Differentially Private Adapters for Parameter Efficient Acoustic Modeling. (arXiv:2305.11360v1 [cs.SD])

In this work, we devise a parameter-efficient solution to bring differential
privacy (DP) guarantees into adaptation of a cross-lingual speech classifier.
We investigate a new frozen pre-trained adaptation framework for DP-preserving
speech modeling without full model fine-tuning. First, we introduce a noisy
teacher-student ensemble into a conventional adaptation scheme leveraging a
frozen pre-trained acoustic model and attain superior performance than DP-based
stochastic gradient descent (DPSGD). Next, we insert residual adapters (RA)
between layers of the frozen pre-trained acoustic model. The …

acoustic differential privacy framework modeling parameter privacy private solution speech student work