DocumentCode :
3152236
Title :
Sentence modeling for extractive speech summarization
Author :
Chen, Bing ; Hao-chin Chang ; Kuan-Yu Chen
Author_Institution :
Nat. Taiwan Normal Univ., Taipei, Taiwan
fYear :
2013
fDate :
15-19 July 2013
Firstpage :
1
Lastpage :
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 :
relevance feedback; speech processing; KL divergence measure; Kullback-Leibler divergence measure; LM framework; broadcast news summarization; extractive speech summarization; language modeling framework; relevance modeling; sentence modeling; sentence selection; spoken document; summary sentence; Context modeling; Measurement; Semantics; Speech; Speech recognition; Training; Vectors; Kullback-Leibler divergence; Speech summarization; language modeling; sentence modeling;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multimedia and Expo (ICME), 2013 IEEE International Conference on
Conference_Location :
San Jose, CA
ISSN :
1945-7871
Type :
conf
DOI :
10.1109/ICME.2013.6607518
Filename :
6607518
Link To Document :
بازگشت