Publication at Faculty of Mathematics and Physics |
2012
Abstract
Segmentation into topically coherent segments is one of the crucial points in information retrieval (IR). Suitable segmentation may improve the results of IR system and help users to find relevant passages faster.
Segmentation is especially important in audiovisual recordings, in which the navigation is difficult. We present several methods used for topic segmentation, based on textual, audio and visual information.
The proposition of our approach to topic segmentation based on the fusion of audio and visual data is presented in the article.