| 摘要 |
<P>PROBLEM TO BE SOLVED: To provide a technology, used for a speech recognition system, for evaluating fitness of grammar. <P>SOLUTION: A plurality of statements are received (701) from within a grammar structure. A number of alignment regions across the statements are identified (703) by aligning the statements on a word set basis. A number of potential confusion zones are identified (705) across the statements. For each of the identified potential confusion zones, phonetic pronunciations of the words within the potential confusion zone are analyzed to determine (707) a measure of confusion probability between the words when audibly processed by a speech recognition system during the computing event. An identity of the potential confusion zones across the statements and their corresponding measure of confusion probability are reported (709) to facilitate grammar structure improvement. <P>COPYRIGHT: (C)2012,JPO&INPIT |
