7th International Conference on Spoken Language Processing

September 16-20, 2002
Denver, Colorado, USA

Risk Based Lattice Cutting for Segmental Minimum Bayes-Risk Decoding

Shankar Kumar, William Byrne

Johns Hopkins University, USA

Minimum Bayes-Risk (MBR) speech recognizers have been shown to give improvements over the conventional maximum a-posteriori probability (MAP) decoders through N-best list rescoring and A* search over word lattices. Segmental MBR (SMBR) decoders simplify the implementation of MBR recognizers by segmenting the N-best lists or lattices over which the recognition is performed. We present a lattice cutting procedure that attempts to minimize the total Bayes-Risk of all word strings in the segmented lattice. We provide experimental results on the Switchboard conversational speech corpus showing that this segmentation procedure, in conjunction with SMBR decoding, gives modest but significant improvements over MAP decoders as well as MBR decoders on unsegmented lattices.

Full Paper

Bibliographic reference.  Kumar, Shankar / Byrne, William (2002): "Risk based lattice cutting for segmental minimum Bayes-risk decoding", In ICSLP-2002, 373-376.