Keyword spotting (KWS) refers to detection of a limited number of given keywords in speech utterances. In this paper, we evaluate a robust keyword spotting system based on hidden markov models for speaker independent Persian conversational telephone speech. Performance of base line keyword spotter is improved by means of normalizing features using cepstral mean and variance normalization (CMVN) and cepstral gain normalization (CGN). And better performance is gained by applying auto-regressive moving average (ARMA) filter on normalized features. Experimental results show that although all these methods improve keyword spotting performance, CMVN and ARMA (MVA) processing of PLP features works much better on our Persian conversational telephone speech database and 41% improvement to baseline system is achieved at false alarm (FA) rate equal to 8.6 FA/KW/Hour.

No abstract

No abstract

Evaluating the accuracy of HMM-based and SVM-based spotters in detecting keywords and recognizing the true place of keyword occurrence shows that the HMM-based spotter detects the place of occurrence more precisely than the SVM-based spotter. On the other hand, the SVM-based spotter performs much better in detecting keywords and has higher detection rate.In this paper, we propose a rule based combination method for combining output of these two keyword spotters in order to benefit from features and advantages of each method and overcome weaknesses and drawbacks of them. Experimental results of applying this combination method on both clean and noisy test sets show that its recognition rate has considerable growth rather than each individual method.