English

Controllable Accent Normalization via Discrete Diffusion

Audio and Speech Processing 2026-03-17 v1 Artificial Intelligence Sound

Abstract

Existing accent normalization methods do not typically offer control over accent strength, yet many applications-such as language learning and dubbing-require tunable accent retention. We propose DLM-AN, a controllable accent normalization system built on masked discrete diffusion over self-supervised speech tokens. A Common Token Predictor identifies source tokens that likely encode native pronunciation; these tokens are selectively reused to initialize the reverse diffusion process. This provides a simple yet effective mechanism for controlling accent strength: reusing more tokens preserves more of the original accent. DLM-AN further incorporates a flow-matching Duration Ratio Predictor that automatically adjusts the total duration to better match the native rhythm. Experiments on multi-accent English data show that DLM-AN achieves the lowest word error rate among all compared systems while delivering competitive accent reduction and smooth, interpretable accent strength control.

Keywords

Cite

@article{arxiv.2603.14275,
  title  = {Controllable Accent Normalization via Discrete Diffusion},
  author = {Qibing Bai and Yuhan Du and Tom Ko and Shuai Wang and Yannan Wang and Haizhou Li},
  journal= {arXiv preprint arXiv:2603.14275},
  year   = {2026}
}

Comments

Submitted for review to Interspeech 2026

R2 v1 2026-07-01T11:20:34.992Z