Using Dutch phonological rules to model pronunciation
variation in ASR.
Mirjam Wester, Judith M. Kessens, Helmer Strik (2000)
Dept. of Language & Speech, University of Nijmegen
P.O. Box 9103, 6500 HD Nijmegen, The Netherlands
Proc. of the workshop on phonetics and phonology in ASR, March 1-3, 2000, Saarbrücken, Germany
Using Dutch phonological rules to model pronunciation variation in ASR.
In this paper, we describe how the performance of a continuous speech
recognizer for Dutch has been improved by modeling within-word and
cross-word pronunciation variation. Within-word variants were
automatically generated by applying five phonological rules to the words
in the lexicon. Cross-word pronunciation variation was modeled by adding
multi-words and their variants to the lexicon. The best results were
obtained when the cross-word method was combined with the within-word
method: a relative improvement of 8.8% in the WER was found compared to
baseline system performance. We also describe an error analysis that was
carried out to investigate whether rules in isolation can predict the
performance of rules in combination.