2024/09/21 by Geeticka Chauhan, Chauhan, Geeticka, Steve Chien +7
Computer Science · Engineering · #Audio and Speech Processing (eess.AS) #Context-Aware Activity Recognition Systems #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Modular Robots and Swarm Intelligence #Sound (cs.SD) #Wireless Body Area Networks #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2409.13953
openalex publication_date 2024/09/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Self-supervised learning (SSL) methods for large speech models have proven to be highly effective at ASR. With the interest in public deployment of large pre-trained models, there is a rising concern for unintended memorization and leakage of sensitive data points from the training data. In this paper, we apply differentially private (DP) pre-training to a SOTA Conformer-based encoder, and study its performance on a downstream ASR task assuming the fine-tuning data is public. This paper is the first to apply DP to SSL for ASR, investigating the DP noise tolerance of the BEST-RQ pre-training method. Notably, we introduce a novel variant of model pruning called gradient-based layer freezing that provides strong improvements in privacy-utility-compute trade-offs. Our approach yields a LibriSpeech test-clean/other WER (%) of 3.78/ 8.41 with (10, 1e-9)-DP for extrapolation towards low dataset scales, and 2.81/ 5.89 with (10, 7.9e-11)-DP for extrapolation towards high scales.