Work

Production federated keyword spotting via distillation, filtering, and joint federated-centralized training

Year: 2022
Type: conference-paper
Abstract: We trained a keyword spotting model using federated learning on real user devices and observed significant improvements when the model was deployed for inference on phones. To compensate for data domains that are missing from on-device training caches, we employed joint federated-centralized training. And to learn in the absence of curated labels on-device, we formulated a confidence filtering strategy based on user-feedback signals for federated distillation. These techniques created models that significantly improved quality metrics in offline evaluations and user-experience metrics in live A/B experiments.
Language: English
Open Access status: green
OpenAlex ID: W4297841802
FWCI: 1.018
Cites: 26
Cited by: 19
Related to: 10