Spoken Sentence Recognition Based on HMM-LR with Hybrid Language Modeling

Kenji KITA  Tsuyoshi MORIMOTO  Kazumi OHKURA  Shigeki SAGAYAMA  Yaneo YANO  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E77-D   No.2   pp.258-265
Publication Date: 1994/02/25
Online ISSN: 
DOI: 
Print ISSN: 0916-8532
Type of Manuscript: Special Section PAPER (Special Issue on Natural Language Processing and Understanding)
Category: 
Keyword: 
speech recognition,  LR parsing,  hidden Markov model,  HMM-LR,  language model,  

Full Text: PDF(720.1KB)>>
Buy this Article




Summary: 
This paper describes Japanese spoken sentence recognition using hybrid language modeling, which combines the advantages of both syntactic and stochastic language models. As the baseline system, we adopted the HMM-LR speech recognition system, with which we have already achieved good performance for Japanese phrase recognition tasks. Several improvements have been made to this system aimed at handling continuously spoken sentences. The first improvement is HMM training with continuous utterances as well as word utterances. In previous implementations, HMMs were trained with only word utterances. Continuous utterances are included in the HMM training data because coarticulation effects are much stronger in continuous utterances. The second improvement is the development of a sentential grammar for Japanese. The sentential grammar was created by combining inter- and intra-phrase CFG grammars, which were developed separately. The third improvement is the incorporation of stochastic linguistic knowledge, which includes stochastic CFG and a bigram model of production rules. The system was evaluated using continuously spoken sentences from a conference registration task that included approximately 750 words. We attained a sentence accuracy of 83.9% in the speaker-dependent condition.