The ID R&D VoxCeleb Speaker Recognition Challenge 2023 System Description

The ID R&D VoxCeleb Speaker Recognition Challenge 2023 System Description

This report describes ID R&D team submissions for Track 2 (open) to the VoxCeleb Speaker Recognition Challenge 2023 (VoxSRC-23). Our solution is based on the fusion of deep ResNets and self-supervised learning (SSL) based models trained on a mixture of a VoxCeleb2 dataset and a large version of...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2023-08
Hauptverfasser: Torgashov, Nikita, Makarov, Rostislav, Yakovlev, Ivan, Malov, Pavel, Balykin, Andrei, Okhotnikov, Anton
Format: Artikel
Sprache:eng
Schlagworte:
Datasets
R&D
Research & development
Self-supervised learning
Speech recognition
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This report describes ID R&D team submissions for Track 2 (open) to the VoxCeleb Speaker Recognition Challenge 2023 (VoxSRC-23). Our solution is based on the fusion of deep ResNets and self-supervised learning (SSL) based models trained on a mixture of a VoxCeleb2 dataset and a large version of a VoxTube dataset. The final submission to the Track 2 achieved the first place on the VoxSRC-23 public leaderboard with a minDCF(0.05) of 0.0762 and EER of 1.30%.
ISSN:2331-8422