cd /news/artificial-intelligence/ediar-training-free-open-speaker-str… · home › topics › artificial-intelligence › article
[ARTICLE · art-170352] src=aiflash.com ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

eDIAR: Training-Free Open-Speaker Streaming Diarization for Long Meetings and Large Archives via e-means

Researchers introduced eDIAR, a training-free open-speaker streaming diarization method that removes the fixed speaker-slot limit of neural diarizers such as Streaming Sortformer and Nemotron-3, which cannot name more speakers than their output slots. The eDIAR approach targets long meetings of up to an hour and large archives where the number of speakers is unknown in advance, and the authors say it lifts the slot cap without retraining.

read1 min views1 publishedNov 16, 2026

Meetings last up to an hour, and nobody knows in advance how many people will speak. Neural diarizers with a fixed number of output slots, such as Streaming Sortformer and Nemotron-3, are accurate and run online, but they cannot name more speakers than they have slots. We remove this limit without r

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @ediar 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/ediar-training-free-…] indexed:0 read:1min 2026-11-16 · —