%Aigaion2 BibTeX export from Idiap Publications
%Saturday 21 December 2024 04:51:22 PM

@INCOLLECTION{Grangier_WILEY_2009,
         author = {Grangier, David and Keshet, Joseph and Bengio, Samy},
         editor = {Keshet, Joseph and Bengio, Samy},
       projects = {Idiap},
          title = {Discriminative Keyword Spotting},
      booktitle = {Automatic Speech and Speaker Recognition: Large Margin and Kernel Methods},
           year = {2009},
      publisher = {John Wiley and Sons},
       abstract = {This chapter introduces a discriminative method for detecting and spotting keywords in spoken utterances. Given a word represented as a sequence of phonemes and a spoken utterance, the keyword spotter predicts the best time span of the phoneme sequence in the spoken utterance along with a confidence. If the prediction confidence is above certain level the keyword is declared to be spoken in the utterance within the predicted time span, otherwise the keyword is declared as not spoken. The problem of keyword spotting training is formulated as a discriminative task where the model parameters are chosen so the utterance in which the keyword is spoken would have higher confidence than any other spoken utterance in which the keyword is not spoken. It is shown theoretically and empirically that the proposed training method resulted with a high area under the receiver operating characteristic (ROC) curve, the most common measure to evaluate keyword spotters. We present an iterative algorithm to train the keyword spotter efficiently. The proposed approach contrasts with standard spotting strategies based on HMMs, for which the training procedure does not maximize a loss directly related to the spotting performance. Several experiments performed on TIMIT and WSJ corpora show the advantage of our approach over HMM-based alternatives.}
}