Key points are not available for this paper at this time.
Based on the principle of large margin classifier, recently we proposed two novel training methods, namely large margin estimation (LME) 8 and maximum relative margin estimation (MRME) 9 for speech recognition. In LME or MRME, HMM parameters are estimated to maximize the minimum margin among all training utterances. However their original formulation is limited to isolated-word ASR tasks. In this paper, we propose a new training method based on N-best string models to extend the original MRME framework to continuous speech recognition. We also study a new definition of relative margin which is more theoretically sound than the one used in 9. Experimental results in a connected digit recognition task clearly show that the string-level MRME is very effective in terms of reducing recognition error rates by up to 57% over our best MCE-trained models. A string error rate as low as 0.84% has been achieved on the standard TIDIGITS test set, which is the best result that has ever been reported in this task.
Liu et al. (Sat,) studied this question.