A New Framework For Large Vocabulary Keyword Spotting Using Two-Pass Confidence Measure

Abstract

In this paper, a new framework for large vocabulary keyword spotting is proposed, which involves three phases. In the first phase, N-best sub-word lattice is generated by hidden Markov model (HMM). Keyword candidates are hypothesized by dynamic keyword matching during the second phase. In the last phase, two-pass confidence measure, which provides complementary information, is used for keyword verification. Experimental results show that, with the use of these improvements, the keyword spotting system proves to be more accurate and robust without much computation cost.