Lightweight Spoken Utterance Classification with CFG, tf-idf and Dynamic Programming

Abstract

We describe a simple spoken utterance classification method suitable for data-sparse domains which can be approximately described by CFG grammars. The central idea is to perform robust matching of CFG rules against output from a large-vocabulary recogniser, using a dynamic programming method which optimises the tf-idf score of the matched grammar string. We present results of experiments carried out on a substantial CFG-based medical speech translator and the publicly available Spoken CALL Shared Task. Robust utterance classification using the tf-idf method strongly outperforms plain CFG-based recognition for both domains. When comparing with Naive Bayes classifiers trained on data sampled from the CFG grammars, the tf-idf/dynamic programming method is much better on the complex speech translation domain, but worse on the simple Spoken CALL Shared Task domain.

The work described here was funded by the Fondation privée des Hôpitaux universitaires de Genève and Unitec. We would like to thank Pierrette Bouillon for semantic annotation of the test data and many helpful suggestions, and Nuance Inc for generously making their software available to us for research purposes.