BriefGPT.xyz
Oct, 2020
使用联邦学习训练语音识别模型：质量/成本框架
Training Speech Recognition Models with Federated Learning: A Quality/Cost Framework
HTML
PDF
Dhruv Guliani, Francoise Beaufays, Giovanni Motta
TL;DR
本文提出使用联邦学习来训练语音识别模型，并通过对非独立同分布数据分布程度的调整来平衡模型质量和联邦训练计算成本之间的关系，并证明超参数优化和适当使用变分噪声可以弥补非独立同分布数据对模型影响的影响。
Abstract
We propose using
federated learning
, a decentralized on-device learning paradigm, to train
speech recognition
models. By performing epochs of training on a per-user basis,
→