论文标题
生产联合关键字通过蒸馏，过滤和联合联邦中心化培训来发现
Production federated keyword spotting via distillation, filtering, and joint federated-centralized training
论文作者
论文摘要
我们使用在实际用户设备上使用联合学习的联合学习训练了一个关键字发现模型，并在部署模型以推断电话时观察到了显着改进。为了补偿在设备培训缓存中缺少的数据域，我们采用了联合联邦中心化培训。为了在没有策划的标签上学习，我们根据用户反馈信号制定了置信度过滤策略，用于联合蒸馏。这些技术创建了模型，可在实时A/B实验中显着改善离线评估和用户体验指标的质量指标。
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.
