Hiertalker: A default hierarchy of high order neural networks that learns to read english aloud

Summary form only given. The authors proposed and tested a learning procedure, based on a default hierarchy of high-order neural networks, which exhibited an enhanced capability of generalization and a good efficiency. This architecture is suitable for learning regularities embedded in a stream of information with inherent long range correlations. When applied to the conversion of English works to phonemes, a simulator of such a hierarchy, HIERtalker, achieved an accuracy of typically 99% for the words in the training set, and 96% for new words. Also, HIERtalker used considerably less computer time than NETtalk did. The Hebbian learning rule without any error corrections was also used. >