New language models using phrase structures extracted from parse trees
Takatoshi Jitsuhiro, Hirofumi Yamamoto, Setsuo Yamada, Yoshinori Sagisaka · 2001
This paper proposes a new speech recognition scheme using three linguistic constraints. Multi-class composite bigram models [1] are used in the first and second passes to reflect word-neighboring characteristics as an extension of conventional word n-gram models. Trigram models with constituent boundary markers and word pattern models are both used in the third pass to utilize phrasal constraints and headword cooccurrences, respectively. These two models are made using a training text corpus with phrase structures given by an examplebased Transfer-Driven Machine Translation (TDMT) parser [2]. Speech recognition experiments show that the new recognition scheme reduces word errors 9.50% from the conventional scheme by using word-neighboring characteristics, that is only the multi-class composite bigram models.