mlsanityData to 14 Oct 2026

Accented Speech Recognition: A Survey

arXiv 2104.10747 ↗First posted 21 Apr 2021cs.CL cs.SD eess.AScited by 12

Not on the map. Why?

Abstract (arXiv)

Automatic Speech Recognition (ASR) systems generalize poorly on accented speech. The phonetic and linguistic variability of accents present hard challenges for ASR systems today in both data collection and modeling strategies. The resulting bias in ASR performance across accents comes at a cost to both users and providers of ASR. We present a survey of current promising approaches to accented speech recognition and highlight the key challenges in the space. Approaches mostly focus on single model generalization and accent feature engineering. Among the challenges, lack of a standard benchmark makes research and comparison especially difficult.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 13 of its 40 references that are in the map. First posted on arXiv 21 Apr 2021.

Builds on

13 of 40 references.

References · 13

  1. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  2. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
  3. 2018Progress & Compress: A scalable framework for continual learningcited by 520
  4. 2016Achieving Human Parity in Conversational Speech Recognitioncited by 63
  5. 2019Personalizing ASR for Dysarthric and Accented Speech with Limited Datacited by 45
  6. 2018Domain Adversarial Training for Accented Speech Recognitioncited by 40
  7. 2017Multi-Dialect Speech Recognition With A Single Sequence-To-Sequence Modelcited by 37
  8. 2018Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognitioncited by 14
  9. 2019AIPNet: Generative Adversarial Pre-training of Accent-invariant Networks for End-to-end Speech Recognitioncited by 11
  10. 2020Multi-Accent Adaptation based on Gate Mechanismcited by 9
  11. 2020Black-box Adaptation of ASR for Accented Speechcited by 8
  12. 2019Leveraging native language information for improved accented speech recognitioncited by 7
1 more
  1. 2019Domain Expansion in DNN-based Acoustic Models for Robust Speech Recognitioncited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 2; 2023: 4; 2024: 2; 2025: 2; 2026: 1.

12 papers.

  1. 2023CommonAccent: Exploring Large Acoustic Pretrained Models for Accent Classification Based on Common Voicecited by 20
  2. 2025Afrispeech-Dialog: A Benchmark Dataset for Spontaneous English Conversations in Healthcare and Beyondcited by 11
  3. 2023AfriNames: Most ASR models "butcher" African Namescited by 7
  4. 2022Global Performance Disparities Between English-Language Accents in Automatic Speech Recognitioncited by 6
  5. 2023A Deep Dive into the Disparity of Word Error Rates Across Thousands of NPTEL MOOC Videoscited by 5
  6. 2023Some voices are too common: Building fair speech recognition systems using the Common Voice datasetcited by 3
  7. 2024AccentFold: A Journey through African Accents for Zero-Shot ASR Adaptation to Target Accentscited by 3
  8. 2022Measuring the Impact of Individual Domain Factors in Self-Supervised Pre-Trainingcited by 2
  9. 2025Effects of Speaker Count, Duration, and Accent Diversity on Zero-Shot Accent Robustness in Low-Resource ASRcited by 2
  10. 2021Bridging the Gap: Using Deep Acoustic Representations to Learn Grounded Language from Percepts and Raw Speechcited by 1
  11. 2024Nollywood: Let's Go to the Movies!cited by 0
  12. 2026On-Policy Self-Distillation for Multi-Dialect ASR: Mastering Dialects, Retaining Mandarincited by 0