The pleasantness of sensory dissonance is mediated by musical style and expertise

Abstract

Western musical styles use a large variety of chords and vertical sonorities. Based on objective acoustical properties, chords can be situated on a dissonant-consonant continuum. While this might to some extent converge with the unpleasant-pleasant continuum, subjective liking might diverge for various chord forms from music across different styles. Our study aimed to investigate how well appraisals of the roughness and pleasantness dimensions of isolated chords taken from real-world music are predicted by Parncutt's established model of sensory dissonance. Furthermore, we related these subjective ratings to style of origin and acoustical features of the chords as well as musical sophistication of the raters. Ratings were obtained for chords deemed representative of the harmonic language of three different musical styles (classical, jazz and avant-garde music), plus randomly generated chords. Results indicate that pleasantness and roughness ratings were, on average, mirror opposites; however, their relative distribution differed greatly across styles, reflecting different underlying aesthetic ideals. Parncutt's model only weakly predicted ratings for all but Classical chords, suggesting that listeners' appraisal of the dissonance and pleasantness of chords bears not only on stimulus-side but also on listener-side factors. Indeed, we found that levels of musical sophistication negatively predicted listeners' tendency to rate the consonance and pleasantness of any one chord as coupled measures, suggesting that musical education and expertise may serve to individuate how these musical dimensions are apprehended.

Figure 1

Histograms depicting the bivariate distribution of ratings across stimuli, separately for each style. The count of all rating pairs in each bin is indexed as per the greyscale bar; and clustered into the four corners of each rating space, where counts are expressed as a percentage of the total histogram mass. Italicised conjunctions (and, yet) in each cluster’s description reflect the working hypothesis that listeners generally ascribe a chord’s pleasantness in proportion to its degree of consonance.

Figure 2

Mean pleasantness and roughness ratings for chords. Ratings are averaged across repetitions, exemplars and participants. Error bars indicate ±1SEM across participants. **p < 0.01.

Figure 3

Cross-participant correlation between GMSI and sensory decoupling ability (SDA) scores, within styles (a) and collapsing across styles (b). Fit-line slopes are comparable across plots as measures of effect size, since axis ranges are matched. Each plot includes the least-squares regression line, with the 95% confidence band around it shaded.