Print
Univis
Search
 
FAU-Logo
Techn. Fakultät Willkommen am Institut für Informatik FAU-Logo

Carlos Ariel Ferrer-Riesgo Ph.D.

Researcher in the Speech Processing and Understanding (SAGI) group at the Pattern Recognition Lab of the Friedrich-Alexander-Universität Erlangen-Nürnberg

Objective Automatic Assessment of Pathological Voice

Ronquera - Objective Automatic Assessment of the Level of Dysphonia

The severity of dysphonia is traditionally assessed by perceptual means, and several scales are currently in use (GRBAS, RBH, CAPE-V). Many objective (optical, electrical, acoustical) measures have been developed to compensate the subjectivity of perceptual assessment. However, to date, these measures have failed to be sensitive (reflect changes of the perceptual trait), specific (reflect changes only of the intended perceptual trait), and consistent (with similar results across different studies) enough to be adopted in clinical practice. When there is no satisfactory correspondence between a perceptual rating and its purported objective correlate, the error(s) can arise from four possible sources/reasons:

  • The objective measurement

  • The perceptual ratings

  • The procedure to establish the correspondence

  • Actual absence of correspondence

This project (codenamed "Ronquera" as the Spanish for "Hoarseness") attempts to obtain more sensitive, specific, and consistent measures of dysphonia in the German RBH scale (roughness, breathiness, hoarseness), addressing problems in the four possible causes of correspondence.