Skip to content

Detail of publication

Citation

Marie Kunešová and Vlasta Radová : Ideas for Clustering of Similar Models of a Speaker in an Online Speaker Diarization System . Text, Speech and Dialogue, Proceedings of the 18th International Conference TSD 2015, Lecture Notes in Computer Science, vol. 9302, p. 225-233, Springer, 2015.

Abstract

During online speaker diarization, a situation may occur where a single speaker is being represented by several different models. Such situation leads to worsened diarization results, because the diarization system considers every change of a model to be a change of speakers. In the article we describe a method for detecting this situation and propose several ways of solving it. Experiments show that the most suitable option is treating multiple GMMs as belonging to a single speaker, i.e. updating all of them with the same data every time one of them is assigned a new segment. In that case, there was a relative improvement in Diarization Error Rate of 30.69% in comparison with the baseline system.

Detail of publication

Title: Ideas for Clustering of Similar Models of a Speaker in an Online Speaker Diarization System
Author: Marie Kunešová ; Vlasta Radová
Language: English
Date of publication: 1 Sep 2015
Year: 2015
Type of publication: Papers in proceedings of reviewed conferences
Title of journal or book: Text, Speech and Dialogue, Proceedings of the 18th International Conference TSD 2015
Series: Lecture Notes in Computer Science
Číslo vydání: 9302
Page: 225 - 233
DOI: 10.1007/978-3-319-24033-6_26
ISBN: 978-3-319-24032-9
Publisher: Springer
/ 2017-09-21 14:11:59 /

Keywords

speaker clustering, speaker diarization, speaker segmentation

BibTeX

@INPROCEEDINGS{MarieKunesova_2015_IdeasforClustering,
 author = {Marie Kune\v{s}ov\'{a} and Vlasta Radov\'{a}},
 title = {Ideas for Clustering of Similar Models of a Speaker in an Online Speaker Diarization System },
 year = {2015},
 publisher = {Springer},
 journal = {Text, Speech and Dialogue, Proceedings of the 18th International Conference TSD 2015},
 volume = {9302},
 pages = {225-233},
 series = {Lecture Notes in Computer Science},
 ISBN = {978-3-319-24032-9},
 doi = {10.1007/978-3-319-24033-6_26},
 url = {http://www.kky.zcu.cz/en/publications/MarieKunesova_2015_IdeasforClustering},
}