摘要 |
A speech recognition apparatus 100 comprises a speech analyzer 103 which extracts feature patterns of spontaneous speech divided into frames; a keyword model database (104, 105) 104 which prestores keyword which represent feature patterns of a plurality of keywords to be recognized; a garbage model database (104, 105) 105 which prestores feature patterns of components of extraneous speech to be identified; and a likelihood calculator 106 which calculates likelihood of feature values based on feature values patterns of each frames, keywords, and extraneous speech. The device 100 recognizes a keyword contained in the spontaneous speech by calculating cumulative likelihood based on the likelihood for each frame to match each HMM.
|