An Intelligent Directionality System for Hearing Aids Incorporating Deep Neural Networks: Improving Speech Understanding While Preserving Spatial Awareness
Daniel Marquardt, Jinjun Xiao, Al Ganeshkumar, Jingjing Xu, Larissa Taylor, Martin McKinney, David A. Fabry, Achintya K. Bhowmik · 2026
Read An Intelligent Directionality System for Hearing Aids Incorporating Deep Neural Networks: Improving Speech Understanding While Preserving Spatial Awareness by Daniel Marquardt, Jinjun Xiao, Al Ganeshkumar, Jingjing Xu, Larissa Taylor, Martin McKinney, David A. Fabry, Achintya K. Bhowmik (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13600042.txt.
Description
Hearing aids that focus on speech from the front can leave users deaf to the world around them. Daniel Marquardt and co-authors build a neural network direction system that aims to keep both speech and spatial awareness in a 2026 study.
The system learns spatial filtering from data rather than fixed rules, enhancing target speech while leaving environmental sounds audible. It was tested against standard direction modes with word tests, clarity ratings, and listener preference. An automated speech-to-text score gave an objective yardstick beside the human ones. Speech thresholds improved over both the legacy directional mode and an all-around mode, notably for speech coming from the side. Users kept access to surrounding sound, a safety point for daily life.
Catalog record
| CREATOR | Daniel Marquardt, Jinjun Xiao, Al Ganeshkumar, Jingjing Xu, Larissa Taylor, Martin McKinney, David A. Fabry, Achintya K. Bhowmik |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 51 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |