mlsanityData to 7 Oct 2026

Supervised Contrastive Learning for Accented Speech Recognition

arXiv 2107.00921 ↗First posted 2 Jul 2021cs.SD cs.LG eess.AScited by 10

Not on the map. Why?

Abstract (arXiv)

Neural network based speech recognition systems suffer from performance degradation due to accented speech, especially unfamiliar accents. In this paper, we study the supervised contrastive learning framework for accented speech recognition. To build different views (similar "positive" data samples) for contrastive learning, three data augmentation techniques including noise injection, spectrogram augmentation and TTS-same-sentence generation are further investigated. From the experiments on the Common Voice dataset, we have shown that contrastive learning helps to build data-augmentation invariant and pronunciation invariant representations, which significantly outperforms traditional joint training methods in both zero-shot and full-shot settings. Experiments show that contrastive learning can improve accuracy by 3.66% (zero-shot) and 3.78% (full-shot) on average, comparing to the joint training method.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 14 of its 20 references that are in the map. First posted on arXiv 2 Jul 2021.

Builds on

14 of 20 references.

References · 14

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2020Supervised Contrastive Learningcited by 2,803
  5. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  6. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  7. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  8. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
  9. 2019A Theoretical Analysis of Contrastive Unsupervised Representation Learningcited by 530
  10. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 308
  11. 2020Data Augmenting Contrastive Learning of Speech Representations in the Time Domaincited by 63
  12. 2018Domain Adversarial Training for Accented Speech Recognitioncited by 40
2 more
  1. 2020Learning Fast Adaptation on Cross-Accented Speech Recognitioncited by 28
  2. 2018Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognitioncited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 2; 2023: 2; 2024: 1; 2025: 3; 2026: 1.

10 papers.

  1. 2022Superficial White Matter Analysis: An Efficient Point-cloud-based Deep Learning Framework with Supervised Contrastive Learning for Consistent Tractography Parcellation across Populations and dMRI Acquisitionscited by 19
  2. 2023ContraBAR: Contrastive Bayes-Adaptive Deep RLcited by 9
  3. 2024A Contrastive Learning Approach to Mitigate Bias in Speech Modelscited by 9
  4. 2023Accented Speech Recognition With Accent-specific Codebookscited by 6
  5. 2022Robust Vocal Quality Feature Embeddings for Dysphonic Voice Detectioncited by 3
  6. 2025Adapting Automatic Speech Recognition for Accented Air Traffic Control Communicationscited by 3
  7. 2025DyPCL: Dynamic Phoneme-level Contrastive Learning for Dysarthric Speech Recognitioncited by 2
  8. 2025Accent-Invariant Automatic Speech Recognition via Saliency-Driven Spectrogram Maskingcited by 2
  9. 2021SCaLa: Supervised Contrastive Learning for End-to-End Speech Recognitioncited by 1
  10. 2026Contrastive Regularization for Accent-Robust ASRcited by 0