7th International Conference on Spoken Language Processing

September 16-20, 2002
Denver, Colorado, USA

ASR in a Human Word Recognition Model: Generating Phonemic Input for Shortlist

Odette Scharenborg, Lou Boves, Johan de Veth

University of Nijmegen, The Netherlands

The current version of the psycholinguistic model of human word recognition Shortlist suffers from two unrealistic constraints. First, the input of Shortlist must consist of a single string of phoneme symbols. Second, the current version of the search in Shortlist makes it difficult to deal with insertions and deletions in the input phoneme string. This research attempts to fully automatically derive a phoneme string from the acoustic signal that is as close as possible to the number of phonemes in the lexical representation of the word. We optimised an Automatic Phone Recogniser (APR) using two approaches, viz. varying the value of the mismatch parameter and optimising the APR output strings on the output of Shortlist. The approaches show that it will be very difficult to satisfy the input requirements of the present version of Shortlist with a phoneme string generated by an APR.

Full Paper

Bibliographic reference.  Scharenborg, Odette / Boves, Lou / Veth, Johan de (2002): "ASR in a human word recognition model: generating phonemic input for shortlist", In ICSLP-2002, 633-636.