Answers are grounded in this paper and cite their sources.
The choice of method for training a speech recognizer is posed as an optimization problem. The currently used method of maximum likelihood, while heuristic, is shown to be superior under certain assumptions to another heuristic: the method of conditional maximum likelihood.
No takes yet. Share an insight, caveat, or question.
Arthur Nádas (1983) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: