mlsanityData to 7 Oct 2026

Training Keyword Spotting Models on Non-IID Data with Federated Learning

arXiv 2005.10406 ↗First posted 21 May 2020eess.AS cs.CL cs.LGcited by 36

Not on the map. Why?

Abstract (arXiv)

We demonstrate that a production-quality keyword-spotting model can be trained on-device using federated learning and achieve comparable false accept and false reject rates to a centrally-trained model. To overcome the algorithmic constraints associated with fitting on-device data (which are inherently non-independent and identically distributed), we conduct thorough empirical studies of optimization algorithms and hyperparameter configurations using large-scale federated simulations. To overcome resource constraints, we replace memory intensive MTR data augmentation with SpecAugment, which reduces the false reject rate by 56%. Finally, to label examples (given the zero visibility into on-device data), we explore teacher-student training.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 9; 2023: 5; 2024: 4; 2025: 4; 2026: 2.

36 papers.

Sort:

  1. 2021A Field Guide to Federated Optimizationcited by 312
  2. 2022Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakagecited by 72
  3. 2023No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifiercited by 55
  4. 2021Convergence and Accuracy Trade-Offs in Federated Learning and Meta-Learningcited by 52
  5. 2022ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsitycited by 45
  6. 2022On Convergence of FedProx: Local Dissimilarity Invariant Bounds, Non-smoothness and Beyondcited by 37
  7. 2021End-to-End Speech Recognition from Federated Acoustic Modelscited by 30
  8. 2023Can Public Large Language Models Help Private Cross-device Federated Learning?cited by 30
  9. 2022Scaling Language Model Size in Cross-Device Federated Learningcited by 25
  10. 2022A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairnesscited by 13
  11. 2021Enabling On-Device Training of Speech Recognition Models with Federated Dropoutcited by 12
  12. 2021Federated Learning with Dynamic Transformer for Text to Speechcited by 11
24 more
  1. 2024Training Machine Learning models at the Edge: A Surveycited by 11
  2. 2021Privacy attacks for automatic speech recognition acoustic models in a federated learning frameworkcited by 10
  3. 2022Production federated keyword spotting via distillation, filtering, and joint federated-centralized trainingcited by 9
  4. 2024Analysis of Privacy Leakage in Federated Large Language Modelscited by 9
  5. 2021A Method to Reveal Speaker Identity in Distributed ASR Training, and How to Counter Itcited by 8
  6. 2022FLAME: Federated Learning Across Multi-device Environmentscited by 8
  7. 2021Jointly Learning from Decentralized (Federated) and Centralized Data to Mitigate Distribution Shiftcited by 7
  8. 2023Federated Learning for ASR based on Wav2vec 2.0cited by 7
  9. 2022Privacy-preserving Speech Emotion Recognition through Semi-Supervised Federated Learningcited by 6
  10. 2021Federated Self-Training for Semi-Supervised Audio Recognitioncited by 5
  11. 2021On the Impact of Device and Behavioral Heterogeneity in Federated Learningcited by 4
  12. 2021Zero-Shot Federated Learning with New Classes for Audio Classificationcited by 4
  13. 2022Avoid Overfitting User Specific Information in Federated Keyword Spottingcited by 4
  14. 2024Confidential Federated Computationscited by 4
  15. 2021Retrieving Speaker Information from Personalized Acoustic Models for Speech Recognitioncited by 2
  16. 2023Federated Automatic Differentiationcited by 2
  17. 2023Speech Privacy Leakage from Shared Gradients in Distributed Learningcited by 1
  18. 2024Efficient Language Model Architectures for Differentially Private Federated Learningcited by 1
  19. 2025Regularized Federated Learning for Privacy-Preserving Dysarthric and Elderly Speech Recognitioncited by 1
  20. 2025Unifying Physics- and Data-Driven Modeling via Novel Causal Spatiotemporal Graph Neural Network for Interpretable Epidemic Forecastingcited by 0
  21. 2025Enhancing the Performance of Global Model by Improving the Adaptability of Local Models in Federated Learningcited by 0
  22. 2025LAPA-based Dynamic Privacy Optimization for Wireless Federated Learning in Heterogeneous Environmentscited by 0
  23. 2026FedSteer: Taming Extreme Gradient Staleness in Federated Learning with Corrective Projections and Cachingcited by 0
  24. 2026Towards Personalized Federated Learning for Dysarthric Speech Recognitioncited by 0