Fractionating auditory priors: A neural dissociation between active and passive experience of musical sounds

Abstract

Learning, attention and action play a crucial role in determining how stimulus predictions are formed, stored, and updated. Years-long experience with the specific repertoires of sounds of one or more musical styles is what characterizes professional musicians. Here we contrasted active experience with sounds, namely long-lasting motor practice, theoretical study and engaged listening to the acoustic features characterizing a musical style of choice in professional musicians with mainly passive experience of sounds in laypersons. We hypothesized that long-term active experience of sounds would influence the neural predictions of the stylistic features in professional musicians in a distinct way from the mainly passive experience of sounds in laypersons. Participants with different musical backgrounds were recruited: professional jazz and classical musicians, amateur musicians and non-musicians. They were presented with a musical multi-feature paradigm eliciting mismatch negativity (MMN), a prediction error signal to changes in six sound features for only 12 minutes of electroencephalography (EEG) and magnetoencephalography (MEG) recordings. We observed a generally larger MMN amplitudes-indicative of stronger automatic neural signals to violated priors-in jazz musicians (but not in classical musicians) as compared to non-musicians and amateurs. The specific MMN enhancements were found for spectral features (timbre, pitch, slide) and sound intensity. In participants who were not musicians, the higher preference for jazz music was associated with reduced MMN to pitch slide (a feature common in jazz music style). Our results suggest that long-lasting, active experience of a musical style is associated with accurate neural priors for the sound features of the preferred style, in contrast to passive listening.

Fig 1. Stimuli.

“Alberti Bass” played with piano tones in notation (top row) and schematic (bottom row) depiction. Each tone was 200 ms with an ISI of 5 ms. Each pattern of four notes includes deviant sound at the 3^rd position (X notes on the figure). Deviant order is randomized. The patterns are transposed to a different key every six bars, going through all major and minor keys during the presentation.

Fig 2. Grand averaged difference waveforms and topographic maps of MMN for four groups and six deviants recorded at Fz electrode.

Grey area marks MMN peak.

Fig 3. Average areal mean curves and MMNm amplitudes obtained for each musical group and six types of deviants.

Histograms represent mean values of MMNm responses. Asterisks mark significant results of Bonferroni-corrected planned comparisons (p < 0.05). A schematic picture of the gradiometers selected for calculating areal mean curves (dark circles) is at the bottom left.

Fig 4. Correlation plots.

(a) Significant partial correlation between right hemisphere MMNm amplitudes to slide and preference for jazz music (left) in non-musicians and amateurs (NM + AM) controlled for preference for classical music (corrected data plotted); (b) Significant correlation between years of music playing and right hemisphere MMNm amplitude to slide.