VCCA2026 – Hearing-Aid Innovation and Performance Assessment

DNN-based speech enhancement in hearing aids show their advantage only in realistic conditions, exposing the limits of current evaluation methods.

This study evaluates a novel amplitude compression strategy for improved listening outcomes with hearing aids at moderate to high sound levels.

This study evaluates a framework for real-time DOA-guided single, and multi-beam MVDR beamforming for hearing aids using a participant-in-the-loop speech reception test.

We investigated the benefit of scene-aware dynamic range compression (DRC) in comparison to conventional DRC in complex communication scenarios using a database of natural conversations for simulations in a virtual acoustic environment with a-priori knowledge.

A deep learning model trained on 120,000+ consumer ratings of commercial hearing aids predicts listener-rated ease of speech understanding from audio with high accuracy on held-out devices.

This project investigates how adults with hearing aids perceive voice cues and vocal emotions, compared to adults without hearing aids.

This presentation examines the design and integration of a real-time edge-AI neural denoiser for hearing aids, highlighting the challenges of meeting strict latency and computational constraints while improving speech intelligibility, preserving speech quality.