VCCA2026 – Computational Audiology & Digital Hearing Research

We use audiogram-derived phoneme confusions to adapt self-supervised speech representations for listener-aware hearing-aid processing without requiring behavioral listener responses.

Clinical cochlear implant registries suffer from structured, non-random missingness in key variables, and a measurement-aware design is essential to enable reliable, generalizable predictive modeling and personalized care.

This study explores differential privacy in synthetic audiometric data, simulating epsilon noise levels that preserve statistical validity for open reproducible research.

This presentation outlines a part‑task simulation framework in audiology education that addresses clinical training capacity and assessment challenges by progressively developing and integrating discrete clinical competencies into holistic simulated cases.

A review and discussion of some auditory models used for closed-loop hearing loss compensation.

Design and validation of a software tool for labeling and machine learning–based classification of cortical auditory evoked potentials.

Using characteristics-based filter parameter estimation methods applied to recent physiological and forward masking data, we derived updated human auditory filter parameters.

 We demonstrate that the proposed corticothalamic circuitry between the MGB, PAC, and TRN can be implemented as a stable, biologically plausible computational model, with future applications in selective attention and tinnitus research.

 This presentation showcases student‑led digital arts innovations in audiology, including virtual learning platforms, serious games, and virtual reality tools designed to enhance clinical training, hearing health education, accessibility, and learner engagement.

Analyzing the distribution of keyword recognition accuracy for sentences presented in competing speech can provide estimates of how often listeners are affected by informational and energetic masking.

This study investigates the effect of hearing acuity on daily-life conversation characteristics, detected using a machine learning algorithm trained on acoustic features and Ecological Momentary Assessment data.

This study compares perceived and objective time in audiometric testing using a fast Bayesian method (BAL) and the conventional Hughson-Westlake (HW) method in young musicians, examining the impact of stimulus structure and anticipation. Results show that HW leads to an underestimation of perceived duration, whereas BAL does not. We investigate the sequence of tones generated by each protocol as the output of a dynamical system, whose temporal predictability properties are analyzed.

 NEMA+ Watch extends ecological momentary assessment to smartwatches, enabling low-burden, user-initiated reporting of real-world listening experiences alongside contextual and physiological data.

Replacing old PTA-4 averages with R-based algorithms for high-precision audiology.