arxiv
PublishedJune 2, 2026 at 4:00 AM
Echo: A Joint-Embedding Predictive Architecture for Speaker Diarization and Speech Recognition in a Shared Latent Space
Publisher summary· verbatim
arXiv:2606.01909v1 Announce Type: cross Abstract: We present Echo, a proof-of-concept audio system built around a single 25 M-parameter ViT encoder. The encoder is pretrained with a JEPA objective and then specialised by stages to carry speaker identity, phonetic content, and dynamic source routing
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivDemocratizing Agent Deployment Safety: A Structural Monitoring Approach19harxivHarnessing LLMs for Reliable Academic Supervision: A Comparative Study19harxivAccelerating A/B-Tests with Counterfactual Estimation: Reducing Variance through Policy Overlap19harxivTIDE: Trustworthy and Interpretable Battery Degradation Estimation with Contextual Learning and Symbolic Distillation19hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