| Paper | Code | DER | ModelName | ReleaseDate |
|---|---|---|---|---|
| Efficient and Generalizable Speaker Diarization via Structured Pruning of Self-Supervised Models | ✓ Link | 10.8 | diarizen-wavlm-large-s80-md-v2 | 2025-06-23 |
| VBx for End-to-End Neural and Clustering-based Diarization | ✓ Link | 12.4 | DiariZen-Large-s80 + cVBx | 2025-10-22 |
| Fine-tune Before Structured Pruning: Towards Compact and Accurate Self-Supervised Models for Speaker Diarization | ✓ Link | 15.8 | DiariZen WavLM-Large 80% pruned (3-domain) | 2025-05-30 |
| Diarization-Guided Multi-Speaker Embeddings | ✓ Link | 15.9 | 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 | 19.5 | PixIT (lambda=1, diarization only) | 2024-03-04 |
| Powerset multi-class cross entropy loss for neural speaker diarization | ✓ Link | 23.3 | Powerset (compound training) | 2023-10-19 |