Evaluating a Deep Neural Noise-Reduction Algorithm for Hearing Aids

NCT07287774 | Recruiting FDA Device

• 1 other identifier: 1406014978-2
• Study Type: interventional
• Target: 50
• Locations: 1 country
• Sites: 1

Brief Summary

This study is designed to understand how different hearing-aid noise-reduction technologies affect a listener's ability to hear speech in noisy environments. Participants will listen to speech at several background-noise levels while trying different processing settings. By comparing performance across these conditions, the study aims to identify which types of noise reduction improve speech intelligibility the most. We expect that some noise-reduction strategies will help listeners understand speech better than others, especially in more difficult listening situations.

Conditions

Hearing Loss, Cochlear

Keywords

hearing aids; noise reduction; speech understanding; listening in noise; speech perception; hearing loss; background noise

Outcome Measures

Primary Outcomes (2)

• Immediate Speech Recall

  Accuracy of immediate verbal repetition of the first sentence in each dual-sentence trial. Participants hear Sentence A followed by Sentence B; they immediately repeat Sentence A aloud. Performance is scored as the number of keywords correctly recalled per sentence. This measure assesses speech intelligibility under different noise-reduction processing conditions and signal-to-noise ratios.

  During a single study visit (approximately 1-2 hours), assessed immediately following presentation of each dual-sentence trial.

• Delayed Speech Recall (Cognitive Demand)

  Accuracy of delayed recall of the second sentence in each dual-sentence trial. Participants hear Sentence A followed by Sentence B, repeat the first sentence immediately, and then type the second sentence from memory. Performance is scored as the number of keywords correctly recalled per sentence. This measure reflects the combined effects of speech intelligibility, working-memory load, and cognitive demand under each noise-reduction processing condition and signal-to-noise ratio.

  During a single study visit (approximately 1-2 hours), assessed immediately following presentation of each dual-sentence trial.

Study Arms (2)

Hearing Aid Noise-Reduction Processing

EXPERIMENTAL

Participants complete all noise-reduction conditions (Off, Low, High) at all tested signal-to-noise ratios in a within-subject crossover design.

Device: Hearing Aid Noise Reduction - Off; Device: Hearing Aid Noise Reduction - Low; Device: Hearing Aid Noise Reduction - High

Signal-to-Noise Ratio

EXPERIMENTAL

Relative speech and noise levels

Other: Negative SNR; Other: Zero signal-to-noise ratio; Other: Positive SNR

Interventions

Hearing Aid Noise Reduction - Low DEVICE

Neural noise suppression using the lower-strength algorithm parameters.

Hearing Aid Noise-Reduction Processing

Hearing Aid Noise Reduction - High DEVICE

Neural noise suppression using the higher-strength algorithm parameters.

Hearing Aid Noise-Reduction Processing

Zero signal-to-noise ratio OTHER

Equal speech and noise levels

Signal-to-Noise Ratio

Positive SNR OTHER

Speech levels higher than noise levels

Signal-to-Noise Ratio

Hearing Aid Noise Reduction - Off DEVICE

No neural noise suppression applied. Baseline processing condition.

Hearing Aid Noise-Reduction Processing

Negative SNR OTHER

Noise levels higher than speech levels

Signal-to-Noise Ratio

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• A hearing aid candidate with mild-to-moderate cochlear hearing loss, based on audiometric profile (at least 20 dB of hearing loss at 2000 Hz, with progressively worse hearing levels at higher frequencies).

You may not qualify if:

• Normal hearing
• Severe or profound hearing loss
• Conductive hearing loss
• Neural hearing loss

Sponsors & Collaborators

• Purdue University: lead
• Oticon: collaborator

Study Sites (1)

Purdue University

West Lafayette, Indiana, 47905, United States

RECRUITING

Related Links

• Purdue EAR Lab

MeSH Terms

Conditions

Hearing Loss, Sensorineural; Hearing Loss

Condition Hierarchy (Ancestors)

Hearing Disorders; Ear Diseases; Otorhinolaryngologic Diseases; Sensation Disorders; Neurologic Manifestations; Nervous System Diseases; Signs and Symptoms; Pathological Conditions, Signs and Symptoms

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: DOUBLE
• Who Masked: PARTICIPANT, INVESTIGATOR
• Purpose: TREATMENT
• Intervention Model: CROSSOVER
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Associate Professor

Model Details: Participants complete all noise-reduction conditions in a fully counterbalanced crossover design. Each participant is exposed to every processing mode at each signal-to-noise ratio, with the order of conditions varied across participants to reduce learning effects and order bias.

Study Record Dates

• First Submitted: December 3, 2025
• First Posted: December 17, 2025
• Study Start: October 16, 2025
• Primary Completion: April 30, 2026
• Study Completion: April 30, 2026
• Last Updated: December 17, 2025

Record last verified: 2025-12

Data Sharing

• IPD Sharing: Will share
• Shared Documents: STUDY PROTOCOL, ICF

Locations

US (1)