Sonority contours in word recognition

Abstract

Contrary to the Generativist distinction between competence and performance which asserts that speech or perception errors are due to random, nonlinguistic factors, it seems likely that errors are principled and possibly governed by some of the same constraints as language. A preliminary investigation of errors modeled after the child’s ‘‘Chain Whisper’’ game (a degraded stimulus task) suggests that a significant number of recognition errors can be characterized as an improvement in syllable sonority contour towards the linguistically least‐marked, voiceless‐stop‐plus‐vowel syllable. An independent study of sonority contours showed that approximately half of the English lexicon can be uniquely identified by their contour alone. Additionally, ‘‘sororities’’ (groups of words that share a single sonority contour), surprisingly, show no correlation to familiarity or frequency in either size or membership. Together these results imply that sonority contours may be an important factor in word recognition and in defining word ‘‘neighborhoods.’’ Moreover, they suggest that linguistic markedness constraints may be more prevalent in performance‐related phenomena than previously accepted.