UCL logo

UCL Discovery

UCL home » Library Services » Electronic resources » UCL Discovery

Word recognition from tiered phonological models

Huckvale, M; (1994) Word recognition from tiered phonological models. Presented at: IOA Conference on Speech and Hearing, Istanbul, Turkey. Green open access

[img]
Preview
PDF
ioa94.pdf

Download (30kB)

Abstract

Phonologically constrained morphological analysis (PCMA) is the decomposition of words into their component morphemes conditioned by both orthography and pronunciation. This article describes PCMA and its application in large-vocabulary continuous speech recognition to enhance recognition performance in some tasks. Our experiments, based on the British National Corpus and the LOB Corpus for training data and WSJCAM0 for test data, show clearly that PCMA leads to smaller lexicon size, smaller language models, superior word lattices and a decrease in word error rates. PCMA seems to show most benefit in open-vocabulary tasks, where the productivity of a morph unit lexicon makes a substantial reduction in out-ofvocabulary rates.

Type: Conference item (UNSPECIFIED)
Title: Word recognition from tiered phonological models
Event: IOA Conference on Speech and Hearing
Location: Istanbul, Turkey
Dates: 2000
Open access status: An open access version is available from UCL Discovery
Language: English
UCL classification: UCL > School of Life and Medical Sciences
UCL > School of Life and Medical Sciences > Faculty of Brain Sciences
UCL > School of Life and Medical Sciences > Faculty of Brain Sciences > Psychology and Language Sciences (Division of) > Speech, Hearing and Phonetic Sciences
URI: http://discovery.ucl.ac.uk/id/eprint/97732
Downloads since deposit
63Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item