Optical Microphone-Based Speech Reconstruction System With Deep Learning for Individuals With Hearing Loss.

Journal: IEEE transactions on bio-medical engineering
PMID:

Abstract

OBJECTIVE: Although many speech enhancement (SE) algorithms have been proposed to promote speech perception in hearing-impaired patients, the conventional SE approaches that perform well under quiet and/or stationary noises fail under nonstationary noises and/or when the speaker is at a considerable distance. Therefore, the objective of this study is to overcome the limitations of the conventional speech enhancement approaches.

Authors

  • Yu-Min Lin
  • Ji-Yan Han
  • Cheng-Hung Lin
    Department of Electrical Engineering and Biomedical Engineering Research Center, Yuan Ze University, Jungli 32003, Taiwan.
  • Ying-Hui Lai