15th Annual Conference of the International Speech Communication Association

September 14-18, 2014

Removing Redundancy from Lattices

David Nolden (1), Hagen Soltau (2), Daniel Povey (3), Pegah Ghahremani (3), Lidia Mangu (2), Hermann Ney (1)

(1) RWTH Aachen University, Germany
(2) IBM T.J. Watson Research Center, USA
(3) Johns Hopkins University, USA

In this work we present a novel word lattice filtering algorithm which removes redundancy from lattices. We use the filtering algorithm to analyze lattices obtained from dynamic network and transducer-based LVCSR decoders from several sites regarding size, coverage, and redundancy. We show that our filtering algorithm reduces the size of lattices by 30 to 90% without degrading the oracle word error rate.

Full Paper

Bibliographic reference.  Nolden, David / Soltau, Hagen / Povey, Daniel / Ghahremani, Pegah / Mangu, Lidia / Ney, Hermann (2014): "Removing redundancy from lattices", In INTERSPEECH-2014, 656-660.