Autoapprentissage pour le regroupement en locuteurs : premières investigations (First investigations on self trained speaker diarization )

Gaël Le Lan, Sylvain Meignier, Delphine Charlet, Anthony Larcher


Abstract
This paper investigates self trained cross-show speaker diarization applied to collections of French TV archives, based on an i-vector/PLDA framework. The parameters used for i-vectors extraction and PLDA scoring are trained in a unsupervised way, using the data of the collection itself. Performances are compared, using combinations of target data and external data for training. The experimental results on two distinct target corpora show that using data from the corpora themselves to perform unsupervised iterative training and domain adaptation of PLDA parameters can improve an existing system, trained on external annotated data. Such results indicate that performing speaker indexation on small collections of unlabeled audio archives should only rely on the availability of a sufficient external corpus, which can be specifically adapted to every target collection. We show that a minimum collection size is required to exclude the use of such an external bootstrap.
Anthology ID:
2016.jeptalnrecital-jep.10
Volume:
Actes de la conférence conjointe JEP-TALN-RECITAL 2016. volume 1 : JEP
Month:
7
Year:
2016
Address:
Paris, France
Editors:
Laurence Danlos, Thierry Hamon
Venue:
JEP/TALN/RECITAL
SIG:
Publisher:
AFCP - ATALA
Note:
Pages:
82–90
Language:
French
URL:
https://aclanthology.org/2016.jeptalnrecital-jep.10
DOI:
Bibkey:
Cite (ACL):
Gaël Le Lan, Sylvain Meignier, Delphine Charlet, and Anthony Larcher. 2016. Autoapprentissage pour le regroupement en locuteurs : premières investigations (First investigations on self trained speaker diarization ). In Actes de la conférence conjointe JEP-TALN-RECITAL 2016. volume 1 : JEP, pages 82–90, Paris, France. AFCP - ATALA.
Cite (Informal):
Autoapprentissage pour le regroupement en locuteurs : premières investigations (First investigations on self trained speaker diarization ) (Le Lan et al., JEP/TALN/RECITAL 2016)
Copy Citation:
PDF:
https://aclanthology.org/2016.jeptalnrecital-jep.10.pdf