@inproceedings{28047311370d4d90ac5c88bf69ebdb2d,
title = "Separate but Together: Unsupervised Federated Learning for Speech Enhancement from Non-IID Data",
abstract = "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 realworld 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.",
keywords = "Speech enhancement, federated learning, non-IID learning, source separation, unsupervised learning",
author = "Efthymios Tzinis and Jonah Casebeer and Zhepei Wang and Paris Smaragdis",
note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2021 ; Conference date: 17-10-2021 Through 20-10-2021",
year = "2021",
doi = "10.1109/WASPAA52581.2021.9632783",
language = "English (US)",
series = "IEEE Workshop on Applications of Signal Processing to Audio and Acoustics",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "46--50",
booktitle = "2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2021",
address = "United States",
}