An Experimental Study on Private Aggregation of Teacher Ensemble Learning for End-to-End Speech Recognition. (arXiv:2210.05614v2 [cs.SD] UPDATED)

Differential privacy (DP) is one data protection avenue to safeguard user
information used for training deep models by imposing noisy distortion on
privacy data. Such a noise perturbation often results in a severe performance
degradation in automatic speech recognition (ASR) in order to meet a privacy
budget $\varepsilon$. Private aggregation of teacher ensemble (PATE) utilizes
ensemble probabilities to improve ASR accuracy when dealing with the noise
effects controlled by small values of $\varepsilon$. We extend PATE learning to
work with …

aggregation arxiv ensemble experimental speech speech recognition study