mlsanityData to 7 Oct 2026

Attentive Statistics Pooling for Deep Speaker Embedding

arXiv 1803.10963 ↗First posted 29 Mar 2018eess.AS cs.SDcited by 108

Not on the map. Why?

Abstract (arXiv)

This paper proposes attentive statistics pooling for deep speaker embedding in text-independent speaker verification. In conventional speaker embedding, frame-level features are averaged over all the frames of a single utterance to form an utterance-level feature. Our method utilizes an attention mechanism to give different weights to different frames and generates not only weighted means but also weighted standard deviations. In this way, it can capture long-term variations in speaker characteristics more effectively. An evaluation on the NIST SRE 2012 and the VoxCeleb data sets shows that it reduces equal error rates (EERs) from the conventional method by 7.5% and 8.1%, respectively.

Key facts. Cited by 108 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 17; 2023: 17; 2024: 22; 2025: 15; 2026: 20.

108 papers.

Sort:

By area:

  1. 2021Attention, please! A survey of Neural Attention Models in Deep Learningcited by 50
  2. 2024A Large-Scale Evaluation of Speech Foundation Modelscited by 38
  3. 2024ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf modelscited by 22
  4. 2023CommonAccent: Exploring Large Acoustic Pretrained Models for Accent Classification Based on Common Voicecited by 19
  5. 2025Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-spoofingcited by 17
  6. 2021Self-Supervised Speaker Verification with Simple Siamese Network and Self-Supervised Regularizationcited by 14
  7. 2022Partially Fake Audio Detection by Self-attention-based Fake Span Discoverycited by 14
  8. 2021Voting for the right answer: Adversarial defense for speaker verificationcited by 12
  9. 2022Deepfake audio detection by speaker verificationcited by 11
  10. 2023Disentangling Voice and Content with Self-Supervision for Speaker Recognitioncited by 10
  11. 2022Improving the Training Recipe for a Robust Conformer-based Hybrid Modelcited by 9
  12. 2024Boosting Graph Pooling with Persistent Homologycited by 9
38 more
  1. 2024Enhancing Partially Spoofed Audio Localization with Boundary-aware Attention Mechanismcited by 9
  2. 2024The VoxCeleb Speaker Recognition Challenge: A Retrospectivecited by 9
  3. 2021Multi-task Voice Activated Framework using Self-supervised Learningcited by 8
  4. 2021Multi-View Self-Attention Based Transformer for Speaker Recognitioncited by 8
  5. 2023VoxSRC 2022: The Fourth VoxCeleb Speaker Recognition Challengecited by 8
  6. 2021STC speaker recognition systems for the NIST SRE 2021cited by 6
  7. 2022Combining Automatic Speaker Verification and Prosody Analysis for Synthetic Speech Detectioncited by 6
  8. 2023CoverHunter: Cover Song Identification with Refined Attention and Alignmentscited by 6
  9. 2023Towards Effective and Compact Contextual Representation for Conformer Transducer Speech Recognition Systemscited by 6
  10. 2024USAT: A Universal Speaker-Adaptive Text-to-Speech Approachcited by 6
  11. 2022ECAPA-TDNN for Multi-speaker Text-to-speech Synthesiscited by 5
  12. 2022Multi-Frequency Information Enhanced Channel Attention Module for Speaker Representation Learningcited by 5
  13. 2023Generalizable Zero-Shot Speaker Adaptive Speech Synthesis with Disentangled Representationscited by 5
  14. 2024Exploring Pathological Speech Quality Assessment with ASR-Powered Wav2Vec2 in Data-Scarce Contextcited by 5
  15. 2021Serialized Multi-Layer Multi-Head Attention for Neural Speaker Embeddingcited by 4
  16. 2021SVSNet: An End-to-end Speaker Voice Similarity Assessment Modelcited by 4
  17. 2022Large-scale learning of generalised representations for speaker recognitioncited by 4
  18. 2023Audio-Visual Speaker Verification via Joint Cross-Attentioncited by 4
  19. 2024Adapting WavLM for Speech Emotion Recognitioncited by 4
  20. 2025Privacy-Preserving Biometric Verification with Handwritten Random Digit Stringcited by 4
  21. 2022DT-SV: A Transformer-based Time-domain Approach for Speaker Verificationcited by 3
  22. 2023Improving Transformer-based Networks With Locality For Automatic Speaker Verificationcited by 3
  23. 2023Cross-modal Audio-visual Co-learning for Text-independent Speaker Verificationcited by 3
  24. 2024DIFFRENT: A Diffusion Model for Recording Environment Transfer of Speechcited by 3
  25. 2024Audio-Visual Person Verification based on Recursive Fusion of Joint Cross-Attentioncited by 3
  26. 2024Dynamic Cross Attention for Audio-Visual Person Verificationcited by 3
  27. 2024PDAF: A Phonetic Debiasing Attention Framework For Speaker Verificationcited by 3
  28. 2021The NPU System for the 2020 Personalized Voice Trigger Challengecited by 2
  29. 2021Phoneme-aware and Channel-wise Attentive Learning for Text DependentSpeaker Verificationcited by 2
  30. 2021MACCIF-TDNN: Multi aspect aggregation of channel and context interdependence features in TDNN-based speaker verificationcited by 2
  31. 2021Optimized Power Normalized Cepstral Coefficients towards Robust Deep Speaker Verificationcited by 2
  32. 2022Spoofing-Aware Speaker Verification with Unsupervised Domain Adaptationcited by 2
  33. 2022Spoofing-Aware Speaker Verification by Multi-Level Fusioncited by 2
  34. 2022Pretraining Approaches for Spoken Language Recognition: TalTech Submission to the OLR 2021 Challengecited by 2
  35. 2022Learning Audio-Visual embedding for Person Verification in the Wildcited by 2
  36. 2023Automatic Modulation Classification with Deep Neural Networkscited by 2
  37. 2024Layer-aware TDNN: Speaker Recognition Using Multi-Layer Features from Pre-Trained Modelscited by 2
  38. 2024Exploring SSL Discrete Speech Features for Zipformer-based Contextual ASRcited by 2

50 most cited of 108 All 108 (JSON)