Strategies to Improve a Speaker Diarisation Tool

David Tavarez, Eva Navas, Daniel Erro, Ibon Saratxaga


Abstract
This paper describes the different strategies used to improve the results obtained by an off-line speaker diarisation tool with the Albayzin 2010 diarisation database. The errors made by the system have been analyzed and different strategies have been proposed to reduce each kind of error. Very short segments incorrectly labelled and different appearances of one speaker labelled with different identifiers are the most common errors. A post-processing module that refines the segmentation by retraining the GMM models of the speakers involved has been built to cope with these errors. This post-processing module has been tuned with the training dataset and improves the result of the diarisation system by 16.4% in the test dataset.
Anthology ID:
L12-1413
Volume:
Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12)
Month:
May
Year:
2012
Address:
Istanbul, Turkey
Editors:
Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Mehmet Uğur Doğan, Bente Maegaard, Joseph Mariani, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
4117–4121
Language:
URL:
http://www.lrec-conf.org/proceedings/lrec2012/pdf/711_Paper.pdf
DOI:
Bibkey:
Cite (ACL):
David Tavarez, Eva Navas, Daniel Erro, and Ibon Saratxaga. 2012. Strategies to Improve a Speaker Diarisation Tool. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 4117–4121, Istanbul, Turkey. European Language Resources Association (ELRA).
Cite (Informal):
Strategies to Improve a Speaker Diarisation Tool (Tavarez et al., LREC 2012)
Copy Citation:
PDF:
http://www.lrec-conf.org/proceedings/lrec2012/pdf/711_Paper.pdf