[snip]
> You may also find it useful to look at DP-like algorithms in the
> speech recognition area (alignment of phonetic sequences with phonetic
> dictionary entries) ...
One reference is "Better Alignment Procedures for Speech Recognition
Evaluation", W. M. Fisher and J. G. Fiscus, IEEE International Conference
on Acoustics, Speech, and Signal Processing 1993, pp. II-59 - II-62.
(It doesn't just use a phonetic dictionary, though -- if a word isn't in
the
dictionary, it generates its pron with TTP rules. ) And you can download
the
vanilla C code for a more general split/merge package which includes it,
aldistsm-1.2.tar.Z, via anonymous ftp from jaguar.ncsl.nist.gov/pub.
But I wouldn't call it a fast algorithm.
- Bill F.