Direct construction of compact context-dependency transducers from data
Venue
Computer Speech & Language (2013) (to appear)
Publication Year
2013
Authors
David Rybach, Michael Riley, Chris Alberti
BibTeX
Abstract
This paper describes a new method for building compact context-dependency
transducers for finite-state transducer-based ASR decoders. Instead of the
conventional phonetic decision tree growing followed by FST compilation, this
approach incorporates the phonetic context splitting directly into the transducer
construction. The objective function of the split optimization is augmented with a
regularization term that measures the number of transducer states introduced by a
split. We give results on a large spoken-query task for various n-phone orders and
other phonetic features that show this method can greatly reduce the size of the
resulting context-dependency transducer with no significant impact on recognition
accuracy. This permits using context sizes and features that might otherwise be
unmanageable.
