eDIAR: training-free streaming diarization removes fixed speaker-slot limits
kaist-ai · hf · 2026-11-16
KAIST AI researchers present eDIAR, a training-free open-speaker streaming diarization method. Instead of being capped by fixed output slots (a 4-slot model can't name a 5th speaker), it clusters speaker embeddings within slots via e-means once all slots are used, supporting unlimited speakers and efficient linking for long meetings and large archives.
More from Research
- Researchers formally specify ops interfaces for CockroachDB, Kafka and RabbitMQ to make AI operators verifiable — tianyin_xu · 2026-11-16
- Astera Residencies open: up to $2M in funding for off-network researchers — dr_alphalyrae · 2026-11-16
- 'It Knows Google Is Watching': Viral Chat Surfaces J-Lens Evaluation-Awareness Research — repligate · 2026-11-16
- NeurIPS Paper Explains Why Knowledge Editing in English Fails to Propagate Across Languages in Multilingual LLMs — Tanmoy_Chak · 2026-11-16
- MDPI review surveys reinforcement learning approaches in quantitative trading — PtrPomorski · 2026-11-16
- JEM trained in 20 H100-hours lands 1 point behind fine-tuned DINOv3 — gabriberton · 2026-11-16