论文信息 - The DRAGON system--An overview

The DRAGON system--An overview

This paper briefly describes the major features of the DRAGON speech understanding system. DRAGON makes systematic use of a general abstract model to represent each of the knowledge sources necessary for automatic recognition of continuous speech. The model--that of a probabilistic function of a Markov process--is very flexible and leads to features which allow DRAGON to function despite high error rates from individual knowledge sources. Repeated use of a simple abstract model produces a system which is simple in structure, but powerful in capabilities.

J. Baker | J. Baker

[1] R. Bellman. Dynamic programming. , 1957, Science.

[2] L. Baum,et al. An inequality with applications to statistical estimation for probabilistic functions of Markov processes and to a model for ecology , 1967 .

[3] Lee D. Erman,et al. Working Papers in Speech Recognition - I, , 1972 .

[4] J. E. Paul,et al. Automatic Recognition of Continuous Speech: Further Development of a Hierarchical Strategy. , 1973 .

[5] Lee D. Erman,et al. A model and a system for machine recognition of speech , 1973 .