mlsanityData to 14 Oct 2026

An Enhanced Res2Net with Local and Global Feature Fusion for Speaker Verification

arXiv 2305.12838 ↗First posted 22 May 2023eess.AS cs.SDcited by 42

Not on the map. Why?

Abstract (arXiv)

Effective fusion of multi-scale features is crucial for improving speaker verification performance. While most existing methods aggregate multi-scale features in a layer-wise manner via simple operations, such as summation or concatenation. This paper proposes a novel architecture called Enhanced Res2Net (ERes2Net), which incorporates both local and global feature fusion techniques to improve the performance. The local feature fusion (LFF) fuses the features within one single residual block to extract the local signal. The global feature fusion (GFF) takes acoustic features of different scales as input to aggregate global signal. To facilitate effective feature fusion in both LFF and GFF, an attentional feature fusion module is employed in the ERes2Net architecture, replacing summation or concatenation operations. A range of experiments conducted on the VoxCeleb datasets demonstrate the superiority of the ERes2Net in speaker verification. Code has been made publicly available at https://github.com/alibaba-damo-academy/3D-Speaker.

Key facts. Cited by 42 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 May 2023.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 10; 2025: 13; 2026: 17.

42 papers.

Sort:

By area:

  1. 2024CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Modelscited by 288
  2. 2025CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-trainingcited by 150
  3. 2024FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMscited by 122
  4. 2025Step-Audio: Unified Understanding and Generation in Intelligent Speech Interactioncited by 83
  5. 2025Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-spoofingcited by 19
  6. 20233D-Speaker: A Large-Scale Multi-Device, Multi-Distance, and Multi-Dialect Corpus for Speech Representation Disentanglementcited by 15
  7. 2024Towards Quantifying and Reducing Language Mismatch Effects in Cross-Lingual Speech Anti-Spoofingcited by 7
  8. 2024Certification of Speaker Recognition Models to Additive Perturbationscited by 6
  9. 2024Imperceptible Rhythm Backdoor Attacks: Exploring Rhythm Transformation for Embedding Undetectable Vulnerabilities on Speech Recognitioncited by 5
  10. 2026FlowSE-GRPO: Training Flow Matching Speech Enhancement via Online Reinforcement Learningcited by 5
  11. 2026FlowTTS-GRPO: Online Reinforcement Learning with Multi-Objective Reward Optimization for Flow-Matching Based Text-to-Speechcited by 5
  12. 2025The First VoicePrivacy Attacker Challengecited by 4
30 more
  1. 2024Zero-Shot Voice Conversion via Content-Aware Timbre Ensemble and Conditional Flow Matchingcited by 3
  2. 2026Sparse Autoencoders for Interpretable Emotion Control in Text-to-Speechcited by 3
  3. 2024Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal Speaker Diarizationcited by 2
  4. 2025MELA-TTS: Joint transformer-diffusion model with representation alignment for speech synthesiscited by 2
  5. 2026Scores Know Bobs Voice: Speaker Impersonation Attackcited by 2
  6. 2026X-VC: Zero-shot Streaming Voice Conversion in Codec Spacecited by 2
  7. 2024The First VoicePrivacy Attacker Challenge Evaluation Plancited by 1
  8. 2025VoxAging: Continuously Tracking Speaker Aging with a Large-Scale Longitudinal Dataset in English and Mandarincited by 1
  9. 2025StarVC: A Unified Auto-Regressive Framework for Joint Text and Speech Generation in Voice Conversioncited by 1
  10. 2025UtterTune: LoRA-Based Target-Language Pronunciation Edit and Control in Multilingual Text-to-Speechcited by 1
  11. 2026VoxKnesset: A Large-Scale Longitudinal Hebrew Speech Dataset for Aging Speaker Modelingcited by 1
  12. 2023ChinaTelecom System Description to VoxCeleb Speaker Recognition Challenge 2023cited by 0
  13. 2024GMM-ResNext: Combining Generative and Discriminative Models for Speaker Verificationcited by 0
  14. 2024Disentangling Age and Identity with a Mutual Information Minimization Approach for Cross-Age Speaker Verificationcited by 0
  15. 2025MAVFlow: Preserving Paralinguistic Elements with Conditional Flow Matching for Zero-Shot AV2AV Multilingual Translationcited by 0
  16. 2025A Multi-task Learning Balanced Attention Convolutional Neural Network Model for Few-shot Underwater Acoustic Target Recognitioncited by 0
  17. 2025Seewo's Submission to MLC-SLM: Lessons learned from Speech Reasoning Language Modelscited by 0
  18. 2025LAPS-Diff: A Diffusion-Based Framework for Singing Voice Synthesis With Language Aware Prosody-Style Guided Learningcited by 0
  19. 2025Self Identity Mappingcited by 0
  20. 2026DAME: Duration-Aware Matryoshka Embedding for Duration-Robust Speaker Verificationcited by 0
  21. 2026S-SONDO: Self-Supervised Knowledge Distillation for General Audio Foundation Modelscited by 0
  22. 2026UniAudio-Token: Empowering Semantic Speech Tokenizers with General Audio Perceptioncited by 0
  23. 2026Pmeta-TLA: Backdoor Attacks for Speech Classification Models via Meta-Learning with Timbre Leakage Attackcited by 0
  24. 2026DRL-CLBA: A Clean Label Backdoor Attack for Speech Classification via DDPG Reinforcement Learningcited by 0
  25. 2026Reasoning LLM Improves Speaker Recognition in Long-form TV Dramascited by 0
  26. 2026Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Modelscited by 0
  27. 2026Sequential Trajectories and Simultaneous Blending: Multi-Emotion Modeling for Instruction-Following TTScited by 0
  28. 2026MECT: Mixture of Experts with CNN-Transformer Network for Speaker verificationcited by 0
  29. 2026From Script to Drama: An Agentic Framework for Controllable Multi-Speaker Dialogue TTScited by 0
  30. 2026Can LLM Agents Automate Reinforcement Learning for Text-to-Speech?cited by 0