learning-based Speech Enhancement

Chun Yin Yeung, Steve W.Y. Mung, Yat Sze Choy, Daniel P.K. Lun

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

Abstract

Deep learning-based speech enhancement methods make use of their non-linearity properties to estimate the speech and noise signals, especially the non-stationary noise. DCCRN, in particular, achieves state-of-the-art performance on speech intelligibility. However, the non-linear property also causes concern about the robustness of the method. Novel and unexpected noises can be generated if the noisy input speech is beyond the operation condition of the method. In this paper, we propose a hybrid framework called LDCCRN, which integrates a traditional speech enhancement method LogMMSE-EM and DCCRN. The proposed framework leverages the strength of both approaches to improve the robustness in speech enhancement. While the DCCRN continues to remove the non-stationary noise in the speech, the novel noises generated by DCCRN, if any, are effectively suppressed by LogMMSE-EM. As shown in our experimental results, the proposed method achieves better performance over the traditional approaches measured with standard evaluation methods.

Original languageEnglish
Title of host publicationInternational Workshop on Advanced Imaging Technology, IWAIT 2022
EditorsMasayuki Nakajima, Shogo Muramatsu, Jae-Gon Kim, Jing-Ming Guo, Qian Kemao
PublisherSPIE
ISBN (Electronic)9781510653313
DOIs
Publication statusPublished - 30 Apr 2022
Event2022 International Workshop on Advanced Imaging Technology, IWAIT 2022 - Hong Kong, China
Duration: 4 Jan 20226 Jan 2022

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume12177
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference2022 International Workshop on Advanced Imaging Technology, IWAIT 2022
Country/TerritoryChina
CityHong Kong
Period4/01/226/01/22

Keywords

  • complex-network
  • deep learning denoise
  • Speech enhancement

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this