Work

Physics-informed neural network for predicting in vacuo vocal fold eigenmodes: A proof of concept study

Year: 2026

Type: article

Abstract: This study investigates a machine-learning approach for real-time computation of in vacuo vocal fold eigenmodes. A physics-informed neural network is trained to predict eigenmodes and eigenfrequencies by integrating the governing equations of vocal fold dynamics. The proposed architecture predicts physically consistent modal shapes and frequency estimates, showing strong agreement with finite-element method results for lower-order modes, achieving mean relative errors below 6% in eigenfrequency prediction and cosine correlation values approaching 1 in eigenmode prediction, while prediction accuracy declines for higher-order modes. These findings demonstrate that the physics-informed neural network provides an accurate and efficient real-time computation of in vacuo vocal fold eigenmodes.

Source: JASA Express Letters

DOI: 10.1121/10.0043248

Authors: Mohd Ethar M Al Khasawneh, Michael Döllinger, Zhaoyan Zhang

Institutions: Friedrich-Alexander-Universität Erlangen-Nürnberg, Universitätsklinikum Erlangen, University of California, Los Angeles

Language: English

Topic: Model Reduction and Neural Networks

Subfield: Statistical and Nonlinear Physics

Field: Physics and Astronomy

Domain: Physical Sciences

Open Access status: diamond

Funders: Deutsche Forschungsgemeinschaft, National Institutes of Health, Zurich Information Security and Privacy Center, National Institute on Deafness and Other Communication Disorders

Awards: G5601638812, G6382119541