ARO Symposium Forum

Emerging Capabilities for Evaluating Human Hearing

Chair: Dennis Barbour, Co-chairs: David Moore and Jan-Willem Wasmann

Below you can watch Symposium 13: ‘Emerging Capabilities for Evaluating Human Hearing’ recorded at the ARO conference on 22 February 2021.

Presenters: Dennis Barbour, Josh McDermott, De Wet Swanepoel, Jan-Willem Wasmann, Elle O’brien and David Moore.

It is still posible to perform the DIN-test Demo or to leave comments and questions for the presenters.

Presentation Dennis Barbour


A limitation of science and medicine as currently practiced is how data are apportioned toward desired ends. Improper inference compounds with limited data to result in irreproducibility of scientific trends and suboptimal treatment decisions for patients. Increases in data quantity can alleviate only a portion of this limitation. Recent advances in modern audiologic assessments have shown that more informative inference tools can be constructed without the concomitant data explosion that would typically accompany such advances. These modern machine learning tools, with successful application toward translational questions of hearing, can serve as templates for parallel advances throughout science and medicine.

Presentation Josh McDermott

Following shut-down of in-person human-subject experiments due to COVID-19, interest in online experimentation increased substantially, but with understandable concerns about stimulus presentation and data quality. Our lab has been using online psychoacoustic experiments extensively since 2014. This talk will summarize what we have learned. I will present example results obtained this way, tips for success, and pitfalls to avoid. The main overall message: online experiments can yield large quantities of data that are of comparable quality to what you would get in-lab for many tasks, provided you take some basic steps to promote reasonable sound quality and participant compliance.

Presentation De Wet Swanepoel

More than 90% of adults with hearing loss could be served using low- or no-touch models of audiological care enabled by mobile technologies. Recent work on binaural digits-in-noise consumer tests demonstrates potential to accurately detect and estimate hearing loss severity, and escalate referrals for potential medical risk. Air conduction pure tone and digits-in-noise thresholds can differentiate conductive and sensorineural losses with sensitivity and specificity more than 94%. Advances in self-test options combined with AI otoscopy, support comprehensive low- and no-touch services for the provision of hearing care with ongoing telehealth support.

Presentation Jan-Willem Wasmann

At-home testing options to monitor the hearing abilities of cochlear implant (CI) recipients will reshape CI aftercare. The COVID-19 pandemic has turned “nice-to-have” features (e.g., an at-home evaluation app for CI) into a “must-have” due to heightened barriers to visiting a clinic. At-home test capability allows clinicians to monitor listening performance in daily lives at the places that matter most to our patients. Uncontrolled factors including circadian rhythms, attention, motivation, and listening fatigue might lead to false alarms in a clinic. However, when interpreted correctly, those data can give our patient advice more ecological validity.

Presentation Elle O’Brien

As emphasis grows for large-scale data collection, remote audiological services and machine learning applications to translational and basic science research, researchers will face new technological complexities. For example, data-driven approaches frequently require cloud computing and storage, as well as software approaches such as web and mobile development. Furthermore, many existing datasets may be underutilized because they are difficult to organize, maintain, and share. This talk will survey critical technologies for enabling machine learning and big data research, and propose practical methods for building the infrastructure of labs and research organizations to support emerging practices in hearing assessment.

Presentation Dave Moore

Big datasets relevant to human hearing include specifically curated research resources, such as Human Brain and Connectome Projects, and myriad clinical, device-based and online resources compiled for other reasons. Increasingly, hearing research can interrogate these resources without expensive or impractical experimental data collection. The resources are particularly useful for examining associations, including causal connections, between hearing and demographics, biology or disease. Combined with online evaluations and, increasingly, longitudinal designs, the power and convenience of these resources have barely been tapped. I will focus on utilization of UK Biobank to explore links between speech perception, cognition, cortical connectivity and genetics.


Barbour, D. L.; DiLorenzo, J. C.; Sukesan, K. A.; Song, X. D.; Chen, J. Y.; Degen, E. A.; Heisey, K. L.; and Garnett, R. (2019). Conjoint psychometric field estimation for bilateral audiometry. Behavior Research Methods, 51(3): 1271–1285. 2019.

Barbour, D. L.; Howard, R. T.; Song, X. D.; Metzger, N.; Sukesan, K. A.; DiLorenzo, J. C.; Snyder, B. R. D.; Chen, J. Y.; Degen, E. A.; Buchbinder, J. M.; and Heisey, K. L. (2019). Online Machine Learning Audiometry. Ear and Hearing, 40(4): 918–926. August 2019.

