This paper describes an efficient way of representing a bigram language model with a finite state network used by a beam-search based and continuous speech HMM recognizer. In a previous paper , a compact tree-based organization of the search space was presented, that could be further reduced through an optimization algorithm. There, it was pointed out that for a 10,000-word newspaper dictation task the minimization step could have taken a lot of time and space on a standard workstation. In this paper, a new compilation technique that takes into account the particular tree-based topology is described. Results show that without additional time and space costs, the new technique produces networks equivalent to the tree-based ones but almost as small as the optimized one.
Bibliographic reference. Brugnara, Fabio / Cettolo, Mauro (1995): "Improvements in tree-based language model representation", In EUROSPEECH-1995, 1797-1800.