# Accent-Robust Automatic Speech Recognition Using Supervised and Unsupervised Wav2vec Embeddings

arXiv: https://arxiv.org/abs/2110.03520 · HTML: https://mlsanity.com/paper/2110.03520/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2021.

## Built on by (most cited first, 13 of 13)

- [AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR](https://mlsanity.com/paper/2310.00274/) (2023)
- [Accented Speech Recognition With Accent-specific Codebooks](https://mlsanity.com/paper/2310.15970/) (2023)
- [AccentFold: A Journey through African Accents for Zero-Shot ASR Adaptation to Target Accents](https://mlsanity.com/paper/2402.01152/) (2024)
- [Adapting Automatic Speech Recognition for Accented Air Traffic Control Communications](https://mlsanity.com/paper/2502.20311/) (2025)
- [Identifying and typifying demographic unfairness in phoneme-level embeddings of self-supervised speech recognition models](https://mlsanity.com/paper/2604.22631/) (2026)
- [Pushing the performances of ASR models on English and Spanish accents](https://mlsanity.com/paper/2212.12048/) (2022)
- [Synthetic Cross-accent Data Augmentation for Automatic Speech Recognition](https://mlsanity.com/paper/2303.00802/) (2023)
- [Unsupervised Out-of-Distribution Dialect Detection with Mahalanobis Distance](https://mlsanity.com/paper/2308.04886/) (2023)
- [Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech Recognition](https://mlsanity.com/paper/2602.01967/) (2026)
- [Where Do Self-Supervised Speech Models Become Unfair?](https://mlsanity.com/paper/2604.18249/) (2026)
- [Visualizations of Complex Sequences of Family-Infant Vocalizations Using Bag-of-Audio-Words Approach Based on Wav2vec 2.0 Features](https://mlsanity.com/paper/2203.15183/) (2022)
- [Efficient infusion of self-supervised representations in Automatic Speech Recognition](https://mlsanity.com/paper/2404.12628/) (2024)
- [Revisiting Accent Classification with DistilHuBERT: Speaker-Disjoint Evaluation and Cross-Corpus Generalization](https://mlsanity.com/paper/2610.13440/) (2026)

## Abstract (arXiv)

Speech recognition models often obtain degraded performance when tested on speech with unseen accents. Domain-adversarial training (DAT) and multi-task learning (MTL) are two common approaches for building accent-robust ASR models. ASR models using accent embeddings is another approach for improving robustness to accents. In this study, we perform systematic comparisons of DAT and MTL approaches using a large volume of English accent corpus (4000 hours of US English speech and 1244 hours of 20 non-US-English accents speech). We explore embeddings trained under supervised and unsupervised settings: a separate embedding matrix trained using accent labels, and embeddings extracted from a fine-tuned wav2vec model. We find that our DAT model trained with supervised embeddings achieves the best performance overall and consistently provides benefits for all testing datasets, and our MTL model trained with wav2vec embeddings are helpful learning accent-invariant features and improving novel/unseen accents. We also illustrate that wav2vec embeddings have more advantages for building accent-robust ASR when no accent labels are available for training supervised embeddings.