The Community for Technology Leaders
RSS Icon
Subscribe
Shanghai
Sept. 21, 2005 to Sept. 23, 2005
ISBN: 0-7695-2432-X
pp: 662-667
Ling Guo , Nanjing University of Science and Technology
Ying-Chun Shi , Simulation Center, WuHan Institute of Communication Command
Xian-Zhong Zhou , Nanjing University of Science and Technology
Feng Zhang , Nanjing University of Science and Technology
ABSTRACT
<p>An algorithm on location and extraction of broadcast in news video is proposed in this paper. Firstly, input audio stream is divided into speech and non- speech segments by VQ (Vector Quantification) after a set of new features representing audio segments? time-variant characteristics are extracted, including HZCRR (High Zero-crossing Rate Ratio), LSTER (Low Short-time Energy Ratio) and HBFERR (High Basic-frequency-energy Rate Ratio), etc. Then a QGMM (Quasi Gaussian Mixture Model) is presented to describe the speaker?s identity and BIC (Bayesian Information Criterion) is used to detect speaker change. Finally speaker clustering is carried out with BIC, and location and extraction of broadcast is realized based on rules. Satisfactory results from experiments prove the effectiveness of this algorithm.</p>
INDEX TERMS
null
CITATION
Ling Guo, Ying-Chun Shi, Xian-Zhong Zhou, Feng Zhang, "Location and Extraction of Broadcast in News Video Based on QGMM and BIC", CIT, 2005, The Fifth International Conference on Computer and Information Technology CIT 2005, The Fifth International Conference on Computer and Information Technology CIT 2005 2005, pp. 662-667, doi:10.1109/CIT.2005.137
37 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool