Implications of stress-pattern differences in spoken-word recognition

Existing models of spoken-word recognition positing that stressed syllables tend to be perceived as word onsets have not provided an account of the processings of non-initial-stress words. The present study suggests that such words require additional, time-consuming processing. Two experiments showed that phoneme monitoring is slower in non-initial-stress than initial-stress words, even when the target-carrying syllable is made identical through splicing. In a third experiment, the processing of non-initial-stress words was also found to be more memory-taxing than that of initial-stress words, a result consistent with the need for additional memory storage generated by incorrect lexical activation in non-initial-stress words. Taken together, the results support the view that words bearing different stress patterns are processed differently, with extra processing required for non-initial-stress words. The implementation of such a distinction is discussed in the framework of current models of word recognition, with an emphasis on processing time-course differences. (C) 2000 Academic Press.