One common method for keyword spotting in unconstrained speech is based upon a two pass strategy consisting of Viterbi-decoding to detect and segment possible keyword hits, followed by the verification of those hit. In this thesis, we proposed a simple one-pass strategy where computation of the confidence measure is computed simultaneously with a Viterbi like decoding stage for verification purposes. However, backtracking is not required, which when coupled with the need for only a single pass through the utterance significantly reduces the memory requirements of this algorithm. This feature makes it well suit for devices where processing power and memory are limited. Experimental results on spotting days of the week in continuous speech indicate that the proposed algorithm has compara...[ Read more ]

One common method for keyword spotting in unconstrained speech is based upon a two pass strategy consisting of Viterbi-decoding to detect and segment possible keyword hits, followed by the verification of those hit. In this thesis, we proposed a simple one-pass strategy where computation of the confidence measure is computed simultaneously with a Viterbi like decoding stage for verification purposes. However, backtracking is not required, which when coupled with the need for only a single pass through the utterance significantly reduces the memory requirements of this algorithm. This feature makes it well suit for devices where processing power and memory are limited. Experimental results on spotting days of the week in continuous speech indicate that the proposed algorithm has comparable performance with two pass strategy.