| Paper | Code | DER | ModelName | ReleaseDate |
|---|---|---|---|---|
| Efficient and Generalizable Speaker Diarization via Structured Pruning of Self-Supervised Models | ✓ Link | 13.9 | diarizen-wavlm-large-s80-md-v2 | 2025-06-23 |
| VBx for End-to-End Neural and Clustering-based Diarization | ✓ Link | 13.9 | DiariZen-Large-s80 + cVBx | 2025-10-22 |
| Fine-tune Before Structured Pruning: Towards Compact and Accurate Self-Supervised Models for Speaker Diarization | ✓ Link | 15.1 | DiariZen WavLM-Large 80% pruned (3-domain) | 2025-05-30 |
| Diarization-Guided Multi-Speaker Embeddings | ✓ Link | 15.7 | Diarization-Guided Multi-Speaker Embeddings (MSE) | 2025-08-17 |
| PixIT: Joint Training of Speaker Diarization and Speech Separation from Real-world Multi-speaker Recordings | ✓ Link | 17.1 | PixIT (lambda=1, diarization only) | 2024-03-04 |
| Pretraining Multi-Speaker Identification for Neural Speaker Diarization | 18.96 | ReDimNet-B2 multi-SID + compound DIA pretraining | 2025-05-30 | |
| Powerset multi-class cross entropy loss for neural speaker diarization | ✓ Link | 22.0 | Powerset (compound training) | 2023-10-19 |