| 摘要 |
A voice recognition system selecting word templates necessary for voice recognition from among a plurality of word templates, including: an input phoneme extraction unit (31) for extracting distinctive phonemes which can be clearly recognized from an input pattern of the voice, and all phonemes possibly existing in the input pattern; a dictionary phoneme extraction unit (32) for extracting the distinctive phonemes which can be clearly recognized and can be previously determined at each word template, and all phonemes possibly existing at each word template; and a pre-selector (33) for selecting valid word templates for performing voice recognition based on phoneme information extracted by the input phoneme extraction unit (31) and the dictionary phoneme extraction unit (32). Such a system can enable words to be recognised at high speed from among a large vocabulary. |
