A new dataset of 104k listener ratings for commercial hearing-aid recordings is used to train a Whisper-difference MLP that predicts ease-of-understanding scores and outperforms HASPIv2 on held-out devices.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Large-Scale Database and Predictive Model of Listener-Rated Ease of Speech Understanding in Commercial Hearing Aids
A new dataset of 104k listener ratings for commercial hearing-aid recordings is used to train a Whisper-difference MLP that predicts ease-of-understanding scores and outperforms HASPIv2 on held-out devices.