Published in
Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.
DOI: 10.1109/icassp.2005.1415292
Links
- ORCID
- Institute of Electrical and Electronics Engineers
- [hdl.handle.net]
- [www.research.ed.ac.uk] | PDF
- [www.pure.ed.ac.uk] | PDF
- [www.researchgate.net] | PDF
- [citeseerx.ist.psu.edu] | PDF
- [citeseerx.ist.psu.edu] | PDF
- [homepages.inf.ed.ac.uk] | PDF
- [www.era.lib.ed.ac.uk] | PDF
- [homepages.inf.ed.ac.uk] | PDF
Tools
Maximum entropy segmentation of broadcast news
,
BalaKrishna Kolluru,
Yoshihiko Gotoh,
Steve Renals
Full text: Download
Abstract
This paper presents an automatic system for structuring and preparing a news broadcast for applications such as speech sum-marization, browsing, archiving and information retrieval. This process comprises transcribing the audio using an automatic speech recognizer and subsequently segmenting the text into utter-ances and topics. A maximum entropy approach is used to build statistical models for both utterance and topic segmentation. The experimental work addresses the effect on performance of the topic boundary detector of three factors: the information sources used, the quality of the ASR transcripts, and the quality of the utterance boundary detector. The results show that the topic segmentation is not affected severely by transcripts errors, whereas errors in the utterance segmentation are more devastating.