Laryngeal videoendoscopy is one of the main tools in clinical examinations for voice disorders and voice research. Using high-speed videoendoscopy, it is possible to fully capture the vocal fold oscillations, however, processing the recordings typically involves a time-consuming segmentation of the glottal area by trained experts. Even though automatic methods have been proposed and the task is particularly suited for deep learning methods, there are no public datasets and benchmarks available to compare methods and to allow training of generalizing deep learning models. In an international collaboration of researchers from seven institutions from the EU and USa, we have created BaGLS, a large, multihospital dataset of 59,250 high-speed videoendoscopy frames with individually annotated segmentation masks. The frames are based on 640 recordings of healthy and disordered subjects that were recorded with varying technical equipment by numerous clinicians. the BaGLS dataset will allow an objective comparison of glottis segmentation methods and will enable interested researchers to train their own models and compare their methods.
This study involves preliminary investigation of the characteristics of the voice initiation period (VIP) and voice offset period (VOP) using high-speed digital imaging. The goals of the study were to develop a methodology to objectively analyze these periods of phonation and to explore the feasibility of studying the effects of aging on these phonation segments. Results of the analysis of the data from two female subjects, one younger and one older, with the developed methodology, demonstrated that the older subject's VIP was characterized by a slow and irregular increase in glottal area waveform (GAW) until reaching 90% of the maximum opening of the glottis at 244 frames or 122 ms. The younger subject demonstrated a sharp increase in GAW during VIP, taking only 155 frames or 77.5 ms to reach the 90% mark. Also, the older subject took a greater number of frames for the vocal fold vibration to come to a complete stop than the younger subject during the VOP; 275 frames and 150 frames respectively.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.