| Enhancing Speaker Verification with w2v-BERT 2.0 and Knowledge Distillation guided Structured Pruning | | 0.12 | 0.025 | w2v-BERT 2.0 LoRA Adapter MFA + LMFT + calibration (extra data) | 2025-10-05 |
| ReDimNet2: Scaling Speaker Verification via Time-Pooled Dimension Reshaping | ✓ Link | 0.23 | | ReDimNet2-B6 (VoxBlink2 + VoxCeleb2) (extra data) | 2026-03-12 |
| ECAPA2: A Hybrid Neural Network Architecture and Training Strategy for Robust Speaker Embeddings | | 0.34 | 0.029 | ECAPA2 | 2024-01-16 |
| Kiwano: A Cutting-Edge Open-Source Toolkit for Speaker Verification | | 0.34 | 0.042 | Kiwano fwSE-ResNet-200 (full refinement) | 2026-06-21 |
| Reshape Dimensions Network for Speaker Recognition | ✓ Link | 0.37 | 0.030 | ReDimNet-B6-SF2-LM-ASNorm | 2024-07-25 |
| ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models | ✓ Link | 0.39 | | WavLM-Large + ECAPA-TDNN (extra data) | 2024-01-30 |
| Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit | | 0.447 | 0.043 | WeSpeaker ResNet293 | 2022-10-31 |
| Golden Gemini is All You Need: Finding the Sweet Spots for Speaker Verification | | 0.596 | 0.065 | Gemini DF-ResNet183 | 2023-12-06 |
| ERes2NetV2: Boosting Short-Duration Speaker Verification Performance with Computational Efficiency | ✓ Link | 0.61 | 0.054 | ERes2NetV2 | 2024-06-04 |
| MFA-Conformer: Multi-scale Feature Aggregation Conformer for Automatic Speaker Verification | | 0.64 | 0.081 | MFA-Conformer (1/2) (extra data) | 2022-03-29 |
| TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context | ✓ Link | 0.68 | 0.087 | TitaNet-L (extra data) | 2021-10-08 |
| CAM++: A Fast and Efficient Network for Speaker Verification Using Context-Aware Masking | | 0.73 | 0.0911 | CAM++ | 2023-03-01 |
| An Enhanced Res2Net with Local and Global Feature Fusion for Speaker Verification | ✓ Link | 0.83 | 0.072 | ERes2Net (LMT) | 2023-05-22 |
| ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification | ✓ Link | 0.87 | 0.1066 | ECAPA-TDNN (C=1024) | 2020-05-14 |
| Pushing the limits of raw waveform speaker recognition | ✓ Link | 0.89 | 0.0659 | RawNet3 (extra data) | 2022-03-16 |
| ExPO: Explainable Phonetic Trait-Oriented Network for Speaker Verification | | 1.356 | 0.166 | ExPO (LAAM) | 2025-01-10 |
| UniPET-SPK: A Unified Framework for Parameter-Efficient Tuning of Pre-trained Speech Models for Robust Speaker Verification | | 1.59 | 0.130 | UniPET-SPK (WavLM Base+ + TDNN) | 2025-01-27 |