Phoneme-level speech and natural language intergration for agglutinative languages

dc.creatorKim, Geunbae Lee Jong-Hyeok Lee Kyunghee
dc.date1994-11-05
dc.date.accessioned2026-07-07T09:09:39Z
dc.date.available2026-07-07T09:09:39Z
dc.descriptionA new tightly coupled speech and natural language integration model is presented for a TDNN-based large vocabulary continuous speech recognition system. Unlike the popular n-best techniques developed for integrating mainly HMM-based speech and natural language systems in word level, which is obviously inadequate for the morphologically complex agglutinative languages, our model constructs a spoken language system based on the phoneme-level integration. The TDNN-CYK spoken language architecture is designed and implemented using the TDNN-based diphone recognition module integrated with the table-driven phonological/morphological co-analysis. Our integration model provides a seamless integration of speech and natural language for connectionist speech recognition systems especially for morphologically complex languages such as Korean. Our experiment results show that the speaker-dependent continuous Eojeol (word) recognition can be integrated with the morphological analysis with over 80\% morphological analysis success rate directly from the speech input for the middle-level vocabularies.
dc.description12 pages, Latex Postscript, compressed, uuencoded, will be presented in TWLT-8
dc.identifierhttps://arxiv.org/abs/cmp-lg/9411013
dc.identifierhttp://arxiv.org/abs/cmp-lg/9411013
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/151110
dc.subjectComputation and Language
dc.titlePhoneme-level speech and natural language intergration for agglutinative languages
dc.typetext

Files

Collections