| 摘要 |
PROBLEM TO BE SOLVED: To allow a speech recognition system to provide a possibility for speech-driven selection of a list element coming from a natural language different from a trained language. SOLUTION: The present invention relates to a method for selecting via a speech input a list element from a list of elements, the method comprising the followings: a step recognizing a string of subword units for the speech input, a step comparing the recognized string of subword units to the list of elements and generating a candidate list of best matching elements based on the comparison result, wherein for generating the candidate list of best matching elements a confusion matrix is used which contains matrix elements comprising information about the confusion probability of subword units of different languages. COPYRIGHT: (C)2009,JPO&INPIT
|
