Speech intelligibility prediction based on a physiological model of the human ear and a hierarchical spiking neural network
The Journal of the Acoustical Society of America · 2024
DOI: 10.1121/10.0028584 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, 2024. Verfasst von Yinxin Kou und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechatronic Engineering, China University of Mining and Technology, Xuzhou 221116, China. Hauptthemen laut MEDLINE: Speech Intelligibility, Neural Networks, Computer, Speech Perception. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: National Natural Science Foundation of China, the Postgraduate Research & Practice Innovation Program of Jiangsu Province, Graduate Innovation Program of China University of Mining and Technology.
Abstract (Originalsprache)
A speech intelligibility (SI) prediction model is proposed that includes an auditory preprocessing component based on the physiological anatomy and activity of the human ear, a hierarchical spiking neural network, and a decision back-end processing based on correlation analysis. The auditory preprocessing component effectively captures advanced physiological details of the auditory system, such as retrograde traveling waves, longitudinal coupling, and cochlear nonlinearity. The ability of the model to predict data from normal-hearing listeners under various additive noise conditions was considered. The predictions closely matched the experimental test data under all conditions. Furthermore, we developed a lumped mass model of a McGee stainless-steel piston with the middle-ear to study the recovery of individuals with otosclerosis. We show that the proposed SI model accurately simulates the effect of middle-ear intervention on SI. Consequently, the model establishes a model-based relationship between objective measures of human ear damage, like distortion product otoacoustic emissions, and speech perception. Moreover, the SI model can serve as a robust tool for optimizing parameters and for preoperative assessment of artificial stimuli, providing a valuable reference for clinical treatments of conductive hearing loss.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Mechatronic Engineering, China University of Mining and Technology, Xuzhou 221116, China.
- Key Laboratory of Otorhinolaryngology-Head & Neck Surgery, Ministry of Education, Beijing Tongren Hospital Affiliated to Capital Medical University, Beijing 100730, China.
- Beijing Engineering Research Center of Hearing Technology, Beijing 100730, China.
- College of Otolaryngology Head and Neck Surgery, Chinese PLA General Hospital, Beijing 100853, China.
- Key Lab of Hearing Science, Ministry of Education, Beijing 100853, China.
ORCID-Profile: Houguang Liu, Jianhua Yang
Förderung
- National Natural Science Foundation of China
- the Postgraduate Research & Practice Innovation Program of Jiangsu Province
- Graduate Innovation Program of China University of Mining and Technology
Zitieren
APA
Kou, Y., Liu, H., Wang, J., Guo, W., Yang, J., & Yang, S. (2024). Speech intelligibility prediction based on a physiological model of the human ear and a hierarchical spiking neural network. The Journal of the Acoustical Society of America. https://doi.org/10.1121/10.0028584
Vancouver
Kou Y, Liu H, Wang J, Guo W, Yang J, Yang S. Speech intelligibility prediction based on a physiological model of the human ear and a hierarchical spiking neural network. The Journal of the Acoustical Society of America. 2024. doi:10.1121/10.0028584
BibTeX
@article{Kou2024,
author = {Kou, Yinxin and Liu, Houguang and Wang, Jie and Guo, Weiwei and Yang, Jianhua and Yang, Shanguo},
title = {Speech intelligibility prediction based on a physiological model of the human ear and a hierarchical spiking neural network},
journal = {The Journal of the Acoustical Society of America},
year = {2024},
doi = {10.1121/10.0028584}
}
EUVIMED