HMM based fast keyworld spotting algorithm with no garbage models

Abstract

The problem of discriminating keyword and non-keyword speech which is important in wordspotting applications is addressed. We have shown that garbage models cannot reduce both the rejection and false alarm rates simultaneously. To achieve this we have proposed a new scoring and search method for HMM based wordspotting without garbage models. This is a simple forward search method which incorporates the duration modelling of the keyword for efficient discrimination of keyword and non-keyword speech. This method is computationally fast, which makes it suitable for real-time implementation. The results are reported on a speaker independent database containing 10 keywords embedded in 150 carrier sentences.