Normal Voice Production: Computation of Driving Parameters from Endoscopic Digital High Speed Images

Summary Objectives: A central point for quantitative evaluation of pathological and healthy voices is the analysis of vocal fold oscillations. By means of digital High Speed Glottography (HGG), vocal fold oscillations can be recorded in real time. Recently, a numerical inversion procedure was developed that allows the extraction of physiological parameters from digital high speed videos and a classification of voice disorders. The aim of this work was to validate the inversion procedure and to investigate the applicability to normal voices. Methods: High speed recordings were performed during phonation within a group of five female and five male persons with normal voices. By using knowledge based image processing algorithms, motion curves of the vocal folds were extracted at three different positions (dorsal, medial, ventral). These curves were used to obtain physiological voice parameters, and in particular the degree of symmetry of the vocal folds based upon a biomechanical model of the vocal folds. Results: The highest degree of symmetry was observed for the medial motion curves. While the dor-sally and ventrally extracted motion curves exhibited similar results concerning the degree of symmetry the performance of the algorithm was less stable. Conclusions: The inversion algorithm provides reasonable results for all subjects when applied to the medial motion curves. However, for dorsal and ventral motion curves, correct performance is reduced to 85 %.