Robert F. Orlikoff

Several collaborative projects between South-West University in Blagoevgrad, Bulgaria, and 8 universities in the USA have worked well to improve the overall competence of students in speech-language pathology programs and practicing clinicians to better meet the needs of individuals with fluency and voice disorders. The US Fulbright Senior Specialist and EU Erasmus+ exchange programs serve as effective instruments that provide systemic and long-term impact supporting innovation and fostering contemporary teaching methods. These international projects prepare students and faculty succeed in a global, multicultural society, and in doing so, advance speech-language pathology as an evidence-based allied health science discipline.

Investigating the phonatory processes in connected speech from high-speed videoendoscopy (HSV) demands the accurate detection of the vocal fold edges during vibration. The present paper proposes a new spatio-temporal technique to automatically segment vocal fold edges in HSV data during running speech. The HSV data were recorded from a vocally normal adult during a reading of the “Rainbow Passage.” The introduced technique was based on an unsupervised machine-learning (ML) approach combined with an active contour modeling (ACM) technique (also known as a hybrid approach). The hybrid method was implemented to capture the edges of vocal folds on different HSV kymograms, extracted at various cross-sections of vocal folds during vibration. The k-means clustering method, an ML approach, was first applied to cluster the kymograms to identify the clustered glottal area and consequently provided an initialized contour for the ACM. The ACM algorithm was then used to precisely detect the glottal edges of the vibrating vocal folds. The developed algorithm was able to accurately track the vocal fold edges across frames with low computational cost and high robustness against image noise. This algorithm offers a fully automated tool for analyzing the vibratory features of vocal folds in connected speech.

Studying voice production during running speech can provide new knowledge about the mechanisms of voice production with and without disorder. Laryngeal high-speed videoendoscopy (HSV) systems are powerful tools for studying laryngeal function and, if coupled with flexible fiberoptic endoscopes, they can provide unique possibilities to measure vocal fold vibration with high temporal resolution during connected speech. Hence, we can measure the non-stationary behaviors of the vocal folds, such as the glottal attack and offset times in running speech. In this study, a custom-built flexible fiberoptic HSV system was used to record a “Rainbow Passage” production from a vocally normal female. Automated temporal and spatial segmentation algorithms were developed to determine the time stamps of the vibrating vocal folds and the edges of the vocal folds during phonation. The glottal attack time and offset times were then measured from the temporally and spatially segmented HSV images. The amplification ratio was computed during the phonation onset and the damping ratio was calculated at the offset of sustained portion of phonation. These measures can be used to describe the laryngeal mechanisms of voice production in connected speech.