mlsanityData to 7 Oct 2026

FedNST: Federated Noisy Student Training for Automatic Speech Recognition

arXiv 2206.02797 ↗First posted 6 Jun 2022eess.AS cs.AI cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) enables training state-of-the-art Automatic Speech Recognition (ASR) models on user devices (clients) in distributed systems, hence preventing transmission of raw user data to a central server. A key challenge facing practical adoption of FL for ASR is obtaining ground-truth labels on the clients. Existing approaches rely on clients to manually transcribe their speech, which is impractical for obtaining large training corpora. A promising alternative is using semi-/self-supervised learning approaches to leverage unlabelled user data. To this end, we propose FedNST, a novel method for training distributed ASR models using private and unlabelled user data. We explore various facets of FedNST, such as training models with different proportions of labelled and unlabelled data, and evaluate the proposed approach on 1173 simulated clients. Evaluating FedNST on LibriSpeech, where 960 hours of speech data is split equally into server (labelled) and client (unlabelled) data, showed a 22.5% relative word error rate reduction} (WERR) over a supervised baseline trained only on server data.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 28 of its 37 references that are in the map. First posted on arXiv 6 Jun 2022.

Builds on

28 of 37 references.

References · 28

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  3. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  4. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  5. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  6. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  7. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  8. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  9. 2020Adaptive Federated Optimizationcited by 1,036
  10. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 565
  11. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 404
  12. 2021W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Trainingcited by 340
16 more
  1. 2020HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clientscited by 334
  2. 2019The Non-IID Data Quagmire of Decentralized Machine Learningcited by 303
  3. 2016Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learningcited by 254
  4. 2020Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognitioncited by 185
  5. 2015End-to-End Attention-based Large Vocabulary Speech Recognitioncited by 148
  6. 2020Improved Noisy Student Training for Automatic Speech Recognitioncited by 139
  7. 2019Self-Training for End-to-End Speech Recognitioncited by 128
  8. 2020Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint Learningcited by 112
  9. 2022Divergence-aware Federated Self-Supervised Learningcited by 71
  10. 2018Pre-training on high-resource speech recognition improves low-resource speech-to-text translationcited by 70
  11. 2020Training Speech Recognition Models with Federated Learning: A Quality/Cost Frameworkcited by 46
  12. 2020On the Outsized Importance of Learning Rates in Local Update Methodscited by 34
  13. 2021End-to-End Speech Recognition from Federated Acoustic Modelscited by 30
  14. 2019Privacy-Preserving Adversarial Representation Learning in ASR: Reality or Illusion?cited by 22
  15. 2021Federated Acoustic Modeling For Automatic Speech Recognitioncited by 20
  16. 2021Semi-Supervised Federated Learning with non-IID Data: Algorithm and System Designcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 2; 2025: 0; 2026: 1.

5 papers.

  1. 2024Automatic Speech Recognition using Advanced Deep Learning Approaches: A surveycited by 50
  2. 2024Communication-Efficient Personalized Federated Learning for Speech-to-Text Taskscited by 8
  3. 2023Federated Learning for ASR based on Wav2vec 2.0cited by 7
  4. 2022Improving Noisy Student Training on Non-target Domain Data for Automatic Speech Recognitioncited by 5
  5. 2026A Practical Recipe for Semi-Supervised Federated ASR: Online Pseudo-Labels with Server Update Stabilizationcited by 0