Dynamic Bayesian Networks and the Concatenation Problem in Speech Recognition

Geoffrey Zweig

EECS Department
University of California, Berkeley
Technical Report No. UCB/CSD-96-927
December 1996

http://www.eecs.berkeley.edu/Pubs/TechRpts/1996/CSD-96-927.pdf

This report describes a method for structuring dynamic Bayesian networks so that word and sentence-level models can be constructed from low-level phonetic models. This ability is a fundamental prerequisite for large-scale speech recognition systems, and is well-addressed in the context of hidden Markov models. With dynamic Bayesian networks, however, subword units cannot simply be concatenated together, and an entirely different approach is necessary.


BibTeX citation:

@techreport{Zweig:CSD-96-927,
    Author = {Zweig, Geoffrey},
    Title = {Dynamic Bayesian Networks and the Concatenation Problem in Speech Recognition},
    Institution = {EECS Department, University of California, Berkeley},
    Year = {1996},
    Month = {Dec},
    URL = {http://www.eecs.berkeley.edu/Pubs/TechRpts/1996/5297.html},
    Number = {UCB/CSD-96-927},
    Abstract = {This report describes a method for structuring dynamic Bayesian networks so that word and sentence-level models can be constructed from low-level phonetic models. This ability is a fundamental prerequisite for large-scale speech recognition systems, and is well-addressed in the context of hidden Markov models. With dynamic Bayesian networks, however, subword units cannot simply be concatenated together, and an entirely different approach is necessary.}
}

EndNote citation:

%0 Report
%A Zweig, Geoffrey
%T Dynamic Bayesian Networks and the Concatenation Problem in Speech Recognition
%I EECS Department, University of California, Berkeley
%D 1996
%@ UCB/CSD-96-927
%U http://www.eecs.berkeley.edu/Pubs/TechRpts/1996/5297.html
%F Zweig:CSD-96-927