Selective Attention Enhances Beta-Band Cortical Oscillation to Speech under "Cocktail-Party" Listening Conditions

Abstract

Human listeners are able to selectively attend to target speech in a noisy environment with multiple-people talking. Using recordings of scalp electroencephalogram (EEG), this study investigated how selective attention facilitates the cortical representation of target speech under a simulated "cocktail-party" listening condition with speech-on-speech masking. The result shows that the cortical representation of target-speech signals under the multiple-people talking condition was specifically improved by selective attention relative to the non-selective-attention listening condition, and the beta-band activity was most strongly modulated by selective attention. Moreover, measured with the Granger Causality value, selective attention to the single target speech in the mixed-speech complex enhanced the following four causal connectivities for the beta-band oscillation: the ones (1) from site FT7 to the right motor area, (2) from the left frontal area to the right motor area, (3) from the central frontal area to the right motor area, and (4) from the central frontal area to the right frontal area. However, the selective-attention-induced change in beta-band causal connectivity from the central frontal area to the right motor area, but not other beta-band causal connectivities, was significantly correlated with the selective-attention-induced change in the cortical beta-band representation of target speech. These findings suggest that under the "cocktail-party" listening condition, the beta-band oscillation in EEGs to target speech is specifically facilitated by selective attention to the target speech that is embedded in the mixed-speech complex. The selective attention-induced unmasking of target speech may be associated with the improved beta-band functional connectivity from the central frontal area to the right motor area, suggesting a top-down attentional modulation of the speech-motor process.

Keywords: informational masking; long-term neural activities; motor theory; neural network; selective attention; speech unmasking.

FIGURE 1

Illustration of the six phases within each trial of EEG recordings. Phase I: a trial was started with the presentation of a single-voiced speech (Voice 1, 2, or 3) to indicate which stimulation condition the present trial belonged to [Voice 1, selective attention to Voice 1 (top panel); Voice 2, selective attention to Voice 2 (middle panel); Voice 3, non-selective attention to the whole mixed-speech complex (bottom panel)]. Phase II: a period of silence lasting 1 s. Phase III: the presentation of the mixed three-voiced speech. Phase IV: a period of silence lasting 1.2 s. Phase V and Phase VI: the repetition of Phase III and Phase IV, respectively. Under the selective-attention condition (with Voice 1 or 2), participants were instructed to press a button if they had heard a wrong words probe (yellow waves); under the non-selective-attention condition, participants were instructed to press a button if they heard a click probe (yellow waves). The blue, green, and red waves indicate the single speech of Voice 1, Voice 2, and Voice 3, respectively.

FIGURE 2

Under the selective attention condition, the correlation between the all-site-averaged EEGs to the mixed-speech complex and the all-site-averaged EEGs to the single speech that was either the target or the masker speech in the mixed-speech complex. ^∗∗p < 0.01, paired t-test. The error bar indicates the standard errors of the mean.

FIGURE 3

The two left columns: for each of the five types of frequency bands [theta (𝜃), alpha (α), beta (β), gamma (γ), broad], the scalp topographical maps showing location distributions of absolute correlations between the EEGs to the mixed-speech complex and EEGs to a single speech under either the non-selective attention (NS) condition or the selective attention (S) condition. The two right columns: for each of the frequency bands, the recordings sites at which the correlation difference between the two attention conditions was significant when the p level was either 0.05 and or 0.015.

FIGURE 4

The four significant event-related Granger Causalities (GCs) induced by selective attention (S) against non-selective attention (NS) of beta band (p < 0.05).

FIGURE 5

For each of the four significant GCs shown in Figure 4, the correlation between the beta (β)-band correlation change index induced by selective attention and the beta (β)-band GC change index induced by selective attention. (A) Causal connectivity from the central frontal area to the right motor area; (B) Causal connectivity from the left frontal area to the right motor area; (C) Causal connectivity from the central frontal area to the right frontal area; (D) Causal connectivity from site TP7 to the right motor area. ^∗p < 0.05.