# Domain Adversarial Training for Accented Speech Recognition

arXiv: https://arxiv.org/abs/1806.02786 · HTML: https://mlsanity.com/paper/1806.02786/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2018.

## Built on by (most cited first, 30 of 40)

- [AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR](https://mlsanity.com/paper/2310.00274/) (2023)
- [Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition](https://mlsanity.com/paper/2203.14222/) (2022)
- [Improving Distortion Robustness of Self-supervised Speech Processing Tasks with Domain Adaptation](https://mlsanity.com/paper/2203.16104/) (2022)
- [A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairness](https://mlsanity.com/paper/2212.09006/) (2022)
- [Accented Speech Recognition: A Survey](https://mlsanity.com/paper/2104.10747/) (2021)
- [Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models](https://mlsanity.com/paper/2404.13752/) (2024)
- [Supervised Contrastive Learning for Accented Speech Recognition](https://mlsanity.com/paper/2107.00921/) (2021)
- [Differentiable Allophone Graphs for Language-Universal Speech Recognition](https://mlsanity.com/paper/2107.11628/) (2021)
- [Speech Technology for Everyone: Automatic Speech Recognition for Non-Native English with Transfer Learning](https://mlsanity.com/paper/2110.00678/) (2021)
- [Boosting Cross-Domain Speech Recognition with Self-Supervision](https://mlsanity.com/paper/2206.09783/) (2022)
- [Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matching](https://mlsanity.com/paper/2104.07491/) (2021)
- [Understanding and Improvement of Adversarial Training for Network Embedding from an Optimization Perspective](https://mlsanity.com/paper/2105.08007/) (2021)
- [Sample-Efficient Unsupervised Domain Adaptation of Speech Recognition Systems A case study for Modern Greek](https://mlsanity.com/paper/2301.00304/) (2022)
- [AfriNames: Most ASR models "butcher" African Names](https://mlsanity.com/paper/2306.00253/) (2023)
- [Advancing Test-Time Adaptation in Wild Acoustic Test Settings](https://mlsanity.com/paper/2310.09505/) (2023)
- [Enhancing and Adversarial: Improve ASR with Speaker Labels](https://mlsanity.com/paper/2211.06369/) (2022)
- [Accented Speech Recognition With Accent-specific Codebooks](https://mlsanity.com/paper/2310.15970/) (2023)
- [Unsupervised domain adaptation for speech recognition with unsupervised error correction](https://mlsanity.com/paper/2209.12043/) (2022)
- [Exploration of Adapter for Noise Robust Automatic Speech Recognition](https://mlsanity.com/paper/2402.18275/) (2024)
- [Improving Automatic Speech Recognition for Non-Native English with Transfer Learning and Language Model Decoding](https://mlsanity.com/paper/2202.05209/) (2022)
- [Adapting Automatic Speech Recognition for Accented Air Traffic Control Communications](https://mlsanity.com/paper/2502.20311/) (2025)
- [Error-driven Fixed-Budget ASR Personalization for Accented Speakers](https://mlsanity.com/paper/2103.03142/) (2021)
- [An Overview of Indian Spoken Language Recognition from Machine Learning Perspective](https://mlsanity.com/paper/2212.03812/) (2022)
- [Qifusion-Net: Layer-adapted Stream/Non-stream Model for End-to-End Multi-Accent Speech Recognition](https://mlsanity.com/paper/2407.03026/) (2024)
- [Effects of Speaker Count, Duration, and Accent Diversity on Zero-Shot Accent Robustness in Low-Resource ASR](https://mlsanity.com/paper/2506.04364/) (2025)
- [Identifying and typifying demographic unfairness in phoneme-level embeddings of self-supervised speech recognition models](https://mlsanity.com/paper/2604.22631/) (2026)
- [Accented Speech Recognition Inspired by Human Perception](https://mlsanity.com/paper/2104.04627/) (2021)
- [Improving Adversarial Robustness for Free with Snapshot Ensemble](https://mlsanity.com/paper/2110.03124/) (2021)
- [MADI: Inter-domain Matching and Intra-domain Discrimination for Cross-domain Speech Recognition](https://mlsanity.com/paper/2302.11224/) (2023)
- [Synthetic Cross-accent Data Augmentation for Automatic Speech Recognition](https://mlsanity.com/paper/2303.00802/) (2023)

## Abstract (arXiv)

In this paper, we propose a domain adversarial training (DAT) algorithm to alleviate the accented speech recognition problem. In order to reduce the mismatch between labeled source domain data ("standard" accent) and unlabeled target domain data (with heavy accents), we augment the learning objective for a Kaldi TDNN network with a domain adversarial training (DAT) objective to encourage the model to learn accent-invariant features. In experiments with three Mandarin accents, we show that DAT yields up to 7.45% relative character error rate reduction when we do not have transcriptions of the accented speech, compared with the baseline trained on standard accent data only. We also find a benefit from DAT when used in combination with training from automatic transcriptions on the accented data. Furthermore, we find that DAT is superior to multi-task learning for accented speech recognition.