Domain-Dependent Speaker Diarization for the Third DIHARD Challenge - Department of Natural Language Processing & Knowledge Discovery Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Domain-Dependent Speaker Diarization for the Third DIHARD Challenge

Résumé

This report presents the system developed by the ABSP Laboratory team for the third DIHARD speech diarization challenge. Our main contribution in this work is to develop a simple and efficient solution for acoustic domain dependent speech diarization. We explore speaker embeddings for acoustic domain identification (ADI) task. Our study reveals that i-vector based method achieves considerably better performance than xvector based approach in the third DIHARD challenge dataset. Next, we integrate the ADI module with the diarization framework. The performance substantially improved over that of the baseline when we optimized the thresholds for agglomerative hierarchical clustering and the parameters for dimensionality reduction during scoring for individual acoustic domains. We achieved a relative improvement of 9.63% and 10.64% in DER for core and full conditions, respectively, for Track 1 of the DIHARD III evaluation set.
Fichier principal
Vignette du fichier
DIHARD_3_Workshop.pdf (110.79 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03117843 , version 1 (21-01-2021)

Identifiants

  • HAL Id : hal-03117843 , version 1

Citer

Kishore A. Kumar, Shefali Waldekar, Goutam Saha, Md Sahidullah. Domain-Dependent Speaker Diarization for the Third DIHARD Challenge. DIHARD 2021 - 3rd Speech Diarization Challenge Workshop, Jan 2021, Virtual, France. ⟨hal-03117843⟩
131 Consultations
124 Téléchargements

Partager

Gmail Facebook X LinkedIn More