An algorithm of high resolution and efficient multiple string hypothesization for continuous speech recognition using inter-word models

We propose a new accurate string hypothesization algorithm to find the N-best multiple string hypotheses in continuous speech recognition. The algorithm differs from the conventional N-best search algorithms in that it allows the use of the same set of long term language model scores and the detailed context-dependent subword models such as inter-word context dependent triphone models in both forward and backward search for high performance speech recognition. It is an extension of the tree-trellis N-best search algorithm[1]. The inter-word context dependency is exactly preserved in both forward partial path map preparation and the proposed backward N-best multiple string hypothesis tree search. The search efficiency is maximized by applying the same high resolution acoustic and language models in both search directions. When search heuristics are used, the proposed approach provides a more accurate string model matching than that of the conventional frame-synchronous Viterbi beam search decoder