Evaluation of deep neural network-based strategies for the compensation of sensorineural hearing loss
The Journal of the Acoustical Society of America · 01.03.2026 · 159 (3) · 2315-2339
DOI: 10.1121/10.0042995 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, online erschienen am 13.03.2026. Verfasst von Marjoleen Wouters und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Technology, Hearing Technology at Wireless, Acoustics, Environment and Expert Systems, Ghent, Belgium. Hauptthemen laut MEDLINE: Hearing Loss, Sensorineural, Hearing Aids, Deep Learning, Neural Networks, Computer. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 69 Literaturangaben. Gefördert von: Horizon 2020 Research and Innovation Programme, FWO Machine Hearing 2.0, EIC transition grant EarDiTech.
Abstract (Originalsprache)
Conventional hearing aid (HA) algorithms, developed based on computational and non-differentiable auditory processing models, do not typically compensate for cochlear synaptopathy (CS). Traditional HAs apply fixed or rule-based gain adjustments within predefined frequency bands and compression ratios, instead of model-based fitting that numerically optimizes processing from neural representations of normal and impaired hearing. To compensate for combined CS and outer-hair-cell (OHC) loss, deep neural network (DNN)-based closed-loop HA systems are gaining traction. Here, we present several DNN-based HA algorithms that embed personalized, differentiable DNN-based auditory models (dCoNNear) inside a closed-loop system to train personalized HA algorithms compensating for OHC damage and/or CS. The HA algorithms were trained using backpropagation to minimize differences between hearing-impaired and normal-hearing auditory nerve (AN) responses. Performance was evaluated using speech and standard auditory stimuli. Results showed enhanced temporal-envelope (TENV) processing of modulated pure tones, particularly for CS, where sharpening of the TENV led to stronger AN onset responses. Transfer functions indicated that DNN-based HA algorithms applied adaptive level-dependent and frequency-specific gain aligned with OHC damage. The algorithms improved the normalized root mean square error of AN responses compared to NAL-NL2 for certain TIMIT phoneme categories. This evaluation offers insights into how machine-learning approaches outperform traditional HA strategies.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Information Technology, Hearing Technology at Wireless, Acoustics, Environment and Expert Systems, Ghent, Belgium.
- Department of Information Technology, IDLAB, Ghent, Belgium.
ORCID-Profile: Marjoleen Wouters, Chuan Wen, Guy Torfs, Sarah Verhulst
Förderung
- Horizon 2020 Research and Innovation Programme
- FWO Machine Hearing 2.0
- EIC transition grant EarDiTech
Zitieren
APA
Wouters, M., Wen, C., Fráter, A., Torfs, G., & Verhulst, S. (2026). Evaluation of deep neural network-based strategies for the compensation of sensorineural hearing loss. The Journal of the Acoustical Society of America, 159(3), 2315-2339. https://doi.org/10.1121/10.0042995
Vancouver
Wouters M, Wen C, Fráter A, Torfs G, Verhulst S. Evaluation of deep neural network-based strategies for the compensation of sensorineural hearing loss. The Journal of the Acoustical Society of America. 2026;159(3):2315-2339. doi:10.1121/10.0042995
BibTeX
@article{Wouters2026,
author = {Wouters, Marjoleen and Wen, Chuan and Fráter, Attila and Torfs, Guy and Verhulst, Sarah},
title = {Evaluation of deep neural network-based strategies for the compensation of sensorineural hearing loss},
journal = {The Journal of the Acoustical Society of America},
year = {2026},
volume = {159},
number = {3},
pages = {2315--2339},
doi = {10.1121/10.0042995}
}
EUVIMED