DYNAMIC SEMANTIC CONTROL OF A SPEECH RECOGNITION SYSTEM

摘要

The speech recognition system recognizes speech and generates one or more wo rd strings, each of which is a hypothesis of the speech, and creates and stores a probability value (210) or score for each of the word strings. The speech recognition system also creates and stores, for each of the word strings, on e or more keyword-value pairs (213) that represent semantic elements and semantic values of the semantic elements for the speech that was spoken. One or more dynamic semantic rules are defined that specify how a probability value of a word string should be modified based on the information about external conditions, facts, or the environment of the application in relatio n to the semantic values of the word string (214). The dynamic semantic rules are applied to word strings and keyword-value pairs (214). The speech recognizer modifies one or more probability values, re-orders the word strin gs (216), and returns control to the application.