mlsanityData to 14 Oct 2026

SSPS: Self-Supervised Positive Sampling for Robust Self-Supervised Speaker Verification

arXiv 2505.14561 ↗First posted 20 May 2025eess.AS cs.AI cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Self-Supervised Learning (SSL) has led to considerable progress in Speaker Verification (SV). The standard framework uses same-utterance positive sampling and data-augmentation to generate anchor-positive pairs of the same speaker. This is a major limitation, as this strategy primarily encodes channel information from the recording condition, shared by the anchor and positive. We propose a new positive sampling technique to address this bottleneck: Self-Supervised Positive Sampling (SSPS). For a given anchor, SSPS aims to find an appropriate positive, i.e., of the same speaker identity but a different recording condition, in the latent space using clustering assignments and a memory queue of positive embeddings. SSPS improves SV performance for both SimCLR and DINO, reaching 2.57% and 2.53% EER, outperforming SOTA SSL methods on VoxCeleb1-O. In particular, SimCLR-SSPS achieves a 58% EER reduction by lowering intra-speaker variance, providing comparable performance to DINO-SSPS.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 24 of its 32 references that are in the map. First posted on arXiv 20 May 2025.

Builds on

24 of 32 references.

References · 24

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  4. 2018VoxCeleb2: Deep Speaker Recognitioncited by 875
  5. 2017VoxCeleb: a large-scale speaker identification datasetcited by 732
  6. 2020ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verificationcited by 628
  7. 2015MUSAN: A Music, Speech, and Noise Corpuscited by 425
  8. 2021With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representationscited by 326
  9. 2020In defence of metric learning for speaker recognitioncited by 126
  10. 2020Self-supervised Text-independent Speaker Verification using Prototypical Momentum Contrastive Learningcited by 33
  11. 2020Augmentation adversarial training for self-supervised speaker recognitioncited by 24
  12. 2021Self-Supervised Speaker Verification with Simple Siamese Network and Self-Supervised Regularizationcited by 17
12 more
  1. 2022Pushing the limits of self-supervised speaker verification using regularized distillation frameworkcited by 15
  2. 2022C3-DINO: Joint Contrastive and Non-contrastive Self-Supervised Learning for Speaker Verificationcited by 12
  3. 2023Self-Supervised Learning with Cluster-Aware-DINO for High-Performance Robust Speaker Verificationcited by 11
  4. 2022Label-Efficient Self-Supervised Speaker Verification With Information Maximization and Contrastive Learningcited by 10
  5. 2022Non-Contrastive Self-supervised Learning for Utterance-Level Information Extraction from Speechcited by 10
  6. 2022Curriculum learning for self-supervised speaker verificationcited by 7
  7. 2022Self-Supervised Training of Speaker Encoder with Multi-Modal Diverse Positive Pairscited by 7
  8. 2022Self-Supervised Speaker Verification Using Dynamic Loss-Gate and Label Correctioncited by 6
  9. 2020Unsupervised Representation Learning for Speaker Recognition via Contrastive Equilibrium Learningcited by 4
  10. 2024GPS-SSL: Guided Positive Sampling to Inject Prior Into Self-Supervised Learningcited by 3
  11. 2024Additive Margin in Contrastive Self-Supervised Frameworks to Learn Discriminative Speaker Representationscited by 3
  12. 2025Self-Supervised Frameworks for Speaker Verification via Bootstrapped Positive Samplingcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Self-Supervised Learning for Speaker Recognition: A study and reviewcited by 0