A Practical Recipe for Semi-Supervised Federated ASR: Online Pseudo-Labels with Server Update Stabilization
These findings yield guidelines for SSFL in ASR training, improving over the strongest prior method on 9 of 11 pairs, by by $20.8\% on average in-domain and cross-domain, narrowing the gap to fully-supervised FL.
Wonho Bae, Zakaria Aldeneh, Martin Pelikan et al.
· 0 citations