SDCLLGASMay 11, 2021

Separate but Together: Unsupervised Federated Learning for Speech Enhancement from Non-IID Data

arXiv:2105.04727v320 citations
Originality Incremental advance
AI Analysis

This addresses speech enhancement for distributed clients with limited, non-IID data, but it is incremental as it builds on existing federated and unsupervised learning methods.

The paper tackles speech enhancement and separation in federated learning with non-IID data by proposing FEDENHANCE, an unsupervised approach that achieves competitive performance compared to IID training and improves convergence speed with server-side transfer learning.

We propose FEDENHANCE, an unsupervised federated learning (FL) approach for speech enhancement and separation with non-IID distributed data across multiple clients. We simulate a real-world scenario where each client only has access to a few noisy recordings from a limited and disjoint number of speakers (hence non-IID). Each client trains their model in isolation using mixture invariant training while periodically providing updates to a central server. Our experiments show that our approach achieves competitive enhancement performance compared to IID training on a single device and that we can further facilitate the convergence speed and the overall performance using transfer learning on the server-side. Moreover, we show that we can effectively combine updates from clients trained locally with supervised and unsupervised losses. We also release a new dataset LibriFSD50K and its creation recipe in order to facilitate FL research for source separation problems.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes