A real-time task-oriented speech understanding system using keyword-spotting

The authors describe a real-time task-oriented spontaneous speech understanding system which extracts semantic content from the spotted keyword lattice using a newly developed LR parser. The parser is driven whenever a keyword candidate is spotted. The keyword candidates are fed into the parser to construct a semantic structure using a grammar. This efficient parsing enables real-time initial-state-free speech understanding. The parser comprises the following functional components: initial-state processing to check if a keyword candidate can be an initial keyword and to create a parsing stack, keyword connection processing to check if a current keyword can connect with a subsentence candidate, and sentence acceptance processing to check if subsentence candidates can be accepted as a sentence candidate. Experimental results for a fast-food task consisting of 30 keywords are presented to show the effectiveness of the system