mlsanityData to 7 Oct 2026

Utterance-level Aggregation For Speaker Recognition In The Wild

arXiv 1902.10107 ↗First posted 26 Feb 2019eess.AS cs.LG cs.MMcited by 49

Not on the map. Why?

Abstract (arXiv)

The objective of this paper is speaker recognition "in the wild"-where utterances may be of variable length and also contain irrelevant signals. Crucial elements in the design of deep networks for this task are the type of trunk (frame level) network, and the method of temporal aggregation. We propose a powerful speaker recognition deep network, using a "thin-ResNet" trunk architecture, and a dictionary-based NetVLAD or GhostVLAD layer to aggregate features across time, that can be trained end-to-end. We show that our network achieves state of the art performance by a significant margin on the VoxCeleb1 test set for speaker recognition, whilst requiring fewer parameters than previous methods. We also investigate the effect of utterance length on performance, and conclude that for "in the wild" data, a longer length is beneficial.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 11; 2023: 9; 2024: 10; 2025: 3; 2026: 4.

49 papers.

Sort:

By area:

  1. 2023AutoAD II: The Sequel -- Who, When, and What in Movie Audio Descriptioncited by 48
  2. 2021Fusion and Orthogonal Projection for Improved Face-Voice Associationcited by 29
  3. 2021Face, Body, Voice: Video Person-Clustering with Multiple Modalitiescited by 24
  4. 2021A Multi-View Approach To Audio-Visual Speaker Verificationcited by 23
  5. 2021Look Who's Talking: Active Speaker Detection in the Wildcited by 21
  6. 2023CommonAccent: Exploring Large Acoustic Pretrained Models for Accent Classification Based on Common Voicecited by 19
  7. 2021Attack on practical speaker verification system using universal adversarial perturbationscited by 17
  8. 2022Winning solutions and post-challenge analyses of the ChaLearn AutoDL challenge 2019cited by 16
  9. 2023Single-branch Network for Multimodal Trainingcited by 13
  10. 2023Disentangling Voice and Content with Self-Supervision for Speaker Recognitioncited by 10
  11. 2024The VoxCeleb Speaker Recognition Challenge: A Retrospectivecited by 9
  12. 2025PAEFF: Precise Alignment and Enhanced Gated Feature Fusion for Face-Voice Associationcited by 9
37 more
  1. 2021Multi-task Voice Activated Framework using Self-supervised Learningcited by 8
  2. 2021Multi-View Self-Attention Based Transformer for Speaker Recognitioncited by 8
  3. 2025Face-voice Association in Multilingual Environments (FAME) 2026 Challenge Evaluation Plancited by 6
  4. 2022Dictionary Attacks on Speaker Verificationcited by 5
  5. 2025Linking Faces and Voices Across Languages: Insights from the FAME 2026 Challengecited by 5
  6. 2022OS-MSL: One Stage Multimodal Sequential Link Framework for Scene Segmentation and Classificationcited by 4
  7. 2024Face-voice Association in Multilingual Environments (FAME) Challenge 2024 Evaluation Plancited by 4
  8. 2024Modality Invariant Multimodal Learning to Handle Missing Modalities: A Single-Branch Approachcited by 4
  9. 2021EfficientTDNN: Efficient Architecture Search for Speaker Recognitioncited by 3
  10. 2021Fusion of Embeddings Networks for Robust Combination of Text Dependent and Independent Speaker Recognitioncited by 3
  11. 2022Learning Branched Fusion and Orthogonal Projection for Face-Voice Associationcited by 3
  12. 2023Audio Representation Learning by Distilling Video as Privileged Informationcited by 3
  13. 2023Experimenting with Additive Margins for Contrastive Self-Supervised Speaker Verificationcited by 3
  14. 2024Additive Margin in Contrastive Self-Supervised Frameworks to Learn Discriminative Speaker Representationscited by 3
  15. 2021SpeechNAS: Towards Better Trade-off between Latency and Accuracy for Large-Scale Speaker Verificationcited by 2
  16. 2022Audio-video fusion strategies for active speaker detection in meetingscited by 2
  17. 2022Deep Architectures for Content Moderation and Movie Content Ratingcited by 2
  18. 2023Zero-shot personalized lip-to-speech synthesis with face image based voice controlcited by 2
  19. 2023Relation-Aware Distribution Representation Network for Person Clustering with Multiple Modalitiescited by 2
  20. 2024Robust Channel Learning for Large-Scale Radio Speaker Verificationcited by 2
  21. 2024Chameleon: Images Are What You Need For Multimodal Learning Robust To Missing Modalitiescited by 2
  22. 2021An Attribute-Aligned Strategy for Learning Speech Representationcited by 1
  23. 2021Inclusive Speaker Verification with Adaptive thresholdingcited by 1
  24. 2022Self-supervised Speaker Recognition Training Using Human-Machine Dialoguescited by 1
  25. 2022Tackling Spoofing-Aware Speaker Verification with Multi-Model Fusioncited by 1
  26. 2022Defend Data Poisoning Attacks on Voice Authenticationcited by 1
  27. 2024Exploring Robust Face-Voice Matching in Multilingual Environmentscited by 1
  28. 2026Face-Voice Association with Inductive Bias for Maximum Class Separationcited by 1
  29. 2026Beyond Short Segments : Expanding Speaker Embeddings with Vector Archivescited by 1
  30. 2022Learnable Nonlinear Compression for Robust Speaker Verificationcited by 0
  31. 2022Dynamic Kernels and Channel Attention for Low Resource Speaker Verificationcited by 0
  32. 2023Deep Neural Networks for Automatic Speaker Recognition Do Not Learn Supra-Segmental Temporal Featurescited by 0
  33. 2024Who is Authentic Speakercited by 0
  34. 2024EnvId: A Metric Learning Approach for Forensic Few-Shot Identification of Unseen Environmentscited by 0
  35. 2024Memory-Efficient Training for Text-Dependent SV with Independent Pre-trained Modelscited by 0
  36. 2026Face and Voice Cross-modal Association with Learning Convex Feature Embeddingcited by 0
  37. 2026Face-voice Association across LAnguages and Gender (FLAG) 2027 Challenge Evaluation Plancited by 0