# Accent Normalization Using Self-Supervised Discrete Tokens with Non-Parallel Data

arXiv: https://arxiv.org/abs/2507.17735 · HTML: https://mlsanity.com/paper/2507.17735/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jul 2025.

## Built on by (most cited first, 4 of 4)

- [CosyAccent: Duration-Controllable Accent Normalization Using Source-Synthesis Training Data](https://mlsanity.com/paper/2602.19166/) (2026)
- [Controllable Accent Normalization via Discrete Diffusion](https://mlsanity.com/paper/2603.14275/) (2026)
- [Synthetic Audio Generation Framework for Air Traffic Control Speech Recognition](https://mlsanity.com/paper/2606.21340/) (2026)
- [TokAN: Accent Normalization Using Self-Supervised Speech Tokens](https://mlsanity.com/paper/2607.03928/) (2026)

## Abstract (arXiv)

Accent normalization converts foreign-accented speech into native-like speech while preserving speaker identity. We propose a novel pipeline using self-supervised discrete tokens and non-parallel training data. The system extracts tokens from source speech, converts them through a dedicated model, and synthesizes the output using flow matching. Our method demonstrates superior performance over a frame-to-frame baseline in naturalness, accentedness reduction, and timbre preservation across multiple English accents. Through token-level phonetic analysis, we validate the effectiveness of our token-based approach. We also develop two duration preservation methods, suitable for applications such as dubbing.