Optimising Hearing Aid Fittings for Speech in Noise with a Differentiable Hearing Loss Model
This work addresses the challenge of improving hearing aid performance in noisy settings for individuals with hearing loss, representing an incremental advancement in customization.
The paper tackled the problem of hearing aids providing variable benefits across noisy environments by proposing a data-driven machine learning technique to customize fittings for speech in noise, using a differentiable hearing loss model optimized via back-propagation, with objective evaluation showing advantages over general prescriptive fittings.
Current hearing aids normally provide amplification based on a general prescriptive fitting, and the benefits provided by the hearing aids vary among different listening environments despite the inclusion of noise suppression feature. Motivated by this fact, this paper proposes a data-driven machine learning technique to develop hearing aid fittings that are customised to speech in different noisy environments. A differentiable hearing loss model is proposed and used to optimise fittings with back-propagation. The customisation is reflected on the data of speech in different noise with also the consideration of noise suppression. The objective evaluation shows the advantages of optimised custom fittings over general prescriptive fittings.