Phoneme-level speech and natural language intergration for agglutinative languages

A 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 phono-logical/morphological co-analysis. Our integration model provides a seamless integration of speech and natural language for con-nectionist speech recognition systems especially for morphologically complex languages such as Korean. Our experiment resultsdation). We also thank to WonIl Lee for coding the lexicon and the morphological parser and to professor Hong Jeong for his valuable suggestions for the earlier draft of this paper. An extended version of this paper was submitted to the journal of natural language engineering for a review. 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.