2002 · 60 citations · 10 references
ComputingComputer ScienceComputational LinguisticsCorpus LinguisticsNatural Language ProcessingDialogue SystemsLanguage ModelingLanguage ModelsN-gram AnalysisNatural Language GenerationSpeech RecognitionAccuracy-computational Cost TradeoffCpu OptimizationGraph GenerationGraph-to-text GenerationSpeech UnderstandingSpeech-based DialogueWord Error RateWord Generation
This paper proposes a large vocabulary spontaneous dialogue speech recognizer using cross-word context constrained word graphs. In this method, two approximation methods "cross-word context approximation" and "lenient language score smearing" are introduced to reduce the computational cost for word graph generation. The experimental results using a "travel arrangement corpus" show that this recognition method achieves a word hypotheses reduction of 25-40% and a cpu-time reduction of 30-60% compared to without approximation, and that the use of class bigram scores as the expected language score for each lexicon tree node decreases the word error rate 25-30% compared to without approximation.
10
Volker Steinbiss, Bach-Hiep Tran, Hermann Ney · 1994 · 144 citations
The 1994 HTK large vocabulary speech recognition system
Philip C. Woodland, C.J. Leggetter, J. J. Odell et al. · 2002 · 108 citations