ICSLP '96: A Fertility Channel Model for Post-Correction
of Continuous Speech Recognition
Please download a copy of the paper by clicking here:
ICSLP '96 Paper in gzip'ed PostScript format
(~28K).
Abstract:
We have implemented a post-processor called SPEECHPP to correct
word-level errors committed by an arbitrary speech recognizer.
Applying a noisy-channel model, SPEECHPP uses a Viterbi beam-search
that employs language and channel models. Previous work demonstrated
that a simple word-for-word channel model was sufficient to yield
substantial increases in word accuracy. This paper demonstrates that
some improvements in word accuracy result from augmenting the channel
model with an account of word fertility in the channel. This work
further demonstrates that a modern continuous speech recognizer can be
used in ``black-box'' fashion for robustly recognizing speech for
which the recognizer was not originally trained. This work also
demonstrates that in the case where the recognizer can be tuned to the
new task, environment, or speaker, the post-processor can also
contribute to performance improvements.
Last Change 96 May 15 by