Title
Speaker linking in large data sets
Author
van Leeuwen, D.A.
Publication year
2019
Abstract
This paper investigates the task of linking speakers across multiple recordings, which can be accomplished by speaker clustering. Various aspects are considered, such as computational complexity, on/offline approaches, and evaluation measures but also speaker recognition approaches. It has not been the aim of this study to optimize clustering performance, but as an experimental exercise, we perform speaker linking on all '1conv-4w' conversation sides of the NIST-2006 evaluation data set. This set contains 704 speakers in 3835 conversation sides. Using both on-line and off-line algorithms, equal-purity figures of about 86 % are obtained. © Odyssey 2010: Speaker and Language Recognition Workshop. All rights reserved.
Subject
Data set
Evaluation measures
Large datasets
Multiple recordings
Off-line algorithm
Speaker clustering
Speaker recognition
Speech recognition
To reference this document use:
http://resolver.tudelft.nl/uuid:b524a8a2-74ce-4da3-9011-4610838947b8
TNO identifier
869623
Publisher
International Speech Communication Association
Source
Odyssey 2010: Speaker and Language Recognition Workshop, Speaker and Language Recognition Workshop, Odyssey 2010, 28 June 2010 through 1 July 2010, 202-208
Document type
conference paper