Large vocabulary speech recognition using neural-fuzzy and concept networks
This paper describes a new algorithm for large vocabulary speech recognition using two kinds of connectionist models. The first one is a phoneme recognition model which uses a method combining Neural Nets and Fuzzy Inference (here called Neural-Fuzzy). The other is a connected-word sequence selection method using semantic information about conceptual relationships among vocabulary words.
Unable to display preview. Download preview PDF.
- A. Amano, T. Aritsuka, N. Hataoka, and A. Ichikawa, On the Use of Neural Networks and Fuzzy Logic in Speech Recognition, in Proceedings of the IJCNN-89, June 1989Google Scholar
- N. Hataoka, A. Amano, and A. Ichikawa, Large Vocabulary Speech Recognition Using Concept Networks, in Proceedings of the IJCNN-89, June 1989Google Scholar
- A. Amano, N. Hataoka, and A. Ichikawa, Phoneme Recognition Based On Phoneme-Pair Discrimination Rules, in Proceedings of 7th FASE Symposium, pp999, August 1988Google Scholar
- H. Fujisawa, A. Hatakeyama, and J. Higashino, A Personal Universal Filing System Based on the Concept-Relation Model, in Proceedings of First Int. Conf. Expert Database Systems, SC, pp.31–44, April 1986.Google Scholar
- N. Hataoka, A. Amano, S. Yajima, and H. Endoh, VCV Segmentation and Phoneme Recognition in Continuous Speech, in Proceedings of the IEEE ICASSP-86, April 1986.Google Scholar
- D.E. Rumelhart, G.E. Hinton, and R.J. Williams, Learning Internal Representations by Error Propagation, in Parallel Distribution Processing, vol.1, pp.318–362, MIT Press, Cambridge, 1986Google Scholar