For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Speech Recognition Using Function-Word N-Grams and Content-Word N-Grams
Ryosuke ISOTANI Shoichi MATSUNAGA Shigeki SAGAYAMA
IEICE TRANSACTIONS on Information and Systems
Publication Date: 1995/06/25
Print ISSN: 0916-8532
Type of Manuscript: Special Section PAPER (Special Issue on Spoken Language Processing)
speech recognition, stochastic language model, N-gram, function words, content words,
Full Text: PDF(534.7KB)>>
This paper proposes a new stochastic language model for speech recognition based on function-word N-grams and content-word N-grams. The conventional word N-gram models are effective for speech recognition, but they represent only local constraints within a few successive words and lack the ability to capture global syntactic or semantic relationships between words. To represent more global constraints, the proposed language model gives the N-gram probabilities of word sequences, with attention given only to function words or to content words. The sequences of function words and of content words are expected to represent syntactic and semantic constraints, respectively. Probabilities of function-word bigrams and content-word bigrams were estimated from a 10,000-sentence text database, and analysis using information theoretic measure showed that expected constraints were extracted appropriately. As an application of this model to speech recognition, a post-processor was constructed to select the optimum sentence candidate from a phrase lattice obtained by a phrase recognition system. The phrase candidate sequence with the highest total acoustic and linguistic score was sought by dynamic programming. The results of experiments carried out on the utterances of 12 speakers showed that the proposed method is more accurate than a CFG-based method, thus demonstrating its effectiveness in improving speech recognition performance.