Clustering-based hard negative sampling for supervised contrastive speaker verification

• URL: http://arxiv.org/abs/2507.17540v1
• Date: Wed, 23 Jul 2025 14:19:33 GMT
• Title: Clustering-based hard negative sampling for supervised contrastive speaker verification
• Authors: Piotr Masztalski, Michał Romaniuk, Jakub Żak, Mateusz Matuszewski, Konrad Kowalczyk,
• Abstract summary: CHNS is a clustering-based hard negative sampling method dedicated for supervised contrastive speaker representation learning.<n>Our approach clusters embeddings of similar speakers, and adjusts batch composition to obtain an optimal ratio of hard and easy negatives.<n> Experimental evaluation shows that CHNS outperforms a baseline supervised contrastive approach with and without loss-based hard negative sampling.
• Score: 14.401580929768127
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In speaker verification, contrastive learning is gaining popularity as an alternative to the traditionally used classification-based approaches. Contrastive methods can benefit from an effective use of hard negative pairs, which are different-class samples particularly challenging for a verification model due to their similarity. In this paper, we propose CHNS - a clustering-based hard negative sampling method, dedicated for supervised contrastive speaker representation learning. Our approach clusters embeddings of similar speakers, and adjusts batch composition to obtain an optimal ratio of hard and easy negatives during contrastive loss calculation. Experimental evaluation shows that CHNS outperforms a baseline supervised contrastive approach with and without loss-based hard negative sampling, as well as a state-of-the-art classification-based approach to speaker verification by as much as 18 % relative EER and minDCF on the VoxCeleb dataset using two lightweight model architectures.

Related papers

• Large Language Model Enhanced Hard Sample Identification for Denoising Recommendation [4.297249011611168]
  Implicit feedback is often used to build recommender systems. Previous studies have attempted to alleviate this by identifying noisy samples based on their diverged patterns. We propose a Large Language Model Enhanced Hard Sample Denoising framework.
  arXiv  Detail & Related papers  (2024-09-16T14:57:09Z)
• CKD: Contrastive Knowledge Distillation from A Sample-wise Perspective [48.99488315273868]
  We propose a contrastive knowledge distillation framework that achieves sample-wise logit alignment while preserving semantic consistency.<n>Our approach transfers "dark knowledge" through teacher-student contrastive alignment at the sample level.<n>We conduct comprehensive experiments across three benchmark datasets, including the CIFAR-100, ImageNet-1K, and MS COCO datasets.
  arXiv  Detail & Related papers  (2024-04-22T11:52:40Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype Contrast [34.58856143210749]
  We present an approach to learn voice-face representations from the talking face videos, without any identity labels. Previous works employ cross-modal instance discrimination tasks to establish the correlation of voice and face. We propose the cross-modal prototype contrastive learning (CMPC), which takes advantage of contrastive methods and resists adverse effects of false negatives and deviate positives.
  arXiv  Detail & Related papers  (2022-04-28T07:28:56Z)
• Adversarial Contrastive Learning by Permuting Cluster Assignments [0.8862707047517914]
  We propose SwARo, an adversarial contrastive framework that incorporates cluster assignment permutations to generate representative adversarial samples. We evaluate SwARo on multiple benchmark datasets and against various white-box and black-box attacks, obtaining consistent improvements over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-04-21T17:49:52Z)
• Visualizing Classifier Adjacency Relations: A Case Study in Speaker Verification and Voice Anti-Spoofing [72.4445825335561]
  We propose a simple method to derive 2D representation from detection scores produced by an arbitrary set of binary classifiers. Based upon rank correlations, our method facilitates a visual comparison of classifiers with arbitrary scores. While the approach is fully versatile and can be applied to any detection task, we demonstrate the method using scores produced by automatic speaker verification and voice anti-spoofing systems.
  arXiv  Detail & Related papers  (2021-06-11T13:03:33Z)
• Solving Inefficiency of Self-supervised Representation Learning [87.30876679780532]
  Existing contrastive learning methods suffer from very low learning efficiency. Under-clustering and over-clustering problems are major obstacles to learning efficiency. We propose a novel self-supervised learning framework using a median triplet loss.
  arXiv  Detail & Related papers  (2021-04-18T07:47:10Z)
• Jo-SRC: A Contrastive Approach for Combating Noisy Labels [58.867237220886885]
  We propose a noise-robust approach named Jo-SRC (Joint Sample Selection and Model Regularization based on Consistency) Specifically, we train the network in a contrastive learning manner. Predictions from two different views of each sample are used to estimate its "likelihood" of being clean or out-of-distribution.
  arXiv  Detail & Related papers  (2021-03-24T07:26:07Z)
• Doubly Contrastive Deep Clustering [135.7001508427597]
  We present a novel Doubly Contrastive Deep Clustering (DCDC) framework, which constructs contrastive loss over both sample and class views. Specifically, for the sample view, we set the class distribution of the original sample and its augmented version as positive sample pairs. For the class view, we build the positive and negative pairs from the sample distribution of the class. In this way, two contrastive losses successfully constrain the clustering results of mini-batch samples in both sample and class level.
  arXiv  Detail & Related papers  (2021-03-09T15:15:32Z)
• Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning [94.35586521144117]
  We investigate whether applying contrastive learning to fine-tuning would bring further benefits. We propose Contrast-regularized tuning (Core-tuning), a novel approach for fine-tuning contrastive self-supervised visual models.
  arXiv  Detail & Related papers  (2021-02-12T16:31:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.