An integrated top-down/bottom-up approach to speaker diarization - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

An integrated top-down/bottom-up approach to speaker diarization

Simon Bozonnet
  • Fonction : Auteur
  • PersonId : 903988
Nicholas Evans
  • Fonction : Auteur
  • PersonId : 938450
Corinne Fredouille
Raphaël Troncy

Résumé

Most speaker diarization systems fit into one of two cat- egories: bottom-up or top-down. Bottom-up systems are the most popular but can sometimes suffer from instability from merging and stopping criteria difficulties. Top-down systems deliver competitive results but are particularly prone to poor model initialization which often leads to large variations in performance. This paper presents a new integrated bottom-up/top-down approach to speaker diarization which aims to harness the strengths of each system and thus to improve performance and stability. In contrast to previous work, here the two systems are fused at the heart of the segmentation and clustering stage. Experimental results show improvements in speaker diarization performance for both meeting and TV-show domain data indicating increased intra and inter-domain stability. On the TV-show data in particular, an average relative improvement of 32% DER is obtained.
Fichier principal
Vignette du fichier
interspeech2010_1_.pdf (243.24 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-00601390 , version 1 (17-06-2011)

Identifiants

  • HAL Id : hal-00601390 , version 1

Citer

Simon Bozonnet, Nicholas Evans, Corinne Fredouille, Dong Wang, Raphaël Troncy. An integrated top-down/bottom-up approach to speaker diarization. Interspeech 2010, September 26-30, Makuhari, Japan, Sep 2010, Makuhari, Tokyo, Japan. Interspeech 2010, September 26-30, Makuhari, Japan. ⟨hal-00601390⟩
126 Consultations
92 Téléchargements

Partager

Gmail Facebook X LinkedIn More