Modularity in inductively-learned word pronunciation systems

Details Modularity in inductively-learned word pronunciation systems Modularity in inductively-learned word pronunciation systems

1998-01-26

arxiv.org/abs/cmp-lg/9801004v1

Proceedings of NeMLaP3/CoNLL98, 185-194

Computer Science

Computation and Language

10 pages, uses nemlap3.sty and epsf and ipamacs (WSU IPA) macros

Scientific paper

In leading morpho-phonological theories and state-of-the-art text-to-speech systems it is assumed that word pronunciation cannot be learned or performed without in-between analyses at several abstraction levels (e.g., morphological, graphemic, phonemic, syllabic, and stress levels). We challenge this assumption for the case of English word pronunciation. Using IGTree, an inductive-learning decision-tree algorithms, we train and test three word-pronunciation systems in which the number of abstraction levels (implemented as sequenced modules) is reduced from five, via three, to one. The latter system, classifying letter strings directly as mapping to phonemes with stress markers, yields significantly better generalisation accuracies than the two multi-module systems. Analyses of empirical results indicate that positive utility effects of sequencing modules are outweighed by cascading errors passed on between modules.

Affiliated with

Also associated with

No associations

Rating

Modularity in inductively-learned word pronunciation systems does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Modularity in inductively-learned word pronunciation systems, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Modularity in inductively-learned word pronunciation systems will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-375410