Federated Learning (FL) is a privacy-preserving paradigm, allowing edge devices to learn collaboratively without sharing data. Edge devices like Alexa and Siri are prospective sources of unlabeled audio data that can be tapped to learn robust audio representations. In this work, we bring Self-supervised Learning (SSL) and FL together to learn representations for Automatic Speech Recognition respecting data privacy constraints. We use the speaker and chapter information in the unlabeled speech dataset, Libri-Light, to simulate non-IID speaker-siloed data distributions and pre-train an LSTM encoder with the Contrastive Predictive Coding framework with FedSGD. We show that the pre-trained ASR encoder in FL performs as well as a centrally pre-trained model and produces an improvement of 12-15% (WER) compared to no pre-training. We further adapt the federated pre-trained models to a new language, French, and show a 20% (WER) improvement over no pre-training.

翻译：联邦学习是一种隐私保护范式，使边缘设备能够在不共享数据的情况下进行协作学习。Alexa和Siri等边缘设备是未标注音频数据的潜在来源，可用于学习鲁棒的音频表示。在本文中，我们将自监督学习和联邦学习相结合，在满足数据隐私约束的条件下学习面向自动语音识别的表示。我们利用未标注语音数据集Libri-Light中的说话者和章节信息，模拟非独立同分布的说话者-分片数据分布，并采用对比预测编码框架和FedSGD算法预训练LSTM编码器。实验表明，联邦学习框架下预训练的ASR编码器性能与集中式预训练模型相当，相比无预训练的情况，词错误率降低12-15%。我们进一步将联邦预训练模型迁移到新语言法语中，相较于无预训练，词错误率降低20%。