mlsanityData to 7 Oct 2026

Dynamic Recognition of Speakers for Consent Management by Contrastive Embedding Replay

arXiv 2205.08459 ↗First posted 17 May 2022cs.SD cs.LG eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

Voice assistants overhear conversations and a consent management mechanism is required. Consent management can be implemented using speaker recognition. Users that do not give consent enrol their voice and all their further recordings are discarded. Building speaker recognition-based consent management is challenging as dynamic registration, removal, and re-registration of speakers must be efficiently handled. This work proposes a consent management system addressing the aforementioned challenges. A contrastive based training is applied to learn the underlying speaker equivariance inductive bias. The contrastive features for buckets of speakers are trained a few steps into each iteration and act as replay buffers. These features are progressively selected using a multi-strided random sampler for classification. Moreover, new methods for dynamic registration using a portion of old utterances, removal, and re-registration of speakers are proposed. The results verify memory efficiency and dynamic capabilities of the proposed methods and outperform the existing approach from the literature.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 40 references that are in the map. First posted on arXiv 17 May 2022.

Builds on

19 of 40 references.

References · 19

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  3. 2020Supervised Contrastive Learningcited by 2,803
  4. 2016Deep Learning with Differential Privacycited by 2,682
  5. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  6. 2016Matching Networks for One Shot Learningcited by 2,246
  7. 2018Group Normalizationcited by 1,514
  8. 2017VoxCeleb: a large-scale speaker identification datasetcited by 714
  9. 2017Generalized End-to-End Loss for Speaker Verificationcited by 290
  10. 2019Continual learning with hypernetworkscited by 267
  11. 2018Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergencescited by 237
  12. 2021Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learningcited by 140
7 more
  1. 2019A continual learning survey: Defying forgetting in classification taskscited by 118
  2. 2020Self-supervised Text-independent Speaker Verification using Prototypical Momentum Contrastive Learningcited by 29
  3. 2021Self-Supervised Speaker Verification with Simple Siamese Network and Self-Supervised Regularizationcited by 14
  4. 2020Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairscited by 8
  5. 2020Modularizing Deep Learning via Pairwise Learning With Kernelscited by 7
  6. 2019A New Framework for Distance and Kernel-based Metrics in High Dimensionscited by 6
  7. 2022Baselines and Protocols for Household Speaker Recognitioncited by 3

Built on by

Not cited yet.