Christensen, J. H., Saunders, G. H., Porsbo, M., & Pontoppidan, N. H. (n.d.). The everyday acoustic environment and its association with human heart rate: Evidence from real-world data logging with hearing aids and wearables. Royal Society Open Science, 8(2), 201345.

Crum, P. (2019). Hearables will monitor your brain and body to augment your life. IEEE Spectrum

De Sousa, K. C., Swanepoel, D. W., Moore, D. R., Myburgh, H. C., & Smits, C. (2020). Improving Sensitivity of the Digits-In-Noise Test Using Antiphasic Stimuli. Ear and Hearing, 41(2), 442–450.

Ezzatian, P., Pichora-Fuller, M. K., & Schneider, B. A. (2010). Do Circadian Rhythms Affect Adult Age-Related Differences in Auditory Performance? Canadian Journal on Aging / La Revue Canadienne Du Vieillissement, 29(2), 215–221.

Hornsby, B. W. Y., Naylor, G., & Bess, F. H. (2016). A Taxonomy of Fatigue Concepts and Their Relation to Hearing Loss. Ear and Hearing, 37, 136S.
Keidser, G., Naylor, G., Brungart, D. S., Caduff, A., Campos, J., Carlile, S., Carpenter, M. G., Grimm, G., Hohmann, V., Holube, I., Launer, S., Lunner, T., Mehra, R., Rapport, F., Slaney, M., & Smeds, K. (2020). The Quest for Ecological Validity in Hearing Science: What It Is, Why It Matters, and How to Advance It. Ear and Hearing, 41 Suppl 1(Suppl 1), 5S-19S.
McPherson, M.J., McDermott, J.H. (2020) Time-dependent discrimination advantages for harmonic sounds suggest efficient coding for memory. Proceedings of the National Academy of Sciences, 117, 32169-32180.
McPherson, M.J., McDermott, J.H. (2018) Diversity in pitch perception revealed by task dependence. Nature Human Behavior, 2, 52-66.
Moore, D.R., Edmondson-Jones, M., Dawes, P., Fortnum, H., Pierzycki, R.H., McCormack, A., & Munro, K. (2014) Relation between speech-in-noise threshold, hearing loss and cognition from 40 – 69 years of age, PLOS ONE, 9:e107720. PMID:25229622
Song, X. D.; Wallace, B. M.; Gardner, J. R.; Ledbetter, N. M.; Weinberger, K. Q.; and Barbour, D. L. (2015). Fast, Continuous Audiogram Estimation Using Machine Learning. Ear and Hearing, 36(6): e326–335. December 2015.
Vercoulen, J. H., Swanink, C. M., Fennis, J. F., Galama, J. M., van der Meer, J. W., & Bleijenberg, G. (1994). Dimensional assessment of chronic fatigue syndrome. Journal of Psychosomatic Research, 38(5), 383–392.

Wells H.R.R., Freidin, M.B., Zainul Abidin, F.N., Payton, A., Dawes, P., Munro, K.J., Morton, C.C., Moore, D.R., Dawson, S.J., & Williams, F.M.K. (2019) Genome-wide association study identifies 44 independent genomic loci for self-reported adult hearing difficulty in the UK Biobank cohort, American Journal of Human Genetics, 105, 788-802. PMID: 31564434


Woods, K.J.P., Siegel, M., Traer, J., McDermott, J.H. (2017) Headphone screening to facilitate web-based auditory experiments. Attention, Perception, & Psychophysics, 79, 2064-2072.

Heisey, K. L.; Walker, A. M.; Xie, K.; Abrams, J. M.; and Barbour, D. L. (2020). Dynamically Masked Audiograms With Machine Learning Audiometry. Ear and Hearing, 41(6): 1692–1702. December 2020.


Below you can post questions to the presenters. Please start your question with ‘Talk x’, to identify to what talk the question refers to. You can upvote questions or comments you like and also respond to the questions and comments of others.

We do moderate all comments this might cause a small delay before the comment becomes visible.

  • Did you recommend using average models and then make them patient specific models using newer features?

    • Yes, one great advantage of the Bayesian active learning techniques we are using is that population averages can be prior beliefs, and new data from an individual can update those beliefs. Prior beliefs benefit from wide data and the models themselves benefit from deep data.