In this paper we introduce a well-motivated abstract pruning
criterion for LVCSR decoders based on the anticipated recombination
of HMM state alignment paths. We show that several
heuristical pruning methods common in dynamic network
decoders are approximations of this pruning criterion.
The abstract criterion is too complex to be applied directly
in an efficient manner, so we derive approximations which can
be applied efficiently.
Our new pruning methods allow much more exhaustive pruning of the search space than previous methods. We show that the size of the search space can be reduced by up to 50% at equal precision over the previous state of the art, and the RTF by 20%.
The abstract pruning criterion can be considered a guide to derive effective pruning methods for any kind of time synchronous decoder.
Index Terms: speech recognition, search, pruning
Bibliographic reference. Nolden, David / Schlüter, Ralf / Ney, Hermann (2012): "Search space pruning based on anticipated path recombination in LVCSR", In INTERSPEECH-2012, 1015-1018.