Discriminative keyword spotting

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.

Robust discriminative keyword spotting for emotionally colored spontaneous speech using bidirectional LSTM networks

“…In [3] an algorithm for the computation of the weight vector w in Equation 1 is presented. The algorithm aims at training the weights w in a way that they maximize the average AUC on unseen data.…”

“…Feature function φ1A is the same as used in [3] and is based on the hierarchical phoneme classifier described in [13]. The classifier outputs a confidence gp(x) that phoneme p is pronounced in x which is then summed over the whole phoneme sequence to give…”

“…The remaining feature functions φ2 -φ7 used in this work are the same as in [3]. φ2 -φ5 measure the Euclidean distance between feature vectors at both sides of the suggested phoneme boundaries, assuming that the correct alignment will produce a large sum of distances, since the distances at the phoneme boundaries are likely to be high compared to those within a phoneme.…”

“…For these reasons we follow [3] in using a supervised, discriminative approach to keyword spotting, that does not require the use of HMMs. In general, discriminative learing algorithms are likely to outperform generative models such as HMMs since the objective function used during training more closely reflects the actual decision task.…”

“…In general, discriminative learing algorithms are likely to outperform generative models such as HMMs since the objective function used during training more closely reflects the actual decision task. The discriminative method described in [3] uses feature functions to non-linearly map the speech utterance, along with the target keyword, into an abstract vector space. It was shown to prevail over HMM modeling.…”