mlsanityData to 7 Oct 2026

Deep Transfer Learning for Automatic Speech Recognition: Towards Better Generalization

arXiv 2304.14535 ↗First posted 27 Apr 2023cs.SD cs.CL cs.LGcited by 28

Not on the map. Why?

Abstract (arXiv)

Automatic speech recognition (ASR) has recently become an important challenge when using deep learning (DL). It requires large-scale training datasets and high computational and storage resources. Moreover, DL techniques and machine learning (ML) approaches in general, hypothesize that training and testing data come from the same domain, with the same input feature space and data distribution characteristics. This assumption, however, is not applicable in some real-world artificial intelligence (AI) applications. Moreover, there are situations where gathering real data is challenging, expensive, or rarely occurring, which can not meet the data requirements of DL models. deep transfer learning (DTL) has been introduced to overcome these issues, which helps develop high-performing models using real datasets that are small or slightly different but related to the training data. This paper presents a comprehensive survey of DTL-based ASR frameworks to shed light on the latest developments and helps academics and professionals understand current challenges. Specifically, after presenting the DTL background, a well-designed taxonomy is adopted to inform the state-of-the-art. A critical analysis is then conducted to identify the limitations and advantages of each framework. Moving on, a comparative study is introduced to highlight the current challenges before deriving opportunities for future research.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Builds on 85 of its 275 references that are in the map. First posted on arXiv 27 Apr 2023.

Builds on

85 of 275 references.

References · 85

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  4. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  5. 2019A Comprehensive Survey on Transfer Learningcited by 1,154
  6. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 609
  7. 2015Listen, Attend and Spellcited by 542
  8. 2016Domain Separation Networkscited by 317
  9. 2018Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesiscited by 280
  10. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 268
  11. 2018Characterizing and Avoiding Negative Transfercited by 226
  12. 2017State-of-the-art Speech Recognition With Sequence-to-Sequence Modelscited by 196
38 more
  1. 2020A Survey on Negative Transfercited by 120
  2. 2020Self-training and Pre-training are Complementary for Speech Recognitioncited by 98
  3. 2018Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hidingcited by 83
  4. 2020An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separationcited by 81
  5. 2021Recent Advances in Domain Adaptation for the Classification of Remote Sensing Datacited by 70
  6. 2021Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognitioncited by 68
  7. 2019Code-Switched Language Models Using Neural Based Synthetic Data from Parallel Sentencescited by 55
  8. 2020A General Multi-Task Learning Framework to Leverage Text Data for Speech to Text Taskscited by 51
  9. 2019Lightweight and Efficient End-to-End Speech Recognition Using Low-Rank Transformercited by 47
  10. 2018Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptationcited by 45
  11. 2019Transfer Learning with Dynamic Distribution Adaptationcited by 40
  12. 2020Transfer Learning in Large-scale Gaussian Graphical Models with False Discovery Rate Controlcited by 38
  13. 2019Hear "No Evil", See "Kenansville": Efficient and Transferable Black-Box Attacks on Speech Recognition and Voice Identification Systemscited by 37
  14. 2021Improved Fine-Tuning by Better Leveraging Pre-Training Datacited by 36
  15. 2018Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modelingcited by 34
  16. 2020A Survey on Transfer Learning in Natural Language Processingcited by 33
  17. 2021Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERTcited by 31
  18. 2022Efficient Adapter Transfer of Self-Supervised Speech Models for Automatic Speech Recognitioncited by 31
  19. 2023Advancing Medical Imaging with Language Models: A Journey from N-grams to ChatGPTcited by 28
  20. 2017Towards End-to-End Speech Recognition with Deep Convolutional Neural Networkscited by 24
  21. 2018Transfer Learning from Adult to Children for Speech Recognition: Evaluation, Analysis and Recommendationscited by 21
  22. 2020Self-Supervised Representations Improve End-to-End Speech Translationcited by 21
  23. 2023Dropout Reduces Underfittingcited by 21
  24. 2023Deep transfer learning for intrusion detection in industrial control networks: A comprehensive reviewcited by 21
  25. 2021Adversarial Attacks and Defenses for Speech Recognition Systemscited by 20
  26. 2021An Adapter Based Pre-Training for Efficient and Scalable Self-Supervised Speech Representation Learningcited by 19
  27. 2022Knowledge Transfer from Large-scale Pretrained Language Models to End-to-end Speech Recognizerscited by 19
  28. 2019MFCC-based Recurrent Neural Network for Automatic Clinical Depression Recognition and Assessment from Speechcited by 18
  29. 2021A Study of the Generalizability of Self-Supervised Representationscited by 18
  30. 2019Speech-XLNet: Unsupervised Acoustic Model Pretraining For Self-Attention Networkscited by 17
  31. 2021EmoNet: A Transfer Learning Framework for Multi-Corpus Speech Emotion Recognitioncited by 17
  32. 2019Learning Across Tasks and Domainscited by 16
  33. 2020Adversarial Transfer Learning for Punctuation Restorationcited by 15
  34. 2020DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptationcited by 15
  35. 2017Towards Language-Universal End-to-End Speech Recognitioncited by 14
  36. 2019Self-Attention Networks for Connectionist Temporal Classification in Speech Recognitioncited by 14
  37. 2022Improving CTC-based speech recognition via knowledge transferring from pre-trained language modelscited by 14
  38. 2019Preech: A System for Privacy-Preserving Speech Transcriptioncited by 13

