UC BERKELEY
EECS technical reports
TECHNICAL REPORTS


CSD-96-927.pdf
CSD-96-927.ps
Oskicat catalog record
Conditions of Use

Archive Home Page

Dynamic Bayesian Networks and the Concatenation Problem in Speech Recognition

Authors:
Zweig, Geoffrey
Technical Report Identifier: CSD-96-927
December 11, 1996
CSD-96-927.pdf
CSD-96-927.ps

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.