Donald S. Williamson

This researcher works on speech and audio processing, with a focus on predicting and improving speech quality, such as estimating how noisy or clear speech sounds to human listeners and building models to enhance speech in noisy environments. Much of the recent work involves machine learning methods, including attention-based models and contrastive learning, applied to tasks like speech quality assessment, speech enhancement, and dereverberation (removing echo-like effects from recordings). Note that a few unrelated publications on diabetes research appear in the record, which may reflect a data attribution issue rather than this researcher's actual work.

Publication output has grown from a handful of papers per year around 2017-2018 to a more active and fluctuating pace of roughly 7-10 papers per year from 2021 onward, with a notable peak of 13 in 2020.

Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026