Privacy attacks for automatic speech recognition acoustic models in a federated learning framework. (arXiv:2111.03777v2 [cs.CL] UPDATED)

Web: http://arxiv.org/abs/2111.03777

This paper investigates methods to effectively retrieve speaker information
from the personalized speaker adapted neural network acoustic models (AMs) in
automatic speech recognition (ASR). This problem is especially important in the
context of federated learning of ASR acoustic models where a global model is
learnt on the server based on the updates received from multiple clients. We
propose an approach to analyze information in neural network AMs based on a
neural network footprint on the so-called Indicator dataset. Using this …

acoustic attacks framework learning privacy recognition