Summary
|
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. |
|
LR Parsing with a Category Reachability Test Applied to Speech Recognition Kenji KITA Tsuyoshi MORIMOTO Shigeki SAGAYAMA Publication IEICE TRANSACTIONS on Information and Systems Vol.E76-D No.1 pp.23-28 Publication Date: 1993/01/25 Online ISSN: DOI: Print ISSN: 0916-8532 Type of Manuscript: Special Section PAPER (Special Issue on Speech and Discourse Processing in Dialogue Systems) Category: Keyword: speech recognition, HMMs, LR parsing, reachability, LR-CRT algorithm, Full Text: PDF(526.6KB)>>
Summary: In this paper, we propose an extended LR parsing algorithm, called LR parsing with a category reachability test (the LR-CRT algorithm). The LR-CRT algorithm enables a parser to efficiently recognize those sentences that belong to a specified grammatical category. The key point of the algorithm is to use an augmented LR parsing table in which each action entry contains a set of reachable categories. When executing a shift or reduce action, the parser checks whether the action can reach a given category using the augmented table. We apply the LR-CRT algorithm to improve a speech recognition system based on two-level LR parsing. This system uses two kinds of grammars, inter- and intra-phrase grammars, to recognize Japanese sentential speech. Two-level LR parsing guides the search of speech recognition through two-level symbol prediction, phrase category prediction and phone prediction, based on these grammars. The LR-CRT algorithm makes possible the efficient phone prediction based on the phrase category prediction. The system was evaluated using sentential speech data uttered phrase by phrase, and attained a word accuracy of 97.5% and a sentence accuracy of 91.2% | ||||||||||
| ||||||||||
