Open Access Open Access  Restricted Access Subscription Access

Evaluation of Analytical Modeling Functions for the Phonation Onset Process


Affiliations
1 Division of Phoniatrics and Pediatric Audiology at the Department of Otorhinolaryngology Head & Neck Surgery, University Hospital Erlangen, Medical School, Friedrich-Alexander University Erlangen-Nurnberg (FAU), Bohlenplatz 21, 91054 Erlangen, Germany
 

The human voice originates from oscillations of the vocal folds in the larynx. The duration of the voice onset (VO), called the voice onset time (VOT), is currently under investigation as a clinical indicator for correct laryngeal functionality. Different analytical approaches for computing the VOT based on endoscopic imaging were compared to determine the most reliable method to quantify automatically the transient vocal fold oscillations during VO. Transnasal endoscopic imaging in combination with a high-speed camera (8000 fps) was applied to visualize the phonation onset process. Two different definitions of VO interval were investigated. Six analytical functions were tested that approximate the envelope of the filtered or unfiltered glottal area waveform (GAW) during phonation onset. A total of 126 recordings from nine healthy males and 210 recordings from 15 healthy females were evaluated. Three criteria were analyzed to determine the most appropriate computation approach: (1) reliability of the fit function for a correct approximation of VO; (2) consistency represented by the standard deviation of VOT; and (3) accuracy of the approximation of VO. The results suggest the computation of VOT by a fourth-order polynomial approximation in the interval between 32.2 and 67.8% of the saturation amplitude of the filtered GAW.
User
Notifications
Font Size

Abstract Views: 101

PDF Views: 4




  • Evaluation of Analytical Modeling Functions for the Phonation Onset Process

Abstract Views: 101  |  PDF Views: 4

Authors

Simon Petermann
Division of Phoniatrics and Pediatric Audiology at the Department of Otorhinolaryngology Head & Neck Surgery, University Hospital Erlangen, Medical School, Friedrich-Alexander University Erlangen-Nurnberg (FAU), Bohlenplatz 21, 91054 Erlangen, Germany
Stefan Kniesburges
Division of Phoniatrics and Pediatric Audiology at the Department of Otorhinolaryngology Head & Neck Surgery, University Hospital Erlangen, Medical School, Friedrich-Alexander University Erlangen-Nurnberg (FAU), Bohlenplatz 21, 91054 Erlangen, Germany
Anke Ziethe
Division of Phoniatrics and Pediatric Audiology at the Department of Otorhinolaryngology Head & Neck Surgery, University Hospital Erlangen, Medical School, Friedrich-Alexander University Erlangen-Nurnberg (FAU), Bohlenplatz 21, 91054 Erlangen, Germany
Anne Schutzenberger
Division of Phoniatrics and Pediatric Audiology at the Department of Otorhinolaryngology Head & Neck Surgery, University Hospital Erlangen, Medical School, Friedrich-Alexander University Erlangen-Nurnberg (FAU), Bohlenplatz 21, 91054 Erlangen, Germany
Michael Dollinger
Division of Phoniatrics and Pediatric Audiology at the Department of Otorhinolaryngology Head & Neck Surgery, University Hospital Erlangen, Medical School, Friedrich-Alexander University Erlangen-Nurnberg (FAU), Bohlenplatz 21, 91054 Erlangen, Germany

Abstract


The human voice originates from oscillations of the vocal folds in the larynx. The duration of the voice onset (VO), called the voice onset time (VOT), is currently under investigation as a clinical indicator for correct laryngeal functionality. Different analytical approaches for computing the VOT based on endoscopic imaging were compared to determine the most reliable method to quantify automatically the transient vocal fold oscillations during VO. Transnasal endoscopic imaging in combination with a high-speed camera (8000 fps) was applied to visualize the phonation onset process. Two different definitions of VO interval were investigated. Six analytical functions were tested that approximate the envelope of the filtered or unfiltered glottal area waveform (GAW) during phonation onset. A total of 126 recordings from nine healthy males and 210 recordings from 15 healthy females were evaluated. Three criteria were analyzed to determine the most appropriate computation approach: (1) reliability of the fit function for a correct approximation of VO; (2) consistency represented by the standard deviation of VOT; and (3) accuracy of the approximation of VO. The results suggest the computation of VOT by a fourth-order polynomial approximation in the interval between 32.2 and 67.8% of the saturation amplitude of the filtered GAW.