2021/02/08 by Xiaodong Cui, Cui, Xiaodong, Songtao Lu +3 · 1 citation
Computer Science · Engineering · #Audio and Speech Processing (eess.AS) #Distributed #FOS: Computer and information sciences #FOS: Electrical engineering #Face recognition and analysis #Parallel #Privacy-Preserving Technologies in Data #Sound (cs.SD) #Speech Recognition and Synthesis #and Cluster Computing (cs.DC) #cs.DC #cs.SD #eess.AS #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2102.04429
Accepted by ICASSP 2021
arxiv created 2021/02/08 · openalex publication_date 2021/02/08 · arxiv updated 2021/02/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Data privacy and protection is a crucial issue for any automatic speech recognition (ASR) service provider when dealing with clients. In this paper, we investigate federated acoustic modeling using data from multiple clients. A client's data is stored on a local data server and the clients communicate only model parameters with a central server, and not their data. The communication happens infrequently to reduce the communication cost. To mitigate the non-iid issue, client adaptive federated training (CAFT) is proposed to canonicalize data across clients. The experiments are carried out on 1,150 hours of speech data from multiple domains. Hybrid LSTM acoustic models are trained via federated learning and their performance is compared to traditional centralized acoustic model training. The experimental results demonstrate the effectiveness of the proposed federated acoustic modeling strategy. We also show that CAFT can further improve the performance of the federated acoustic model.