Date of Original Version

10-2013

Type

Conference Proceeding

Journal Title

Proceedings of International Joint Conference on Natural Language Processing (IJCNLP)

First Page

648

Last Page

654

Abstract or Description

This paper presents a graph-based model that integrates prosodic features into an unsupervised speech summarization framework without any lexical information. In particular it builds on previous work using mutually reinforced random walks, in which a two-layer graph structure is used to select the most salient utterances of a conversation. The model consists of one layer of utterance nodes and another layer of prosody nodes. The random walk algorithm propagates scores between layers to use shared information for selecting utterance nodes with highest scores as summaries. A comparative evaluation of our prosody-based model against several baselines on a corpus of academic multi-party meetings reveals that it performs competitively on very short summaries, and better on longer summaries according to ROUGE scores as well as the average relevance of selected utterances.

Share

COinS
 

Published In

Proceedings of International Joint Conference on Natural Language Processing (IJCNLP), 648-654.