Psychoacoustical scaling of acoustical voice parameters by multicenter voice ratings.

Background: The purpose of the study was to analyze if perceptual voice qua lity ratings of the well-known RBH rating procedure (a 4-point scale of rou ghness, breathiness, and hoarseness) covary with acoustical voice parameter s. Methods: 120 voice samples from subjects with healthy and hoarse voices were rated on the RBH-index in a multicenter study with 31 raters. Multivar iate regression tree analysis classified the perceptual ratings as "gold st andard". Voice samples were acoustically analyzed with a feature extraction method, Feedforward-networks were trained to selected acoustical parameter s having highest "relative importance" in the regression trees. Based on th e best classifier, a computer program consisting of 50 simultaneous working networks was developed. Results: Mean probabilities for correct classifica tions were found at 0.65-0.85, implying a significance level over chance (0 .25). Classifications of the program matched in 40% with a priori values in the categories roughness combined with breathiness, and in 65% in at least one domain. Conclusions: The new method described here provides a psychoac oustically based "objective" classification of hoarse voices, which seems t o enable future analysis of new parameters (like GNE), which may even impro ve the present results.