Federated Marginal Personalization for ASR Rescoring

Abstract

We introduce federated marginal personalization (FMP), a novel method for continuously updating personalized neural network language models (NNLMs) on private devices using federated learning (FL). Instead of fine-tuning the parameters of NNLMs on personal data, FMP regularly estimates global and personalized marginal distributions of words, and adjusts the probabilities from NNLMs by an adaptation factor that is specific to each word. Our presented approach can overcome the limitations of federated fine-tuning and efficiently learn personalized NNLMs on devices. We study the application of FMP on second-pass ASR rescoring tasks. Experiments on two speech evaluation datasets show modest word error rate (WER) reductions. We also demonstrate that FMP could offer reasonable privacy with only a negligible cost in speech recognition accuracy.

References in corpus (10)

• Federated Learning: Strategies for Improving Communication Efficiency
• Federated Optimization: Distributed Machine Learning for On-Device Intelligence
• An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
• Learning Differentially Private Recurrent Language Models
• Differentially Private Federated Learning: A Client Level Perspective
• Federated Meta-Learning with Fast Convergence and Efficient Communication
• Federated Tensor Factorization for Computational Phenotyping
• Federated User Representation Learning
• Federated Learning of N-gram Language Models
• Generative Knowledge Transfer for Neural Language Models