The development of a speaker independent "general purpose" phonetic recognizer for Italian is described. The CSLU Toolkit was used to develop and implement the system. The recognizer, based on a frame-based hybrid HMM/ANN architecture trained on context-dependent categories to account for coarticulatory variation, recognizes 38 different phonemes (not including silence or closures), and can distinguish between stressed and unstressed vowels as well as open and closed voels. The APASCI corpus, containing nearly 2500 sentences read by 100 speakers, where the sentences have been deisgned to maximize the number of phonemes occnrring in different contexts, was used for training and testing. As of the time of this writing, a phoneme-level accuracy of 82.90
展开▼
