Speaker
Octav Chipara
Abstract
Approximately 44.1 million adults in the US had hearing loss in 2020. Untreated hearing impairment affects communication and can contribute to social isolation, depression, dementia, and reduced quality of life. Hearing aid amplification is the primary intervention for sensorineural hearing loss and related psychosocial consequences. Unfortunately, only 15–30% of those who could benefit from hearing aids use them. The adoption rates are even worse for lower-income people and racial and ethnic minorities disproportionately affected by the high cost of hearing care. The state-of-the-art hearing aid signal-processing and configuration face several fundamental challenges, including: (1) Existing personalization approaches configure only part of the parameters of hearing aids. (2) The personalization process prescribes the same configuration for patients with similar hearing loss, even though these patients usually prefer significantly different configurations. (3) The growing adoption of over-the-counter (OTC) hearing aids promises to reduce the access barriers to hearing care. However, the burden of configuring them is shifted from audiologists to end-users, who currently receive little help.
I will present new signal processing algorithms and configuration methods that empower people with hearing loss to meet their individualized hearing needs. The approaches for personalizing hearing aids have different trade-offs between the degree of personalization, the amount of user effort required to find a satisfactory configuration, and their effectiveness in handling hearing losses of varying severity and auditory environments of varying difficulty. Our approach provides more personalization options than state-of-the-art OTC hearing aids by using different sub-band processing gains, compression parameters, and noise reduction settings depending on the auditory context. These techniques are most suitable for patients with mild-to-moderate sensorineural hearing loss.
Bio
Octav Chipara is a Professor in the Department of Computer Science at the University of Iowa. Chipara’s research focuses on the systems, networking, and software engineering aspects of developing mobile health (mHealth) systems that continuously monitor and infer the health status of patients. His work combines the design of communication protocols, middleware, and programming tools with large-scale real-world deployments of working systems.