
A method for enhancing speech and warning signals based on parallel convolutional neural networks in a noisy environment
Author(s) -
Ha Lim Kang,
Sung Dae Na,
Myoung Nam Kim
Publication year - 2021
Publication title -
technology and health care
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.281
H-Index - 44
eISSN - 1878-7401
pISSN - 0928-7329
DOI - 10.3233/thc-218015
Subject(s) - computer science , speech recognition , intelligibility (philosophy) , convolutional neural network , noise (video) , filter (signal processing) , artificial intelligence , computer vision , philosophy , epistemology , image (mathematics)
Digital hearing aids are based on technology that amplifies sound and removes noise according to the frequency of hearing loss in hearing loss patients. However, within the noise removed is a warning sound that alert the listener; the listener may be exposed to danger because the warning sound is not recognized.