Large Vocabulary Speech Recognition Using Neural-Fuzzy and Concept Networks

An algorithm for large vocabulary speech recognition using two kinds of connectionist models is described. The first one is a phoneme recognition model which uses a method combining neural nets and fuzzy inference called neural-fuzzy. This method uses neural nets as acoustic feature detectors and fuzzy logic as a decision procedure. The other is a connected-word sequence selection method using semantic information about conceptual relationships among vocabulary words. The basic idea of this method is derived from the fact that human beings can recognize words and content precisely from the topic and/or the context even when ambiguous utterances appear in conversation. The proposed method selects only word sequences that are related to each other in meaning from the several candidates, by using excitatory and inhibitory interactions with units (words). >

[1]  N. Hataoka,et al.  VCV Segmentation and phoneme recognition in continuous speech , 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[2]  A. Amano,et al.  On the use of neural networks and fuzzy logic in speech recognition , 1989, International 1989 Joint Conference on Neural Networks.

[3]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[4]  A. Amano,et al.  Large vocabulary speech recognition using concept networks , 1989, International 1989 Joint Conference on Neural Networks.

[5]  Hiromichi Fujisawa,et al.  A Personal Universal Filing System Based on the Concept-Relation Model , 1986, Expert Database Conf..

[6]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .