Toward a massively parallel system for word recognition
Maurice K. Wong, Hon Wai Chun · The Journal of the Acoustical Society of America · 1986
This paper describes a massively parallel system for word recognition. Based on the connectionist network model, the system consists of a large number of simple neuronlike processing units, or nodes, which represent words, phonetic segments, or phonetic features. The computation consists of constant updating of activation levels of all nodes, resulting from the excitatory links and inhibitory links between the nodes. Input to the system consists of frame-by-frame scores of similarity to a set of predefined spectral filters, which represents the set of phonetic segments necessary for distinguishing between words in the vocabulary. These similarity scores are combined into phonetic feature indexes for each frame of speech as input to the feature nodes in the network. A linguistic knowledge base is built into the network, allowing both data-driven processing and top-down prediction to cooperate or compete in working toward the correct lexical hypothesis. The system has been implemented using a software package simulating massively parallel networks on a lisp machine. Preliminary testing of the system using digits and nine letters by one speaker is 100% successful in spite of the low frame-by-frame recognition accuracy.