mlsanityData to 14 Oct 2026

ChinaTelecom System Description to VoxCeleb Speaker Recognition Challenge 2023

arXiv 2308.08181 ↗First posted 16 Aug 2023cs.SD cs.CL eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

This technical report describes ChinaTelecom system for Track 1 (closed) of the VoxCeleb2023 Speaker Recognition Challenge (VoxSRC 2023). Our system consists of several ResNet variants trained only on VoxCeleb2, which were fused for better performance later. Score calibration was also applied for each variant and the fused system. The final submission achieved minDCF of 0.1066 and EER of 1.980%.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 15 references that are in the map. First posted on arXiv 16 Aug 2023.

Builds on

11 of 15 references.

References · 11

  1. 2018VoxCeleb2: Deep Speaker Recognitioncited by 875
  2. 2019Res2Net: A New Multi-scale Backbone Architecturecited by 470
  3. 2015MUSAN: A Music, Speech, and Noise Corpuscited by 425
  4. 2022Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkitcited by 97
  5. 2021SphereFace2: Binary Classification is All You Need for Deep Face Recognitioncited by 42
  6. 2023An Enhanced Res2Net with Local and Global Feature Fusion for Speaker Verificationcited by 42
  7. 2020The IDLAB VoxSRC-20 Submission: Large Margin Fine-Tuning and Quality-Aware Score Calibration in DNN Based Speaker Verificationcited by 23
  8. 2021Simple Attention Module based Speaker Verification with Iterative noisy label detectioncited by 14
  9. 2021Multi-query multi-head attention pooling and Inter-topK penalty for speaker verificationcited by 9
  10. 2022SJTU-AISPEECH System for VoxCeleb Speaker Recognition Challenge 2022cited by 6
  11. 2023Exploring Binary Classification Loss For Speaker Verificationcited by 6

Built on by

Not cited yet.