A Practical Recipe for Semi-Supervised Federated ASR: Online Pseudo-Labels with Server Update Stabilization

T1Covered by 1 source · first reported by arXiv at 24 Sept, 04:00 UTC

arXiv:2609.25471v1 Announce Type: cross Abstract: Semi-supervised federated learning (SSFL) trains models on clients' unlabeled data using a teacher to generate pseudo-labels, with a small labeled seed dataset on the server. Automatic Speech Recognition (ASR) is particularly fragile here…

science

Sources

• T1A Practical Recipe for Semi-Supervised Federated ASR: Online Pseudo-Labels with Server Update StabilizationarXiv24 Sept, 04:00