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

What moved

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. …

Why it matters

Filed as a research filing from Apple, 2026-09-24.

On the record

• Filed from the Apple official RSS on 2026-09-24.
• Primary source host: machinelearning.apple.com.
• 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.