A network model is proposed that uses a special node called epsilon -node. This model makes flexible path weight control of the network representing the acceptable sentences (ASN) possible by giving a score to the epsilon -node. The path weight control strategy is developed using a rule-based system, which has the ability to provide an adequate ASN according to the flow of conversation. A state-transition-network-based system is adopted in order to follow and adapt to the changing topics of conversation. A high-speed, highly reliable conversational speech understanding system is realized.
|ジャーナル||ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings|
|出版ステータス||Published - 1986 12月 1|
ASJC Scopus subject areas