DMCA
Speakers role recognition in multiparty audio recordings using Social Network Analysis and duration distribution modeling (2007)
Cached
Download Links
- [www.idiap.ch]
- [www.idiap.ch]
- [www.dcs.gla.ac.uk]
- DBLP
Other Repositories/Bibliography
| Venue: | IEEE Transactions on Multimedia |
| Citations: | 35 - 6 self |
BibTeX
@ARTICLE{Vinciarelli07speakersrole,
author = {Alessandro Vinciarelli},
title = {Speakers role recognition in multiparty audio recordings using Social Network Analysis and duration distribution modeling},
journal = {IEEE Transactions on Multimedia},
year = {2007},
pages = {1215--1226}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract — This paper presents two approaches for speaker role recognition in multiparty audio recordings. The experiments are performed over a corpus of 96 radio bulletins corresponding to roughly 19 hours of material. Each recording involves, on average, eleven speakers playing one among six roles belonging to a predefined set. Both proposed approaches start by segmenting automatically the recordings into single speaker segments, but perform role recognition using different techniques. The first approach is based on Social Network Analysis, the second relies on the intervention duration distribution across different speakers. The two approaches are used separately and combined and the results show that around 85 percent of the recording time can be labeled correctly in terms of role.
Keyphrases
speaker role recognition social network analysis multiparty audio recording duration distribution eleven speaker radio bulletin recording time second relies first approach different speaker perform role recognition single speaker segment intervention duration distribution different technique
