To improve the performance of continuous speech recognition, it is effective to incorporate grammatical knowledge of task into a word network of a FSN (finite state network) form. But, recently , some of them requires huge memory, so we introduce an ef ficient memory management method for a large word network; distributed FSN model and hiearchical memory model. The system keeps the word network divided to small sub-networks, and activates each sub-network when necessary. Using this method, we can recognize continuously spoken sentences of Japanese addresses, which are made of 390K geographic names, with only 5.6 Mbytes local memory in average.

Full Paper

Bibliographic reference.  Iwasaki, Tomohiro / Abe, Yoshiharu (1997): "A memory management method for a large word network", In EUROSPEECH-1997, 171-174.