CONF
vinciarelli:acmmmvincia:2007/IDIAP
Broadcast News Story Segmentation Using Social Network Analysis and Hidden Markov Models
Vinciarelli, Alessandro
Favre, Sarah
EXTERNAL
https://publications.idiap.ch/attachments/papers/2007/vinciarelli-acmmmvincia-2007.pdf
PUBLIC
https://publications.idiap.ch/index.php/publications/showcite/vinciarelli:rr07-30
Related documents
ACM International Conference on Multimedia
2007
261-264
IDIAP-RR 07-30
This paper presents an approach for the segmentation of broadcast news into stories. The main novelty of this work is that the segmentation process does not take into account the content of the news, i.e. what is said, but rather the structure of the social relationships between the persons that in the news are involved. The main rationale behind such an approach is that people interacting with each other are likely to talk about the same topics, thus social relationships are likely to be correlated to stories. The approach is based on Social Network Analysis (for the representation of social relationships) and Hidden Markov Models (for the mapping of social relationships into stories). The experiments are performed over 26 hours of radio news and the results show that a fully automatic process achieves a purity higher than 0.75.
REPORT
vinciarelli:rr07-30/IDIAP
Broadcast News Story Segmentation Using Social Network Analysis and Hidden Markov Models
Vinciarelli, Alessandro
Favre, Sarah
EXTERNAL
https://publications.idiap.ch/attachments/reports/2007/vinciarelli-idiap-rr-07-30.pdf
PUBLIC
Idiap-RR-30-2007
2007
IDIAP
This paper presents an approach for the segmentation of broadcast news into stories. The main novelty of this work is that the segmentation process does not take into account the content of the news, i.e. what is said, but rather the structure of the social relationships between the persons that in the news are involved. The main rationale behind such an approach is that people interacting with each other are likely to talk about the same topics, thus social relationships are likely to be correlated to stories. The approach is based on Social Network Analysis (for the representation of social relationships) and Hidden Markov Models (for the mapping of social relationships into stories). The experiments are performed over 26 hours of radio news and the results show that a fully automatic process achieves a purity higher than 0.75.