Connectionist modeling of speech perception
Journal/Book: Psychol Bull. 1999; 125: 750 First St NE, Washington, DC 20002-4242, USA. Amer Psychological Assoc. 410-436.
Abstract: Connectionist models of perception and cognition, including the process of deducing meaningful messages from patterns of acoustic waves emitted by vocal tracts, are developed and refined as human understanding of brain function, psychological processes, and the properties of massively parallel architectures advances. The present article presents several important contributions from diverse points of view in the area of connectionist modeling of speech perception and discusses their relative merits with respect to specific theoretical issues and empirical findings. TRACE, the Elman/Norris net, and Adaptive Resonance Theory constitute pivotal points exemplifying overall modeling success, progress in temporal representation, and plausible modeling of learning, respectively. Other modeling efforts are presented for the specific insights they offer, and the article concludes with a discussion of computational versus dynamic modeling of phonological processes.
Note: Review Protopapas A, Panteion Univ Athens, Dept Psychol, Leoforos Syngrou 136, GR-17671 Athens, GREECE
Keyword(s): SPOKEN-WORD-RECOGNITION; NEURAL-NETWORK MODEL; LEXICAL ACCESS; PHONEME IDENTIFICATION; PHONOLOGICAL VARIATION; FORMANT TRANSITIONS; STOP CONSONANTS; TRACE MODEL; DISCRIMINATION; COMPETITION