Regularized Federated Learning for Privacy-Preserving Dysarthric and Elderly Speech Recognition
Not on the map. Why?
Abstract (arXiv)
Accurate recognition of dysarthric and elderly speech remains challenging to date. While privacy concerns have driven a shift from centralized approaches to federated learning (FL) to ensure data confidentiality, this further exacerbates the challenges of data scarcity, imbalanced data distribution and speaker heterogeneity. To this end, this paper conducts a systematic investigation of regularized FL techniques for privacy-preserving dysarthric and elderly speech recognition, addressing different levels of the FL process by 1) parameter-based, 2) embedding-based and 3) novel loss-based regularization. Experiments on the benchmark UASpeech dysarthric and DementiaBank Pitt elderly speech corpora suggest that regularized FL systems consistently outperform the baseline FedAvg system by statistically significant WER reductions of up to 0.55% absolute (2.13% relative). Further increasing communication frequency to one exchange per batch approaches centralized training performance.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 28 of its 48 references that are in the map. First posted on arXiv 2 Jun 2025.
Builds on
28 of 48 references.
References · 28
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
- 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
- 2019A Survey on Distributed Machine Learningcited by 188
- 2020Alzheimer's Dementia Recognition through Spontaneous Speech: The ADReSS Challengecited by 104
- 2018Federated Learning for Keyword Spottingcited by 95
- 2020Training Speech Recognition Models with Federated Learning: A Quality/Cost Frameworkcited by 46
- 2020Training Keyword Spotting Models on Non-IID Data with Federated Learningcited by 36
- 2020Improving on-device speaker verification using federated learning with privacycited by 30
- 2021End-to-End Speech Recognition from Federated Acoustic Modelscited by 30
- 2022Speaker adaptation for Wav2vec2 based dysarthric ASRcited by 21
16 more
- 2021Federated Acoustic Modeling For Automatic Speech Recognitioncited by 20
- 2022Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognitioncited by 19
- 2022Recent Progress in the CUHK Dysarthric Speech Recognition Systemcited by 17
- 2024Enhancing Pre-trained ASR System Fine-tuning for Dysarthric Speech Recognition using Adversarial Data Augmentationcited by 17
- 2022Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognitioncited by 16
- 2021Federated Learning in ASR: Not as Easy as You Thinkcited by 14
- 2022Semi-FedSER: Semi-supervised Learning for Speech Emotion Recognition On Federated Learning using Multiview Pseudo-Labelingcited by 12
- 2022Conformer Based Elderly Speech Recognition System for Alzheimer's Disease Detectioncited by 12
- 2023Federated learning for secure development of AI models for Parkinson's disease detection using speech from different languagescited by 9
- 2024Self-supervised ASR Models and Features For Dysarthric and Elderly Speech Recognitioncited by 9
- 2023Importance of Smoothness Induced by Optimizers in FL4ASR: Towards Understanding Federated Learning for End-to-End ASRcited by 8
- 2024Communication-Efficient Personalized Federated Learning for Speech-to-Text Taskscited by 8
- 2022Federated Learning with Intermediate Representation Regularizationcited by 3
- 2023Sparse Training for Federated Learning with Regularized Error Correctioncited by 2
- 2024Parameter-Efficient Transfer Learning under Federated Learning for Automatic Speech Recognitioncited by 2
- 2025Phone-purity Guided Discrete Tokens for Dysarthric Speech Recognitioncited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.