Integrated speech and morphological processing in a connectionist continuous speech understanding for Korean

Simple item page
dc.creatorLee, Geunbae
dc.creatorLee, Jong-Hyeok
dc.date1996-03-18
dc.date.accessioned2026-07-07T09:10:08Z
dc.date.available2026-07-07T09:10:08Z
dc.descriptionA new tightly coupled speech and natural language integration model is presented for a TDNN-based continuous possibly large vocabulary speech recognition system for Korean. Unlike popular n-best techniques developed for integrating mainly HMM-based speech recognition and natural language processing in a {\em word level}, which is obviously inadequate for morphologically complex agglutinative languages, our model constructs a spoken language system based on a {\em morpheme-level} speech and language integration. With this integration scheme, the spoken Korean processing engine (SKOPE) is designed and implemented using a TDNN-based diphone recognition module integrated with a Viterbi-based lexical decoding and symbolic phonological/morphological co-analysis. Our experiment results show that the speaker-dependent continuous {\em eojeol} (Korean word) recognition and integrated morphological analysis can be achieved with over 80.6% success rate directly from speech inputs for the middle-level vocabularies.
dc.descriptionlatex source with a4 style, 15 pages, to be published in computer processing of oriental language journal
dc.identifierhttps://arxiv.org/abs/cmp-lg/9603005
dc.identifierhttp://arxiv.org/abs/cmp-lg/9603005
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/151269
dc.subjectComputation and Language
dc.titleIntegrated speech and morphological processing in a connectionist continuous speech understanding for Korean
dc.typetext

Files

Collections

arXiv