Segmentation ART: A Neural Network for Word Recognition from Continuous Speech
Carpenter, Gail A.
Wilson, Frank D. M.
MetadataShow full item record
The Segmentation ATIT (Adaptive Resonance Theory) network for word recognition from a continuous speech stream is introduced. An input sequeuce represents phonemes detected at a preproccesing stage. Segmentation ATIT is trained rapidly, and uses a fast-learning fuzzy ART modules, top-down expectation, and a spatial representation of temporal order. The network performs on-line identification of word boundaries, correcting an initial hypothesis if subsequent phonemes are incompatible with a previous partition. Simulations show that the system's segmentation perfonnance is comparable to that of TRACE, and the ability to segment a number of difficult phrases is also demonstrated.