Improved Speech Summarization and Spoken Term Detection with Graphical Analysis of Utterance Similarities

We present summarization and spoken term detection (STD) approaches that take into account similarities between utterances to be scored for summary extraction or ranking in STD. A graph is constructed in which each utterance is a node. Similar utterances are connected by edges, with the edge weights representing the degree of similarity. The similarity for summarization is topical similarity; that for STD is featurespace similarity. The score of each utterance for extraction in summarization and ranking in STD is not solely decided by the individual utterance but is influenced by similar utterances on the graph. Experimental results show significant improvements compared with two baselines in terms of the ROUGE evaluation for summarization and mean average precision for STD.