mlsanityData to 7 Oct 2026

ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification

arXiv 2005.07143 ↗First posted 14 May 2020eess.AS cs.SDcited by 606

Not on the map. Why?

Cited by 37 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Current speaker verification techniques rely on a neural network to extract speaker representations. The successful x-vector architecture is a Time Delay Neural Network (TDNN) that applies statistics pooling to project variable-length utterances into fixed-length speaker characterizing embeddings. In this paper, we propose multiple enhancements to this architecture based on recent trends in the related fields of face verification and computer vision. Firstly, the initial frame layers can be restructured into 1-dimensional Res2Net modules with impactful skip connections. Similarly to SE-ResNet, we introduce Squeeze-and-Excitation blocks in these modules to explicitly model channel interdependencies. The SE block expands the temporal context of the frame layer by rescaling the channels according to global properties of the recording. Secondly, neural networks are known to learn hierarchical features, with each layer operating on a different level of complexity. To leverage this complementary information, we aggregate and propagate features of different hierarchical levels. Finally, we improve the statistics pooling module with channel-dependent frame attention. This enables the network to focus on different subsets of frames during each of the channel's statistics estimation. The proposed ECAPA-TDNN architecture significantly outperforms state-of-the-art TDNN based systems on the VoxCeleb test sets and the 2019 VoxCeleb Speaker Recognition Challenge.

Key facts. Cited by 606 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 24; 2022: 73; 2023: 95; 2024: 120; 2025: 124; 2026: 170.

606 papers.

Sort:

By area:

  1. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,609
  2. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 404
  3. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 373
  4. 2023Powerset multi-class cross entropy loss for neural speaker diarizationcited by 109
  5. 2025Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokenscited by 109
  6. 2024ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scalecited by 88
  7. 2021A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understandingcited by 82
  8. 2021Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representationscited by 81
  9. 2024AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encodingcited by 67
  10. 2024Open-Source Conversational AI with SpeechBrain 1.0cited by 55
  11. 2022Speech Emotion Recognition using Self-Supervised Featurescited by 52
  12. 2023AutoAD: Movie Description in Contextcited by 50
38 more
  1. 2022Pushing the limits of raw waveform speaker recognitioncited by 49
  2. 2024The VoicePrivacy 2024 Challenge Evaluation Plancited by 39
  3. 2021Fine-tuning wav2vec2 for speaker recognitioncited by 35
  4. 2024DASB - Discrete Audio and Speech Benchmarkcited by 32
  5. 2023Speech Self-Supervised Representation Benchmarking: Are We Doing it Right?cited by 28
  6. 2022Why does Self-Supervised Learning for Speech Recognition Benefit Speaker Recognition?cited by 27
  7. 2024Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Surveycited by 27
  8. 2021Learning Audio-Visual Dereverberationcited by 26
  9. 2024How Should We Extract Discrete Audio Tokens from Self-Supervised Models?cited by 24
  10. 2023Multi-modal Facial Affective Analysis based on Masked Autoencodercited by 23
  11. 2024SpoofCeleb: Speech Deepfake Detection and SASV In The Wildcited by 22
  12. 2024Building a Taiwanese Mandarin Spoken Language Model: A First Attemptcited by 22
  13. 2024Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Surveycited by 22
  14. 2026OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Modelscited by 22
  15. 2024Preference Alignment Improves Language Model-Based TTScited by 21
  16. 2022Language-Agnostic Meta-Learning for Low-Resource Text-to-Speech with Articulatory Featurescited by 20
  17. 2022Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacycited by 20
  18. 2025AudioJudge: Understanding What Works in Large Audio Model Based Speech Evaluationcited by 20
  19. 2023CommonAccent: Exploring Large Acoustic Pretrained Models for Accent Classification Based on Common Voicecited by 19
  20. 2025LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancementcited by 19
  21. 2023LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speechcited by 17
  22. 2023Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generationcited by 17
  23. 2024Attentive Merging of Hidden Embeddings from Pre-trained Speech Model for Anti-spoofing Detectioncited by 17
  24. 2025Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-spoofingcited by 17
  25. 2021Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learningcited by 16
  26. 2023Speech Self-Supervised Representations Benchmarking: a Case for Larger Probing Headscited by 16
  27. 2022Low-Resource Multilingual and Zero-Shot Multispeaker TTScited by 15
  28. 2022Speaking Style Conversion in the Waveform Domain Using Discrete Self-Supervised Unitscited by 15
  29. 20233D-Speaker: A Large-Scale Multi-Device, Multi-Distance, and Multi-Dialect Corpus for Speech Representation Disentanglementcited by 15
  30. 2025VoiceAgentBench: Are Voice Assistants ready for agentic tasks?cited by 15
  31. 2021Self-Supervised Speaker Verification with Simple Siamese Network and Self-Supervised Regularizationcited by 14
  32. 2023ClArTTS: An Open-Source Classical Arabic Text-to-Speech Corpuscited by 14
  33. 2023SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition Systemscited by 14
  34. 2023AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representationcited by 14
  35. 2022Exact Prosody Cloning in Zero-Shot Multispeaker Text-to-Speechcited by 13
  36. 2024Enabling Auditory Large Language Models for Automatic Speech Quality Evaluationcited by 13
  37. 2024StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identificationcited by 13
  38. 2022MFA: TDNN with Multi-scale Frequency-channel Attention for Text-independent Speaker Verification with Short Utterancescited by 12

50 most cited of 606 All 606 (JSON)