Beatboxers and Guitarists Engage Sensorimotor Regions Selectively When Listening to the Instruments They can Play

Abstract

Studies of classical musicians have demonstrated that expertise modulates neural responses during auditory perception. However, it remains unclear whether such expertise-dependent plasticity is modulated by the instrument that a musician plays. To examine whether the recruitment of sensorimotor regions during music perception is modulated by instrument-specific experience, we studied nonclassical musicians-beatboxers, who predominantly use their vocal apparatus to produce sound, and guitarists, who use their hands. We contrast fMRI activity in 20 beatboxers, 20 guitarists, and 20 nonmusicians as they listen to novel beatboxing and guitar pieces. All musicians show enhanced activity in sensorimotor regions (IFG, IPC, and SMA), but only when listening to the musical instrument they can play. Using independent component analysis, we find expertise-selective enhancement in sensorimotor networks, which are distinct from changes in attentional networks. These findings suggest that long-term sensorimotor experience facilitates access to the posterodorsal "how" pathway during auditory processing.

Figure 1.

Postscan behavioral ratings provided by each group when listening to clips from the two music conditions (beatbox—gray bars/filled diamonds; guitar—clear/unfilled diamonds). Each data point represents a participant (N = 20 in each group), the bars depict the mean in both conditions. Lower ratings indicate that the stimuli are perceived to be easier to produce.

Figure 2.

Depicts the results of univariate analyses conducted in SPM to explore group × condition modulation in listening activity. Panel (A) shows activity for the beatbox > guitar music contrast in beatboxers, guitarists, and nonmusicians. Regions where activity for listening to beatboxing exceeds that of listening to guitar music are shown in red–yellow, regions where activity for guitar music exceeds that of guitar music are shown in blue–light blue. This highlights that beatboxers and guitarists show increases in activity over dorsal stream regions for music they can produce. Nonmusicians do not show a modulation by condition in these dorsal stream regions, but do show increased activity for beatbox > guitar music in superior temporal cortex bilaterally. Note that analyses were inclusively masked by regions that showed the group × condition interaction, which are shown in panel (B). Panel (B) depicts regions where beatbox > guitar activity is modulated by group membership (beatboxer/guitarist/nonmusician), highlighted in red/yellow. These include left and right inferior frontal cortex, left postcentral gyrus and inferior parietal regions, supplementary and cingulate motor areas, and inferior temporal cortex and posterior superior temporal gyri bilaterally. For panels (C–E), analyses were inclusively masked by the regions depicted in panel (B). Panel (C) shows regions where beatboxers and guitarists have a differential response to the beatbox > guitar music contrast. Areas highlighted in red–yellow show regions where there is positive instrument-specific modulation by musicians, and those in blue show negative instrument-specific modulation. Bar graphs show mean beta values from highlighted clusters, bars in blue show the mean activity for beatbox > guitar music in guitarists, the bars in green show the same for the beatboxers. Positive values indicate more activity for beatboxing, whereas negative values suggest more activity for guitar music. Error bars denote ±1 standard error of the mean (SEM). Each data point represents an individual participant. Panel (D) shows regions where guitarists and nonmusicians have a differential response to the beatbox > guitar music contrast. Bar graphs show mean beta values from highlighted clusters, bars in blue show the mean activity for beatbox > guitar music in guitarists, the bars in purple show the same for the nonmusicians. Error bars denote ±1 SEM. Each data point represents an individual participant. Panel (E) shows regions where beatboxers and nonmusicians have a differential response to the beatbox > guitar music contrast (P < 0.05 FWE cluster-corrected). Bar graphs show mean beta values from highlighted clusters, bars in green show the mean activity for beatbox > guitar music in beatboxers, the bars in purple show the same for the nonmusicians. Each data point represents an individual participant. Error bars denote ±1 SEM. Thresholded activation maps (P < 0.05 FWE) for each contrast described here are registered to and displayed on a cortical surface using Freesurfer. The cortical surface was generated using the average T1 of the MNI-152 template. Activity in the cerebellum is not shown.

Figure 3.

Depicts the results of univariate ROI analyses, where mean beta values for left and right hand and mouth regions were extracted for beatbox > guitar music in each participant. Positive values indicate more activity for beatboxing, whereas negative values suggest more activity for guitar music. Error bars depict ±1 standard error of the mean. Each data point represents an individual participant. Nonmusicians (NM) are represented by filled circles, beatboxers (BB) by filled squares and guitarists (G) using filled triangles. These graphs clearly show that guitarists, but not the other 2 groups, show greater activity for guitar music in hand regions. In the mouth regions, beatboxers, but not the other 2 groups, show greater activity for beatboxing. The specific ROIs we sampled from are highlighted in the figure, and were derived from group activity for hand and mouth movements.

Figure 4.

Depicts activity in for listening to guitar music (black) and listening to beatboxing (gray) in the 12 non-noise independent components. Networks were derived using a group concatenation approach implemented in FSL MELODIC, and dual regression was used to calculate cope values for each network in each participant for the contrasts beatbox > rest and guitar music > rest. Networks are labeled with a number as well as a functional descriptor based on their spatial distribution (see Supplementary Fig. S1). Graphs show mean beta values for these 2 contrasts, and error bars depict ±1 SEM. Networks C1 (auditory), C11 (higher-level sensorimotor), C12 (temporal–opercular), and C4 (left frontotemporo-parietal) show increases in activity when listening to music, whereas networks C5 (visual), C7 (default mode network), C8 (default mode network), and C10 (visual) show decreases in activity when listening to music.

Figure 5.

Demonstrates group × condition interactions in 6 of the 12 non-noise independent components derived using FSL MELODIC. The insets below each network label show regions included in the network, with regions that are positively covarying in white and those that show negative covariation in black. These are projected on the fsaverage cortical surface (for further details, such as activity on the medial surface, see Supplementary Fig. S1). Dual regression was used to derive subject-specific time courses for each of these 6 networks, and cope values for each network in each participant were calculated for the contrast beatbox > guitar music. In these graphs, values greater than 0 represent a preference for beatboxing relative to guitar music, whereas values less than 0 depict the opposite preference. Mean cope values for each group are shown by the bars, and the data points represent individual participants. Error bars depict ±1 SEM. Nonmusicians (NM) are depicted using filled circles, beatboxers (BB) with filled squares, and guitarists (G) using filled triangles. Musicians recruit auditory and sensorimotor networks as they listen to music they can produce, while inhibiting spatially overlapping default mode network (DMN) and executive control networks.