System output combination for improved speaker diarization - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

System output combination for improved speaker diarization

Résumé

System combination or fusion is a popular, successful and sometimes straightforward means of improving performance in many fields of statistical pattern classification, including speech and speaker recognition. Whilst there is significant work in the literature which aims to improve speaker diarization performance by combining multiple feature streams, there is little work which aims to combine the outputs of multiple systems. This paper reports our first attempts to combine the outputs of two state-of-the-art speaker diarization systems, namely ICSI's bottom-up and LIA-EURECOM's top-down systems. We show that a cluster matching procedure reliably identifies corresponding speaker clusters in the two system outputs and that, when they are used in a new realignment and resegmentation stage, the combination leads to relative improvements of 13% and 7% DER on independent development and evaluation sets.
Fichier principal
Vignette du fichier
interspeech2010_paper2_1_.pdf (102.04 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-00601409 , version 1 (17-06-2011)

Identifiants

  • HAL Id : hal-00601409 , version 1

Citer

Simon Bozonnet, Nicholas Evans, Xavier Anguera, Oriol Vinyals, Gerald Friedland, et al.. System output combination for improved speaker diarization. Interspeech 2010, September 26-30, Makuhari, Japan, Sep 2010, Makuhari, Tokyo, Japan. Interspeech 2010, September 26-30, Makuhari, Japan. ⟨hal-00601409⟩
83 Consultations
63 Téléchargements

Partager

Gmail Facebook X LinkedIn More