A connectionist model of phonological representation in speech perception

Abstract A number of recent studies have examined the effects of phonological variation on the perception of speech. These studies show that both the lexical representations of words and the mechanisms of lexical access are organized so that natural, systematic variation is tolerated by the perceptual system, while a general intolerance of random deviation is maintained. Lexical abstraction distinguishes between phonetic features that form the invariant core of a word and those that are susceptible to variation. Phonological inference relies on the context of surface changes to retrieve the underlying phonological form. In this article we present a model of these processes in speech perception, based on connectionist learning techniques. A simple recurrent network was trained on the mapping from the variant surface form of speech to the underlying form. Once trained, the network exhibited features of both abstraction and inference in its processing of normal speech, and predicted that similar behavior will be found in the perception of nonsense words. This prediction was confirmed in subsequent research (Gaskell & Marslen-Wilson, 1994).

[1]  W. Ganong.  Phonetic categorization in auditory word perception. , 1980, Journal of experimental psychology. Human perception and performance.

[2]  John Kingston,et al.  Between the grammar and physics of speech , 1994 .

[3]  Anne Cutler,et al.  Monitoring sentence comprehension , 1979 .

[4]  Douglas Biber,et al.  Frequency Analysis of English Vocabulary and Grammar , 1991 .

[5]  C. Browman,et al.  Papers in Laboratory Phonology: Tiers in articulatory phonology, with some implications for casual speech , 1990 .

[6]  Jean Lowenstamm,et al.  The internal structure of phonological elements: a theory of charm and government , 1985, Phonology Yearbook.

[7]  Francis Nolan,et al.  Gesture, Segment, Prosody: The descriptive role of segments: evidence from assimilation , 1992 .

[8]  Perceptual distance and competition in lexical access. , 1996 .

[9]  Nick Chater,et al.  A phonologically motivated input representation for the modelling of auditory word perception in continuous speech , 1992 .

[10]  William D. Marslen-Wilson,et al.  Phonological variation and inference in lexical access. , 1996 .

[11]  James L. McClelland,et al.  Understanding normal and impaired word reading: computational principles in quasi-regular domains. , 1996, Psychological review.

[12]  Dennis Norris,et al.  A dynamic-net model of human speech recognition , 1991 .

[13]  W. Marslen-Wilson.  Functional parallelism in spoken word-recognition , 1987, Cognition.

[14]  Diana Archangeli,et al.  Aspects of underspecification theory , 1988, Phonology.

[15]  V. Marchman,et al.  From rote learning to system building: acquiring verb morphology in children and connectionist nets , 1993, Cognition.

[16]  Dawn G. Blasko,et al.  Do the Beginnings of Spoken Words Have a Special Status in Auditory Word Recognition , 1993 .

[17]  Lorraine K. Tyler,et al.  A Distributed Memory Model of the Associative Boost in Semantic Priming , 1994, Connect. Sci..

[18]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[19]  J. Elman,et al.  Learning and morphological change , 1995, Cognition.

[20]  W. Marslen-Wilson,et al.  Accessing Spoken Words: The Importance of Word Onsets , 1989 .

[21]  Dani Byrd.  Perception of Assimilation in Consonants Clusters:A Gestural Model , 1992 .

[22]  W. Marslen-Wilson,et al.  The mental representation of lexical form: A phonological approach to the recognition lexicon , 1991, Cognition.

[23]  James L. McClelland,et al.  Learning Subsequential Structure in Simple Recurrent Networks , 1988, NIPS.

[24]  Gary S. Dell,et al.  Structure and Content in Language Production: A Theory of Frame Constraints in Phonological Speech Errors , 1993, Cogn. Sci..

[25]  W. Marslen-Wilson,et al.  Morphology and meaning in the English mental lexicon. , 1994 .

[26]  Mark S. Seidenberg.  Language and connectionism: the developing interface , 1994, Cognition.

[27]  James L. McClelland,et al.  The TRACE model of speech perception , 1986, Cognitive Psychology.

[28]  J. Stemberger.  Apparent anti-frequency effects in language production: The Addition Bias and phonological underspecification☆ , 1991 .

[29]  Javier R. Movellan,et al.  Learning Continuous Probability Distributions with Symmetric Diffusion Networks , 1993, Cogn. Sci..

[30]  James L. McClelland,et al.  Explorations in parallel distributed processing: a handbook of models, programs, and exercises , 1988 .

[31]  Klaus J. Kohler,et al.  Segmental Reduction in Connected Speech in German: Phonological Facts and Phonetic Explanations , 1990 .

[32]  Mary Hare,et al.  The Role of Similarity in Hungarian Vowel Harmony: a Connectionist Account , 1990 .

[33]  R. Reilly,et al.  Connectionist approaches to natural language processing , 1994 .

[34]  James L. McClelland,et al.  A distributed, developmental model of word recognition and naming. , 1989, Psychological review.

[35]  J. Elman.  Learning and development in neural networks: the importance of starting small , 1993, Cognition.

[36]  William D. Marslen-Wilson,et al.  Phonological variation and mismatch in lexical access , 1993, EUROSPEECH.

[37]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[38]  R. Quirk,et al.  A Corpus of English Conversation , 1980 .

[39]  D. Archangeli.  Underspecification in Yawelmani phonology and morphology , 1984 .

[40]  P. Keating.  Underspecification in Phonetics , 1988, Phonology.

[41]  Nick Chater,et al.  A CONNECTIONIST MODEL OF AUDITORY WORD PERCEPTION IN CONTINUOUS SPEECH , 1991 .

[42]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[43]  G. Altmann.  Cognitive models of speech processing , 1991 .

[44]  J. Ohala.  Papers in Laboratory Phonology: The phonetics and phonology of aspects of assimilation , 1990 .