TOKEN PASSING: A SIMPLE CONCEPTUAL MODEL FOR CONNECTED SPEECH RECOGNITION SYSTEMS
S.J. Young, N.H. Russell, J.H.S. Thornton
July 31, 1989
This paper describes a simple but powerful abstract model in which connected word recognition is viewed as a process of passing tokens around a transition network. The advantages of this unifying view are many. The various apparently different connected word algorithms can be represented within the same conceptual framework simply by changing the network topology, the application of grammatical constraints is straightforward, and perhaps most importantly, the entire structure is independent of the actual underlying pattern matching technology. To illustrate the power of this conceptual model, the paper concludes by describing some work done under the UK Alvey-sponsored VODIS Project in which the Token Passing paradigm enabled the One Pass algorithm to be straightforwardly extended to include the generation of multiple alternatives and context free syntactic constraints.
If you have difficulty viewing files that end '.gz',
which are gzip compressed, then you may be able to find
tools to uncompress them at the gzip
web site.
If you have difficulty viewing files that are in PostScript, (ending
'.ps' or '.ps.gz'), then you may be able to
find tools to view them at
the gsview
web site.
We have attempted to provide automatically generated PDF copies of documents for which only PostScript versions have previously been available. These are clearly marked in the database - due to the nature of the automatic conversion process, they are likely to be badly aliased when viewed at default resolution on screen by acroread.