The quantitative characterization of vocal fold (VF) motion can greatly enhance the diagnosis and treatment of speech
pathologies. The recent availability of high-speed systems has created new opportunities to understand VF dynamics.
This paper presents quantitative methods for analyzing VF dynamics with high-speed digital phonoscopy, with a focus
on expected VF changes during childhood. A robust method for automatic VF edge tracking during phonation is
introduced and evaluated against 4 expert human observers. Results from 100 test frames show a subpixel difference
between the VF edges selected by algorithm and expert observers. Waveforms created from the VF edge displacement
are used to created motion features with limited sensitivity to variations of camera resolution on the imaging plane. New
features are introduced based on acceleration ratios of critical points over each phonation cycle, which have the potential
for studying issues related to impact stress. A novel denoising and hybrid interpolation/extrapolation scheme is also
introduced to reduce the impact of quantization errors and large sampling intervals relative to the phonation cycle.
Features extracted from groups of 4 adults and 5 children show large differences for features related to asymmetry
between the right and left fold and consistent differences for impact acceleration ratio.© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.