Corrections to "Segmental minimum Bayes-risk decoding for automatic speech recognition"

In our recently published paper [1], we presented a risk-based lattice cutting procedure to segment ASR word lattices into smaller sub-lattices as a means to to improve the efficiency of Minimum Bayes-Risk (MBR) rescoring. In the experiments reported [1], some of the hypotheses in the original lattices were inadvertently discarded during segmentation, and this affected MBR performance adversely. This note gives the corrected results as well as experiments demonstrating that the segmentation process does not discard any paths from the original lattice.