A matter of emphasis: Linguistic stress habits modulate serial recall

Abstract

Models of short-term memory for sequential information rely on item-level, feature-based descriptions to account for errors in serial recall. Transposition errors within alternating similar/dissimilar letter sequences derive from interactions between overlapping features. However, in two experiments, we demonstrated that the characteristics of the sequence are what determine the fates of items, rather than the properties ascribed to the items themselves. Performance in alternating sequences is determined by the way that the sequences themselves induce particular prosodic rehearsal patterns, and not by the nature of the items per se. In a serial recall task, the shapes of the canonical "saw-tooth" serial position curves and transposition error probabilities at successive input-output distances were modulated by subvocal rehearsal strategies, despite all item-based parameters being held constant. We replicated this finding using nonalternating lists, thus demonstrating that transpositions are substantially influenced by prosodic features-such as stress-that emerge during subvocal rehearsal.

Fig. 1

Examples of stimuli employed in Experiment 1: An SD₁ sequence in pairs (left) and triplets (right) groupings

Fig. 2

Prosodic stress probabilities for six-item alternating sequences, conforming to DS (solid lines) and SD (broken lines) structures, during recall under pairs (open circles) and triplets (closed circles) rehearsal

Fig. 3

Serial position plots depicting mean (N = 16) performance obtained for six-item, alternating SD (left) and DS (right) sequences under the two rehearsal strategies. Error bars denote standard errors

Fig. 4

Transposition gradients showing total numbers of items recalled at each input–output pairing under pairs (panels 1 and 2) and triplets (panels 3 and 4) grouping. The input positions (denoted by shading) are arranged left to right at each output position

Fig. 5

Weighted proportions of transposition errors at five successive transposition distances, obtained under pairs and triplets rehearsal, for alternating heterogeneous sequences. Values are expressed as rationalized arcsine units. Error bars denote standard errors

Fig. 6

Prosodic stress probabilities for six-item homogeneous sequences, conforming to D (solid lines) and S (broken lines) structures, during recall under pairs (open circles) and triplets (closed circles) grouping

Fig. 7

Serial position plots depicting mean (N = 16) performance obtained for homogeneous similar (S, left panel) and dissimilar (D, right panel) six-item sequences, under two rehearsal strategies. Error bars denote standard errors

Fig. 8

Transposition gradients showing total numbers of similar (panels 1 and 3) and dissimilar (panels 2 and 4) items recalled at each input–output pairing under pairs (panels 1 and 2) and triplets (panels 3 and 4) rehearsal. The input positions (denoted by shading) are arranged left to right at each output position

Fig. 9

Weighted proportions of transposition errors at five successive transposition distances, obtained under pairs and triplets rehearsal, for homogeneous similar (S) and dissimilar (D) sequences. Values are expressed as rationalized arcsine units. Error bars denote standard errors