Federated Learning

Chapter 20: Federated learning for privacy-preserving speech recognition

Chao-Han Huck Yang^a; Sabato Marco Siniscalchi^b,c    aNvidia Research, Taipei, Taiwan^bUniversity of Enna, Enna, Italy^cNorwegian University of Science and Technology, Trondheim, Norway

Abstract

Speech signal contains rich information encompassing gender, accent, speaking environment, and other speaker characteristics. Meanwhile, deploying high-performance speech applications often requires a large amount of training speech data, which are often collected from end-users. Therefore, protecting data privacy becomes a rising concern when speech data are employed to deploy commercial speech applications. That motivates the rising interest in designing “federated learning” for voice ...