Abstract

We present a semi-supervised algorithm for rescoring the output of a speech keyword search (KWS) system. Conventional loss functions such as squared-error and logistic loss are not suitable for optimizing the commonly-used KWS term-weighted value (TWV) performance metric. We derive a novel concave modified logistic log-likelihood function which lower-bounds TWV. We then use a manifold-regularized kernel classifier that maximizes this lower-bound. A manifold regularization term in our objective function uses available unlabeled speech data and makes our approach semi-supervised. This term is particularly useful for KWS in low-resource languages and ensures that the predicted keyword confidence scores are smooth on a low-dimensional manifold in the feature space. We conduct KWS experiments on the IARPA Babel Vietnamese task and show performance improvements in terms of the maximum …

Date

2014

Authors

Kartik Audhkhasi, Abhinav Sethy, Bhuvana Ramabhadran, Shrikanth S Narayanan

Conference

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Pages

7869-7873

Publisher

IEEE