Stochastic Modeling as a Means of Automatic Speech Recognition (1975)
Defense Technical Information Center · leaf 20
f (3) "the word ’what’," dcscibcs a particular point in the hierarchical state space in our simple example. Since each of the networks is finite, it is possible to define a new network with a separate node for each point in the hierarchical space. In terms of the knowledge represented, this I new… … FIGURE 4 Actually it is possible to represent more knowledge in the integrated network than in the hierarchical system. For example, phonological rules which apply across word boundaries (such as the palatalization in the word pair did you") may be used to make modifications to the network Note…
Baker, James K · Carnegie-mellon univ pittsburgh pa dept of computer science · Computer applications · Speech recognition · Acoustic signals · Markov processes · Network flows · Phonetics · Semantics · Signal processing · Syntax · Theses
Internet Archive · Defense Technical Information Center · Public domain (US government work). Free to use for anything.
