7th International Conference on Spoken Language Processing September 16-20, 2002 Denver, Colorado, USA

Modeling Recognition of Speech Sounds With Minerva2

Travis Wade, Deborah K. Eakin, Russell Webb, Arvin Agah, Frank Brown, Allard Jongman, John Gauch, Thomas A. Schreiber, Joan Sereno

University of Kansas, USA

This study investigates the extent to which a localist-distributive hybrid formal model of human memory replicates observed behavioral patterns in perception and recognition of appropriately coded language data. Extending previous research that considered for modeled memorization only items with uniform, undefined randomly generated featural specifications, a MINERVA2 simulation was trained to recognize linguistic events and categories at both acousticphonetic and phonological-featural processing levels. Results of both test conditions parallel two important effects observed in behavioral data and are discussed with respect to speech perception as well as human memory research.

Full Paper

Bibliographic reference.  Wade, Travis / Eakin, Deborah K. / Webb, Russell / Agah, Arvin / Brown, Frank / Jongman, Allard / Gauch, John / Schreiber, Thomas A. / Sereno, Joan (2002): "Modeling recognition of speech sounds with minerva2", In ICSLP-2002, 1653-1656.