Segmental models have been used in speech recognition to reduce the effect of the counterfactual assumptions of statistical independence which are made in more conventional systems. They have achieved their aim at the cost of a large increase in computational load arising from making assumptions on entire segments rather than on individual frames. In this paper we show how segmental algorithms can be refactored as iterative calculations, removing most of additional computational burden they impose. We also show that the iterative implementation leads naturally to increased flexibility in the handling of timing, allowing an arbitrary timing model to be incorporated at no extra cost.
Bibliographic reference. Houghton, S. M. / Champion, Colin J. (2015): "Inductive implementation of segmental HMMs as CS-HMMs", In INTERSPEECH-2015, 776-780.