Sensibilidad del análisis biomecánico como nueva herramienta para el cribado de la disfonía / Sensitivity of biomechanical analysis as a new tool for the screening of dysphonia

Objetivo: Validar el análisis biomecánico como herramienta de cribado de la disfonía y diseñar un protocolo que establezca la necesidad de derivación a atención especializada. Material y Métodos: Se evaluó a 102 voluntarios, clasificados en grupo control o grupo con patología vocal. Se realizó cribado de voz mediante análisis biomecánico con la herramienta App Online Lab® de Voice Clinical Systems®. Resultados: La edad media fue de 39,8 años. Del total de participantes, 35 se clasificaron en grupo control y 67 presentaban patología vocal. El análisis biomecánico detectó como libres de patología a todos los voluntarios del grupo control (E:1), y como patológicos a 58 de los 67 del grupo con patología vocal (S:0,87). Conclusiones: El análisis biomecánico R1 con umbral del 50% es una herramienta con alta sensibilidad y especificidad para el cribado de la patología de voz y ofrece una nueva posibilidad para su detección y seguimiento (AU)

Objetive: To validate the biomechanical analysis as a screening tool for dysphonia and to design a protocol that establishes the need for referral to specialized care. Material and Methods: We evaluated 102 volunteers, classified as control group or as subjects with voice pathology. Voice screening test was performed by biomechanical analysis tool App Online Lab® by Voice Clinical Systems®. Results: The mean age was 39.8 years old. Of the total of participants, 35 were classified as control group and 67 presented voice pathology. The biomechanical analysis detected all the volunteers in the control group as free of pathology (specificity of 1), and 58 of 67 in the group with voice pathology as pathological (sensitivity of 0.87). Conclusions: The R1 biomechanical analysis with a 50% threshold is a tool with high sensitivity and specificity for the screening of voice pathology and offers a new possibility for its detection and monitoring (AU)

Towards objective evaluation of perceived roughness and breathiness: an approach based on mel-frequency cepstral analysis.

Within this paper, the authors report on an experiment on automatic labelling of perceived voice roughness (R) and breathiness (B), according to the GRBAS scale. The main objective of the experiment has not been to correlate objective measures to perceived R and B, but to automatically evaluate R and B. For this purpose, a system has been trained that extracts the first mel-frequency cepstral coefficients (MFCC) of available sustained vowel phonations. Afterwards, a classifier has been trained to estimate the corresponding degrees of roughness and breathiness. The obtained results reveal a significant correlation between subjective and automatic labelling, hence indicating the feasibility of objective evaluation of voice quality by means of perceptually meaningful measures.