Discriminative Topic Segmentation of Text and Speech

Abstract

We explore automated discovery of topically-coherent segments in speech or text sequences. We give two new discriminative topic segmentation algorithms which employ a new measure of text similarity based on word co-occurrence. Both algorithms function by finding extrema in the similarity signal over the text, with the latter algorithm using a compact support-vector based description of a window of text or speech observations in word similarity space to overcome noise introduced by speech recognition errors and off-topic content. In experiments over speech and text news streams, we show that these algorithms outperform previous methods. We observe that topic segmentation of speech recognizer output is a more difficult problem than that of text streams; however, we demonstrate that by using a lattice of competing hypotheses rather than just the one-best hypothesis as input to the segmentation algorithm, the performance of the algorithm can be improved.