skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

Correntropy-Based Multi-objective Multi-channel Speech Enhancement

Circuits, systems, and signal processing, 2022-09, Vol.41 (9), p.4998-5025 [Peer Reviewed Journal]

The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022 ;The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022. ;ISSN: 0278-081X ;EISSN: 1531-5878 ;DOI: 10.1007/s00034-022-02016-4

Full text available

Citations Cited by
  • Title:
    Correntropy-Based Multi-objective Multi-channel Speech Enhancement
  • Author: Cui, Xingyue ; Chen, Zhe ; Yin, Fuliang ; Xu, Xianfa
  • Subjects: Artificial neural networks ; Circuits and Systems ; Electrical Engineering ; Electronics and Microelectronics ; Engineering ; Instrumentation ; Machine learning ; Performance degradation ; Power spectra ; Signal,Image and Speech Processing ; Speech ; Speech processing
  • Is Part Of: Circuits, systems, and signal processing, 2022-09, Vol.41 (9), p.4998-5025
  • Description: Although deep learning-based methods have greatly advanced the speech enhancement, their performance is intensively degraded under the non-Gaussian noises. To combat the problem, a correntropy-based multi-objective multi-channel speech enhancement method is proposed. First, the log-power spectra (LPS) of multi-channel noisy speech are fed to the bidirectional long short-term memory network with the aim of predicting the intermediate log ideal ratio mask (LIRM) and LPS of clean speech in each channel. Then, the intermediate LPS and LIRM features obtained from each channel are separately integrated into a single-channel LPS and a single-channel LIRM by fusion layers. Next, the two single-channel features are further fused into a single-channel LPS and finally fed to the deep neural network to predict the LPS of clean speech. During training, a multi-loss function is constructed based on correntropy with the aim of reducing the impact of outliers and improving the performance of overall network. Experimental results show that the proposed method achieves significant improvements in suppressing non-Gaussian noises and reverberations and has good robustness to different noises, signal–noise ratios and source–array distances.
  • Publisher: New York: Springer US
  • Language: English
  • Identifier: ISSN: 0278-081X
    EISSN: 1531-5878
    DOI: 10.1007/s00034-022-02016-4
  • Source: ProQuest Central
Back to results list
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait