Author | Conference | Journal | Organization | Year | DOI
Look for results that meet for the following criteria:
Academic
Publications
A Risk-Aware Modeling Framework for Speech Summarization

A Risk-Aware Modeling Framework for Speech Summarization,10.1109/TASL.2011.2159596,IEEE Transactions on Audio, Speech & Language Processing,Berlin Che

Edit
A Risk-Aware Modeling Framework for Speech Summarization  
BibTex | RIS | RefWorks Download
Extractive speech summarization attempts to select a representative set of sentences from a spoken document so as to succinctly describe the main theme of the original document. In this paper, we adapt the notion of risk minimization for extrac- tive speech summarization by formulating the selection of sum- mary sentences as a decision-making problem. To this end, we de- velop several selection strategies and modeling paradigms that can leveragesupervisedandunsupervisedsummarizationmodelstoin- herit their individual merits as well as to overcome their inherent limitations. On top of that, various component models are intro- duced, providing a principled way to render the redundancy and coherence relationships among sentences and between sentences and the whole document, respectively. A series of experiments on speech summarization seem to demonstrate that the methods de- duced from our summarization framework are very competitive with existing summarization methods. Broadly speaking, a summary can be either abstractive or ex- tractive (2). In abstractive summarization, a fluent and concise abstract that reflects the key concepts of a document is gen- erated, whereas in extractive summarization, the summary is usually formed by selecting salient sentences from the original document. The former requires highly sophisticated natural lan- guage processing (NLP) techniques, including semantic repre- sentation and inference, as well as natural language generation, while this would make abstractive approaches difficult to repli- cate or extend from constrained domains to more general do-
Journal: IEEE Transactions on Audio, Speech & Language Processing - TASLP , vol. 20, no. 1, pp. 199-210, 2012
Cumulative Annual
View Publication
The following links allow you to view full publications. These links are maintained by other sources not affiliated with Microsoft Academic Search.
Share this on