| 摘要 |
PROBLEM TO BE SOLVED: To improve the performance of speech recognition with less time and effort required for generation of a speech recognition dictionary.SOLUTION: A recognition dictionary generation device reads in an interaction scenario in which progress procedures of interaction are described in accordance with a prescribed grammar, and extracts vocabularies spoken by a user from the read interaction scenario. After extracting the vocabularies, the recognition dictionary generation device acquires relevant vocabularies preliminarily set for the extracted vocabularies and generates a speech recognition dictionary including the extracted vocabularies and the acquired relevant vocabularies as vocabularies of speech recognition objects. |
