Sotto Voce: Federated Speech Recognition with Differential Privacy Guarantees
This addresses privacy and data-sharing challenges for organizations handling sensitive speech data, though it is incremental as it combines existing federated learning and differential privacy techniques.
The paper tackles the problem of building accurate speech recognition models across multiple organizations without sharing sensitive data by using federated learning with differential privacy, and demonstrates that the model improves with private data while maintaining privacy guarantees.
Speech data is expensive to collect, and incredibly sensitive to its sources. It is often the case that organizations independently collect small datasets for their own use, but often these are not performant for the demands of machine learning. Organizations could pool these datasets together and jointly build a strong ASR system; sharing data in the clear, however, comes with tremendous risk, in terms of intellectual property loss as well as loss of privacy of the individuals who exist in the dataset. In this paper, we offer a potential solution for learning an ML model across multiple organizations where we can provide mathematical guarantees limiting privacy loss. We use a Federated Learning approach built on a strong foundation of Differential Privacy techniques. We apply these to a senone classification prototype and demonstrate that the model improves with the addition of private data while still respecting privacy.