Evaluating the Benefit of Hearing Aids with Motion-Based Beamformer Steering in a Real-World Setup
Bibliographic record
Abstract
Background:Conventional directional hearing aid microphone technology would obstruct listening intentions in walking situations when the talker and listener walk side by side. The purpose of the current study was to evaluate hearing aids that use a motion sensor to address listening needs during walking. Methods:Participants were 22 older adults with moderate-to-severe hearing loss and experience using hearing aids. Each participant completed two walks in randomized order, one walk with each of two hearing aid programs: 1) a conventional classifier that activated an adaptive, multiband beamformer in loud environments and 2) a classifier that additionally utilized motion-based beamformer steering. Participants walked along a pre-defined track and completed tasks assessing speech understanding and environmental awareness. Results:Most participants preferred the motion-based beamformer steering for speech understanding, environmental awareness, overall listening, and sound quality (p<0.05). Additionally, measures of speech understanding (p<0.01) and localization of sound stimuli (p<0.05) were significantly better with the motion-based beamformer steering than with the conventional classifier.Conclusion:The results suggest that hearing aid users benefit from classifiers that use motion sensor input to adapt the signal processing according to the user’s activity. The real-world setup of this study had limitations but also high ecological validity.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".