Pré-Publication, Document De Travail Année : 2026

Assessing the Impact of Speaker Identity in Speech Spoofing Detection

Anh-Tuan Dao
  • Fonction : Auteur
Driss Matrouf
Nicholas Evans
  • Fonction : Auteur

Résumé

Spoofing detection systems are typically trained using diverse recordings from multiple speakers, often assuming that the resulting embeddings are independent of speaker identity. However, this assumption remains unverified. In this paper, we investigate the impact of speaker information on spoofing detection systems. We propose two approaches within our Speaker-Invariant Multi-Task framework, one that models speaker identity within the embeddings and another that removes it. SInMT integrates multi-task learning for joint speaker recognition and spoofing detection, incorporating a gradient reversal layer. Evaluated using four datasets, our speaker-invariant model reduces the average equal error rate by 17% compared to the baseline, with up to 48% reduction for the most challenging attacks (e.g., A11).

Fichier principal
Vignette du fichier
Icassp2026_SSD_IVspk_ATD_camera_ready (1).pdf (809.64 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05591353 , version 1 (21-04-2026)

Licence

Identifiants

Citer

Anh-Tuan Dao, Driss Matrouf, Nicholas Evans. Assessing the Impact of Speaker Identity in Speech Spoofing Detection. 2026. ⟨hal-05591353⟩
12 Consultations
4 Téléchargements

Altmetric

Partager

  • More