Federated Representation Learning for Automatic Speech Recognition
원문 초록
Federated Learning (FL) is a privacy-preserving paradigm, allowing edge devices to learn collaboratively without sharing data. Edge devices like Alexa and Siri are prospective sources of unlabeled audio data that can be tapped to learn robust audio representations. In this work, we bring Self-supervised Learning (SSL) and FL together to learn representations for Automatic Speech Recognition respecting data privacy constraints. We use the speaker and chapter information in the unlabeled speech dataset, Libri-Light, to simulate non-IID speaker-siloed data distributions and pre-train an LSTM encoder with the Contrastive Predictive Coding framework with FedSGD. We show that the pre-trained ASR encoder in FL performs as well as a centrally pre-trained model and produces an improvement of 12-15% (WER) compared to no pre-training. We further adapt the federated pre-trained models to a new language, French, and show a 20% (WER) improvement over no pre-training.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Domain Borders Are There to Be Crossed With Federated Few-Shot Adaptation
Geo-ORBIT: A Federated Digital Twin Framework for Scene-Adaptive Lane Geometry Detection
S2FGL: Spatial Spectral Federated Graph Learning
FedSC: Federated Learning with Semantic-Aware Collaboration
Federated Learning for Commercial Image Sources
A Privacy-Preserving Framework for Advertising Personalization Incorporating Federated Learning and Differential Privacy
토론
이 논문과 연결된 포럼 글이 아직 없습니다.