Federated Learning with Differential Privacy for End-to-End Speech Recognition

no code implementations • 29 Sep 2023 • Martin Pelikan, Sheikh Shams Azam, Vitaly Feldman, Jan "Honza" Silovsky, Kunal Talwar, Tatiana Likhomanenko

($4. 5$, $10^{-9}$)-$\textbf{DP}$) with a 1. 3% (resp.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Importance of Smoothness Induced by Optimizers in FL4ASR: Towards Understanding Federated Learning for End-to-End ASR

no code implementations • 22 Sep 2023 • Sheikh Shams Azam, Tatiana Likhomanenko, Martin Pelikan, Jan "Honza" Silovsky

In this paper, we start by training End-to-End Automatic Speech Recognition (ASR) models using Federated Learning (FL) and examining the fundamental considerations that can be pivotal in minimizing the performance gap in terms of word error rate between models trained using FL versus their centralized counterpart.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2