| 摘要 |
<p>A method and system for identifying spoken sounds in continuous speech by using a voting window provides improved performance in a speech-recognition system. In a speech-recognition system (50) having a plurality of classifiers (30, 34, 38, 42), a voting window includes a sequence of outputs from each of the classifiers. For each classifier (30, 34, 38, 42), a voting sum is generated corresponding to the voting window. A spoken sound is identified by determining which classifier (30, 34, 38, 42) corresponds to the greatest voting sum.</p> |
