How well do acoustic parameters correlate our perception of voice quality?

Auditory perceptual judgments are essential for assessing voice disorders and monitoring treatment progress. This study aimed to examine the acoustic foundations of perceived abnormalities in individuals with and without voice disorders, focusing on the correlation between the Grade, Roughness, Breathiness, Asthenia, Strain (GRBAS) scale and various acoustic parameters. A total of 1217 voice recordings were obtained from the Perceptual Voice Qualities Database (PVQD) and the Saarbruecken Voice Database (SVD). Each recording was perceptually evaluated by five experienced speech therapists based on the GRBAS scale. Only ratings of more than 80% inter-rater agreement was used for further analysis. Acoustic analyses were obtained using Parselmouth, a Python library for the Praat software. Statistical analysis using Spearman’s rank correlation revealed strong correlations between spectral and cepstral results and GRBAS scale. Specifically, the Grade and Breathiness components showed significant negative correlations with the CPPS parameters, with and without voice detection. There was a strong inverse relationship between Harmonics-to-Noise Ratio (HNR) and the Grade and Roughness. Jitter and shimmer demonstrated robust positive correlations with Grade, Breathiness, and Roughness. These findings provide valuable insights into the relationships between acoustic parameters and perceptual GRBAS scale, informing future research and clinical practice in voice and speech pathology.