Sentence modeling for extractive speech summarization
Authors:
- 1 July 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 19457871,p. 1-6
Abstract
Extractive speech summarization, aiming to select an indicative set of sentences from a spoken document so as to concisely represent the most important aspects of the document, has emerged as an attractive area of research and experimentation. A recent school of thought is to employ the language modeling (LM) framework along with the Kullback-Leibler (KL) divergence measure for important sentence selection, which has shown preliminary promise for extractive speech summarization. Our work in this paper continues this general line of research in two significant aspects. First, we explore a novel sentence modeling approach built on top of the notion of relevance, where the relationship between a candidate summary sentence and the spoken document to be summarized is discovered through various granularities of context for relevance modeling. Second, not only lexical but also topical cues inherent in the spoken document are exploited for sentence modeling. Experiments on broadcast news summarization seem to demonstrate the performance merits of our methods when compared to several existing methods.Keywords
This publication has 18 references indexed in Scilit:
- Discriminative Training for Automatic Speech Recognition: Modeling, Criteria, Optimization, Implementation, and PerformanceIEEE Signal Processing Magazine, 2012
- Leveraging Kullback–Leibler Divergence Measures and Information-Rich Cues for Speech SummarizationIEEE Transactions on Audio, Speech, and Language Processing, 2010
- Exploring content models for multi-document summarization2009
- Statistical Language Models for Information Retrieval A Critical ReviewFoundations and Trends® in Information Retrieval, 2008
- A skip-chain conditional random field for ranking meeting utterances by importance2006
- Speech-to-Text and Speech-to-Speech Summarization of Spontaneous SpeechIEEE Transactions on Speech and Audio Processing, 2004
- Relevance based language models2001
- Generic text summarization using relevance measure and latent semantic analysis2001
- A trainable document summarizer1995
- On Information and SufficiencyThe Annals of Mathematical Statistics, 1951