| Popis: |
The Vicens-Reddy system is unique in the sense that it approaches the problem of speech recognition as a whole, rather than treating particular aspects of the problem as in previous attempts. For example, where earlier systems treated only segmentation of speech into phoneme groups, or detected phonemes in a given context, the Vicens-Reddy system processes the incoming speech signal, applies heuristics to segment the signal and to identify phoneme- like units and then uses the total phonemic pattern to recognize an entry in the lexicon. The Vicens-Reddy system divided into six parts: (1) hardware preprocessing, (2) software preprocessing, (3) segmentation, (4) recognition, (5) lexicon development, and (6) lexicon usage. |
