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