mlsanityData to 7 Oct 2026

Production federated keyword spotting via distillation, filtering, and joint federated-centralized training

arXiv 2204.06322 ↗First posted 11 Apr 2022eess.AS cs.CL cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

We trained a keyword spotting model using federated learning on real user devices and observed significant improvements when the model was deployed for inference on phones. To compensate for data domains that are missing from on-device training caches, we employed joint federated-centralized training. And to learn in the absence of curated labels on-device, we formulated a confidence filtering strategy based on user-feedback signals for federated distillation. These techniques created models that significantly improved quality metrics in offline evaluations and user-experience metrics in live A/B experiments.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 21 of its 37 references that are in the map. First posted on arXiv 11 Apr 2022.

Builds on

21 of 37 references.

References · 21

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  4. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  5. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  6. 2020Adaptive Federated Optimizationcited by 1,036
  7. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 580
  8. 2018Federated Learning for Mobile Keyboard Predictioncited by 565
  9. 2020A Survey of Label-noise Representation Learning: Past, Present and Futurecited by 121
  10. 2018Federated Learning for Keyword Spottingcited by 95
  11. 2021BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognitioncited by 88
  12. 2019Putting An End to End-to-End: Gradient-Isolated Learning of Representationscited by 85
9 more
  1. 2020Training Keyword Spotting Models on Non-IID Data with Federated Learningcited by 36
  2. 2020Improving on-device speaker verification using federated learning with privacycited by 29
  3. 2021Large-scale ASR Domain Adaptation using Self- and Semi-supervised Learningcited by 26
  4. 2018End-to-End Streaming Keyword Spottingcited by 25
  5. 2017A Cascade Architecture for Keyword Spotting on Mobile Devicescited by 15
  6. 2018Secure Federated Transfer Learningcited by 13
  7. 2020Learning To Detect Keyword Parts And Whole By Smoothed Max Poolingcited by 10
  8. 2021Noisy student-teacher training for robust keyword spottingcited by 10
  9. 2021Jointly Learning from Decentralized (Federated) and Centralized Data to Mitigate Distribution Shiftcited by 7

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 3; 2024: 4.

9 papers.

  1. 2024Federated Learning in Practice: Reflections and Projectionscited by 15
  2. 2024Federated Distillation: A Surveycited by 14
  3. 2022A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairnesscited by 13
  4. 2024Training Machine Learning models at the Edge: A Surveycited by 11
  5. 2022Mixed Federated Learning: Joint Decentralized and Centralized Learningcited by 8
  6. 2023Federated Learning for ASR based on Wav2vec 2.0cited by 7
  7. 2023Locale Encoding For Scalable Multilingual Keyword Spotting Modelscited by 3
  8. 2023Speech Privacy Leakage from Shared Gradients in Distributed Learningcited by 1
  9. 2024Learning from straggler clients in federated learningcited by 1