A comparison of training approaches for discriminative segmental models
Hao Tang, Kevin Gimpel, Karen Livescu · 2014
Segmental models such as segmental conditional random fields have had some recent success in lattice rescoring for speech recognition. They provide a flexible framework for incorpo-rating a wide range of features across different levels of units, such as phones and words. However, such models have mainly been trained by maximizing conditional likelihood, which may not be the best proxy for the task loss of speech recognition. In addition, there has been little work on designing cost func-tions as surrogates for the word error rate. In this paper, we investigate various losses and introduce a new cost function for training segmental models. We compare lattice rescoring results for multiple tasks and also study the impact of several choices required when optimizing these losses. Index Terms: speech recognition, segmental conditional ran-dom fields, empirical Bayes risk, large-margin training