50 most cited of 85 All 85 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 12; 2025: 10; 2026: 2.

28 papers.

Sort:

  1. 2024Automatic Speech Recognition using Advanced Deep Learning Approaches: A surveycited by 50
  2. 2023Federated Learning for Computer Visioncited by 22
  3. 2024Transformers and Large Language Models for Efficient Intrusion Detection Systems: A Comprehensive Surveycited by 21
  4. 2023AI in Thyroid Cancer Diagnosis: Techniques, Trends, and Future Directionscited by 18
  5. 2023Deep Learning for Steganalysis of Diverse Data Types: A review of methods, taxonomy, challenges and future directionscited by 16
  6. 2024Enhancing IoT Security with CNN and LSTM-Based Intrusion Detection Systemscited by 9
  7. 2024Advancing 3D Point Cloud Understanding through Deep Transfer Learning: A Comprehensive Surveycited by 9
  8. 2024Automatic Speech Recognition with BERT and CTC Transformers: A Reviewcited by 8
  9. 2024A Review of Deep Learning Approaches for Non-Invasive Cognitive Impairment Detectioncited by 5
  10. 2025Advanced Deep Learning and Large Language Models: Comprehensive Insights for Cancer Detectioncited by 4
  11. 2023Current Topological and Machine Learning Applications for Bias Detection in Textcited by 3
  12. 2024Federated and Transfer Learning for Cancer Detection Based on Image Analysiscited by 3
16 more
  1. 2024Deep Transfer Learning for Kidney Cancer Diagnosiscited by 3
  2. 2025Adapting Automatic Speech Recognition for Accented Air Traffic Control Communicationscited by 3
  3. 2025Recent Advances in Transformer and Large Language Models for UAV Applicationscited by 3
  4. 2024Machine Learning and Transformers for Thyroid Carcinoma Diagnosis: A Reviewcited by 2
  5. 2024Deep Learning Techniques for Hand Vein Biometrics: A Comprehensive Reviewcited by 2
  6. 2025Advancing Arabic Speech Recognition Through Large-Scale Weakly Supervised Learningcited by 2
  7. 2024Deep Insights into Cognitive Decline: A Survey of Leveraging Non-Intrusive Modalities with Deep Learning Techniquescited by 1
  8. 2025Improving Pretrained YAMNet for Enhanced Speech Command Detection via Transfer Learningcited by 1
  9. 2025Enhancing Cochlear Implant Signal Coding with Scaled Dot-Product Attentioncited by 1
  10. 2025From Dialect Gaps to Identity Maps: Tackling Variability in Speaker Verificationcited by 1
  11. 2025Benchmarking Automatic Speech Recognition Models for African Languagescited by 1
  12. 2026SE-Enhanced ViT and BiLSTM-Based Intrusion Detection for Secure IIoT and IoMT Environmentscited by 1
  13. 2024Transliterated Zero-Shot Domain Adaptation for Automatic Speech Recognitioncited by 0
  14. 2025Hybrid Artificial Intelligence Strategies for Drone Navigationcited by 0
  15. 2025Transfer Learning-Based Deep Residual Learning for Speech Recognition in Clean and Noisy Environmentscited by 0
  16. 2026Hybrid ResNet-1D-BiGRU with Multi-Head Attention for Cyberattack Detection in Industrial IoT Environmentscited by 0