Parameter-Efficient Transfer Learning under Federated Learning for Automatic Speech Recognition
This work addresses privacy-preserved ASR services for users in federated settings, but it is incremental as it applies existing adapters to a known bottleneck.
The paper tackled the challenge of improving Automatic Speech Recognition (ASR) model performance across user-specific domains while maintaining data privacy, using federated learning and parameter-efficient domain adaptation to reduce communication costs and data requirements, and demonstrated that models with adapters achieve similar performance to centralized tuning.
This work explores the challenge of enhancing Automatic Speech Recognition (ASR) model performance across various user-specific domains while preserving user data privacy. We employ federated learning and parameter-efficient domain adaptation methods to solve the (1) massive data requirement of ASR models from user-specific scenarios and (2) the substantial communication cost between servers and clients during federated learning. We demonstrate that when equipped with proper adapters, ASR models under federated tuning can achieve similar performance compared with centralized tuning ones, thus providing a potential direction for future privacy-preserved ASR services. Besides, we investigate the efficiency of different adapters and adapter incorporation strategies under the federated learning setting.