A comparison of data-derived and knowledge-based modeling of pronunciation variation

Mirjam Wester, Eric Fosler-Lussier

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper focuses on modeling pronunciation variation in two different ways: data-derived and knowledge-based. The knowledge-based approach consists of using phonological rules to generate variants. The data-derived approach consists of performing phone recognition, followed by various pruning and smoothing methods to alleviate some of the errors in the phone recognition. Using phonological rules led to a small improvement in WER; whereas, using a data-derived approach in which the phone recognition was smoothed using simple decision trees (d-trees) prior to lexicon generation led to a significant improvement compared to the baseline. Furthermore, we found that 10% of variants generated by the phonological rules were also found using phone recognition, and this increased to 23% when the phone recognition output was smoothed by using d-trees. In addition, we propose a metric to measure confusability in the lexicon and we found that employing this confusion metric to prune variants results in roughly the same improvement as using the d-tree method.

Original languageEnglish
Title of host publicationSixth International Conference on Spoken Language Processing, ICSLP 2000 / INTERSPEECH 2000, Beijing, China, October 16-20, 2000
Pages270-273
Number of pages4
Publication statusPublished - 2000

Fingerprint

Dive into the research topics of 'A comparison of data-derived and knowledge-based modeling of pronunciation variation'. Together they form a unique fingerprint.

Cite this