The LIA-Eurecom RT'09 speaker diarization system : enhancements in speaker modelling and cluster purification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

The LIA-Eurecom RT'09 speaker diarization system : enhancements in speaker modelling and cluster purification

Simon Bozonnet
  • Fonction : Auteur
  • PersonId : 903988
Corinne Fredouille

Résumé

There are two approaches to speaker diarization. They are bottom-up and top-down. Our work on top-down systems show that they can deliver competitive results compared to bottom-up systems and that they are extremely computationally efficient, but also that they are particularly prone to poor model initialisation and cluster impurities. In this paper we present enhancements to our state-of-the-art, top-down approach to speaker diarization that deliver improved stability across three different datasets composed of conference meetings from five standard NIST RT evaluations. We report an improved approach to speaker modelling which, despite having greater chances for cluster impurities, delivers a 35% relative improvement in DER for the MDM condition. We also describe new work to incorporate cluster purification into a top-down sys- tem which delivers relative improvements of 44% over the baseline system without compromising computational efficiency.
Fichier non déposé

Dates et versions

hal-00601383 , version 1 (17-06-2011)

Identifiants

  • HAL Id : hal-00601383 , version 1

Citer

Simon Bozonnet, Evans Nicholas, Corinne Fredouille. The LIA-Eurecom RT'09 speaker diarization system : enhancements in speaker modelling and cluster purification. ICASSP 2010, 35th International Conference on Acoustics, Speech, and Signal Processing, March 14-19, 2010, Dallas, Texas, USA, Mar 2010, Dallas, United States. pp.ICASSP 2010. ⟨hal-00601383⟩
89 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More