Built from the bench up, this program begins with physical vocal-fold models and controlled airflow, collecting direct intraglottal and subglottal pressures, acoustic recordings, and high-speed video under reproducible conditions. On top of these grounded measurements, we have developed physics-informed models—contact mechanics for collision pressure and finite-element inversion for tissue properties—to generate interpretable, pathology-relevant features such as spatiotemporal opening and closure patterns, symmetry and energy measures, and cumulative collision-pressure "dose." These features are then fed into machine learning models for classification, enabling differentiation of common lesions (for example, nodules, polyps, and posterior glottal insufficiency). The result is a coherent chain—physical modeling → multimodal measurement → physics-informed features → machine-learning classification—that supports diagnosis, therapy planning, and surgical decision-making.
Journal of Speech, Language, and Hearing Research, 65(8), 2829-2845
The Journal of the Acoustical Society of America, 153(1), 654-664
The Journal of the Acoustical Society of America, 150(2), 1332-1345
The Journal of the Acoustical Society of America, 150(1), 478-489
medRxiv, 2020.11.20.20235911
Applied Sciences, 9(11), 2384
Applied Sciences, 9(13), 2735
Temporal intraglottal pressure variations at four positions in a vocal fold model oscillating at 150 Hz, shown with synchronized high-speed imaging.
Designed setup for extracting voice signals and high-speed vocal fold videos.
Ambulatory voice monitoring using neck surface acceleration.