mlsanityData to 7 Oct 2026

Learning Fast Adaptation on Cross-Accented Speech Recognition

arXiv 2003.01901 ↗First posted 4 Mar 2020eess.AS cs.SDcited by 28

Not on the map. Why?

Abstract (arXiv)

Local dialects influence people to pronounce words of the same language differently from each other. The great variability and complex characteristics of accents creates a major challenge for training a robust and accent-agnostic automatic speech recognition (ASR) system. In this paper, we introduce a cross-accented English speech recognition task as a benchmark for measuring the ability of the model to adapt to unseen accents using the existing CommonVoice corpus. We also propose an accent-agnostic approach that extends the model-agnostic meta-learning (MAML) algorithm for fast adaptation to unseen accents. Our approach significantly outperforms joint training in both zero-shot, few-shot, and all-shot in the mixed-region and cross-region settings in terms of word error rate.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 6; 2023: 7; 2024: 2; 2025: 1; 2026: 2.

28 papers.

Sort:

By area:

  1. 2022One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesiacited by 65
  2. 2021AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarizationcited by 51
  3. 2023Prompting Multilingual Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languagescited by 50
  4. 2021Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translationcited by 29
  5. 2022Meta Learning for Natural Language Processing: A Surveycited by 26
  6. 2021Towards Lifelong Learning of End-to-end ASRcited by 20
  7. 2022Hey ASR System! Why Aren't You More Inclusive? Automatic Speech Recognition Systems' Bias and Proposed Bias Mitigation Techniques. A Literature Reviewcited by 19
  8. 2022Automatic Speech Recognition Datasets in Cantonese: A Survey and New Datasetcited by 12
  9. 2021Model Generalization on COVID-19 Fake News Detectioncited by 11
  10. 2021Supervised Contrastive Learning for Accented Speech Recognitioncited by 10
  11. 2021MetaTune: Meta-Learning Based Cost Model for Fast and Efficient Auto-tuning Frameworkscited by 9
  12. 2022Improved Meta Learning for Low Resource Speech Recognitioncited by 7
16 more
  1. 2023Accented Speech Recognition With Accent-specific Codebookscited by 6
  2. 2021Greenformers: Improving Computation and Memory Efficiency in Transformer Models via Low-Rank Approximationcited by 5
  3. 2021X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsingcited by 4
  4. 2024DENOASR: Debiasing ASRs through Selective Denoisingcited by 3
  5. 2023Mitigating Catastrophic Forgetting for Few-Shot Spoken Word Classification Through Meta-Learningcited by 2
  6. 2023Writer adaptation for offline text recognition: An exploration of neural network-based methodscited by 2
  7. 2021Accented Speech Recognition Inspired by Human Perceptioncited by 1
  8. 2022Towards Better Meta-Initialization with Task Augmentation for Kindergarten-aged Speech Recognitioncited by 1
  9. 2023Cross-Lingual Cross-Age Group Adaptation for Low-Resource Elderly Speech Emotion Recognitioncited by 1
  10. 2023PhasePerturbation: Speech Data Augmentation via Phase Perturbation for Automatic Speech Recognitioncited by 1
  11. 2024Improving Self-supervised Pre-training using Accent-Specific Codebookscited by 1
  12. 2021Taming the Beast: Learning to Control Neural Conversational Modelscited by 0
  13. 2023A meta learning scheme for fast accent domain expansion in Mandarin speech recognitioncited by 0
  14. 2025Comparative Study of Pre-Trained BERT and Large Language Models for Code-Mixed Named Entity Recognitioncited by 0
  15. 2026Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech Recognitioncited by 0
  16. 2026Development and multi-center evaluation of domain-adapted speech recognition for human-AI teaming in real-world gastrointestinal endoscopycited by 0