Deep neural network (DNN)-based noise reduction has emerged as a promising advancement in hearing aid signal processing as a means to improve speech intelligibility in noisy environments for hearing aid wearers. The aim of this study was to investigate the impact of the DNN on speech intelligibility in speech-shaped noise (SSN) and multitalker babble (MTB) when the target speech was coming from the front and from...

Audiologists fitting older adults with mild-to-moderately severe hearing loss should monitor emerging evidence on deep neural network noise reduction; if results show significant gains in speech recognition and reduced listening effort, it may support prioritising AI-enabled hearing aids in this population.

Deep neural network noise reduction represents a potentially significant leap in hearing-aid signal processing, and robust evidence on its clinical benefits for older adults would directly guide fitting decisions and counselling.

1. 01Study assessed deep neural network (DNN) noise reduction in hearing aids for older adults with mild-to-moderately severe hearing loss.
2. 02Outcomes measured included speech recognition accuracy, listening effort (mental fatigue from hearing), and perceived sound quality.
3. 03Published in Trends in Hearing, a peer-reviewed audiology journal.
4. 04Target population — older adults with common hearing loss levels — reflects a large share of typical audiology clinic caseloads.
5. 05Findings could influence clinical guidance on selecting AI-enabled versus conventional hearing-aid processing.

PMID

42125824

DOI

10.1177/23312165261449983.

Journal

Trends in Hearing

Publication type

research_article

Evidence level

2b

Population

Older adults with mild to moderately severe hearing loss

Intervention

Deep neural network-based noise reduction in hearing aids

Comparator

Conventional hearing aid noise reduction (implied comparator)