Institution profile

Ecole Pour l'Informatique et les Techniques Avancees

Academic institutioneurope · fr
Official website
Research library23linked papers
Opportunities0open roles
Selected work

Representative Papers

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

May 20, 2025

In self-supervised speaker verification, conventional same-utterance positive sampling causes models to over-rely on channel-specific cues and suffer from high intra-speaker variance. To address this, we propose Self-Supervised Positive Sampling (SSPS), which retrieves cross-condition positive samples—i.e., utterances from the same speaker but different recording conditions—within the latent space. SSPS innovatively integrates K-means clustering assignments with a dynamic memory queue to enable label-free, channel-agnostic positive retrieval, thereby decoupling self-supervised learning from recording-condition dependencies. The method is compatible with both SimCLR and DINO frameworks and is optimized via contrastive learning. On VoxCeleb1-O, DINO-SSPS and SimCLR-SSPS achieve EERs of 2.53% and 2.57%, respectively—substantially outperforming prior state-of-the-art methods. Notably, SimCLR-SSPS yields a 58% relative EER reduction.

1 citationsRead paper

Witnesses Explain Anomalies

Sep 03, 2026

本文提出WAND,一种可解释的无监督表格异常检测方法,通过单位球面上的方向组织计算,直接提供特征归因解释,无需额外查询。

0 citationsRead paper
Recent publications

Latest Papers

Witnesses Explain Anomalies

Sep 03, 2026

本文提出WAND,一种可解释的无监督表格异常检测方法,通过单位球面上的方向组织计算,直接提供特征归因解释,无需额外查询。

0 citationsRead paper