# Computational Models of Normal and Impaired Hearing

> **NIH NIH R01** · MASSACHUSETTS INSTITUTE OF TECHNOLOGY · 2024 · $417,741

## Abstract

PROJECT SUMMARY
Humans with normal hearing excel at deriving information about the world from sound. Our auditory abilities
represent stunning computational feats that only recently have been replicated to any extent in machine systems.
And yet our auditory abilities are highly vulnerable, being greatly compromised in listeners with hearing
impairment, cochlear implants, and auditory neurodevelopmental disorders, particularly in the presence of noise.
Difficulties in recognition often lead to frustration and social isolation, and are not adequately addressed by
current hearing aids, implants, and remediation strategies. The long-term goal of the proposed research is to
build models that replicate our abilities to recognize and localize sounds, and to use these models to facilitate
improved prosthetic devices and therapeutic interventions. The development of more effective devices and
therapies is currently limited by an incomplete understanding of the link between peripheral auditory processing
and auditory behavior. We propose to leverage machine learning to build models that instantiate this link by
performing realistic tasks given simulated peripheral auditory input, and to evaluate the models with large-scale
behavioral assays. Aim 1 will build models of recognition and localization of real-world sounds, and compare
them to human recognition and localization judgments. Aim 2 will augment these models with selective attention,
and compare them to human performance on recognition and localization tasks that require selective attention.
Aim 3 will introduce different types of simulated hearing loss to these models and attempt to isolate distinct
behavioral signatures of different types of hearing loss. The research will generate models that can predict
human auditory behavior along with new behavioral benchmarks with which to evaluate these and future models.
The results will clarify the role of peripheral auditory processing in real-world auditory abilities, setting the stage
for new strategies for remediation.

## Key facts

- **NIH application ID:** 10981923
- **Project number:** 1R01DC021464-01A1
- **Recipient organization:** MASSACHUSETTS INSTITUTE OF TECHNOLOGY
- **Principal Investigator:** Josh H McDermott
- **Activity code:** R01 (R01, R21, SBIR, etc.)
- **Funding institute:** NIH
- **Fiscal year:** 2024
- **Award amount:** $417,741
- **Award type:** 1
- **Project period:** 2024-06-11 → 2029-05-31

## Primary source

NIH RePORTER: https://reporter.nih.gov/project-details/10981923

## Citation

> US National Institutes of Health, RePORTER application 10981923, Computational Models of Normal and Impaired Hearing (1R01DC021464-01A1). Retrieved via AI Analytics 2026-05-24 from https://api.ai-analytics.org/grant/nih/10981923. Licensed CC0.

---

*[NIH grants dataset](/datasets/nih-grants) · CC0 1.0*