Selecting Representative Speakers for a Speech Database on the Basis of Heterogeneous Similarity Criteria

  • Authors:

  • Sacha Krstulović;Frédéric Bimbot;Olivier Boëffard;Delphine Charlet;Dominique Fohr;Odile Mella

  • Affiliations:

  • IRISA/METISS, Campus de Beaulieu, 35 042 Rennes Cedex, France;IRISA/METISS, Campus de Beaulieu, 35 042 Rennes Cedex, France;IRISA/CORDIAL, 6 r. Kerampont, BP 80518, 22 305 Lannion Cedex, France;France Télécom R&D, 2 ave. Marzin, 22 307 Lannion, France;LORIA, Campus Universitaire, BP239, 54 506 Vandoeuvre Cedex, France;LORIA, Campus Universitaire, BP239, 54 506 Vandoeuvre Cedex, France

  • Venue:
  • Speaker Classification II
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

In the context of the NeologosFrench speech database creation project, a general methodology was defined for the selection of representative speaker recordings. The selection aims at providing a good coverage in terms of speaker variability while limiting the number of recorded speakers. This is intended to make the resulting database both more adapted to the development of recently proposed multi-model methods and less expensive to collect.The presented methodology proposes a selection process based on the optimization of a quality criterion defined in a variety of speaker similarity modeling frameworks. The selection can be achieved with respect to a unique similarity criterion, using classical clustering methods such as Hierarchical or K-Medians clustering, or it can combine several speaker similarity criteria, thanks to a newly developed clustering method called Focal Speakers Selection.In this framework, four different speaker similarity criteria are tested, and three different speaker clustering algorithms are compared. Results pertaining to the collection of the Neologosdatabase are also discussed.