Rescoring under fuzzy measures with a multilayer neural network in a rule-based speech recognition system

A speech rescoring system is developed on a set of phonetic hypotheses produced by a bottom-up knowledge-based decoder. An original method to automatically compute a fuzzy membership function from top-down acoustic rules statistics is compared with a possibilistic measure. To aggregate the fuzzy degrees into a phonetic score, a multilayer neural network is trained on the results of all the rules in order to detect how these rules characterize different phonemes and then in order to give a weight to each rule. The rescoring performance of top-down rules for fricatives is discussed on an isolated-word speech database of French with 1000 utterances pronounced by five speakers