Rhythmic pattern facilitates speech production: An ERP study

Abstract

Rhythm affects the speech perception of events unfolding over time. However, it is not clear to what extent the rhythm could affect the processes of sentence speech production. In this event-related potential (ERP) study, we examined whether a particular rhythmic pattern could affect the planning of speech production before articulation. We recorded electrophysiological (EEG) and behavioural (reaction time) data while participants read aloud a target speech in Chinese. Target speeches were sentences or phrases consisting four characters, with regular (e.g., the 2 + 2 pattern; numbers in the brackets represent the number of syllables) or irregular (e.g., 1 + 3) rhythmic patterns, which were preceded by congruent or incongruent musical rhythmic patterns formed by simple pure tones with different temporal intervals. Behavioural and ERP findings indicated a rhythmic priming effect in comparing congruent and incongruent conditions in the regular target speeches, but not in the irregular ones. An early component (N100) that was elicited in response to target speeches that were rhythmically mismatched to primes was linked to the detection of hierarchical linguistic units, which did not conform to expectations. A later negative component (N400) was thought to reflect the violation of expectation on rhythmic pattern in speech production. These findings suggest that rhythmic pattern constrains grammatical and prosodic encoding during speech production, and support the hypothesis that speakers form a grammatical or a prosodic abstract frame before articulation.

Figure 1

(a) Samples of rhythmic patterns for primes (2 + 2: primes with longer interval between the second and the third tone; 1 + 3: primes with longer interval between the first and the second tone). (b) Illustration of hierarchical structures of syntax (left) and prosody (right) for a four-word sentence or phrase. (c) Illustration of segmentation of target speech patterns of 2 + 2 (left) and 1 + 3 (right) in articulation (Blue lines show the pitch contour of the target speech).

Figure 2

(a) Mean latencies of reading target phrase/sentence aloud by prime rhythm pattern and target speech pattern. (b) Grand-average ERP waveforms at the area of middle anterior for different prime rhythm patterns in target speech patterns 2 + 2 (top) and 1 + 3 (bottom), respectively. The map (top) shows the distribution of the effect (2 + 2 prime pattern minus random prime pattern and 1 + 3 prime pattern minus random prime pattern) in 2 + 2 target speech pattern in the time windows of 70–120 ms and 350–500 ms, respectively. The map (bottom) shows the distribution of the effect (2 + 2 prime pattern minus random prime pattern and 1 + 3 prime pattern minus random prime pattern) in 1 + 3 target speech pattern in the time windows of 70–120 ms and 350–500 ms, respectively. (c) Mean amplitudes of different prime rhythm patterns in target speech patterns 2 + 2 and 1 + 3 at the area of middle anterior, in the time windows of 70–120 ms (left) and 350–500 ms (right).