# Region-Aware Masking for Accent-Robust Cross-Lingual Text-to-Speech

arXiv: https://arxiv.org/abs/2610.07524 · HTML: https://mlsanity.com/paper/2610.07524/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Placed in Vocoders and speech synthesis, one of 11 directions in Speech and audio language models.
- Builds on 27 of its 29 references that are in the map.
- First posted on arXiv 5 Oct 2026.

## Placed in

- Speech and audio language models / [Vocoders and speech synthesis](https://mlsanity.com/speech/vocoders-and-speech-synthesis/)

## Builds on (most cited first, 27 of 27)

- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [Improving and generalizing flow-based generative models with minibatch optimal transport](https://mlsanity.com/paper/2302.00482/) (2023)
- [UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022](https://mlsanity.com/paper/2204.02152/) (2022)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale](https://mlsanity.com/paper/2306.15687/) (2023)
- [YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone](https://mlsanity.com/paper/2112.02418/) (2021)
- [XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model](https://mlsanity.com/paper/2406.04904/) (2024)
- [Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling](https://mlsanity.com/paper/2303.03926/) (2023)
- [E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS](https://mlsanity.com/paper/2406.18009/) (2024)
- [Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning](https://mlsanity.com/paper/1907.04448/) (2019)
- [SpeechPainter: Text-conditioned Speech Inpainting](https://mlsanity.com/paper/2202.07273/) (2022)
- [AccentBox: Towards High-Fidelity Zero-Shot Accent Generation](https://mlsanity.com/paper/2409.09098/) (2024)
- [DSE-TTS: Dual Speaker Embedding for Cross-Lingual Text-to-Speech](https://mlsanity.com/paper/2306.14145/) (2023)
- [Cross-Lingual F5-TTS: Towards Language-Agnostic Voice Cloning and Speech Synthesis](https://mlsanity.com/paper/2509.14579/) (2025)
- [Accent Normalization Using Self-Supervised Discrete Tokens with Non-Parallel Data](https://mlsanity.com/paper/2507.17735/) (2025)
- [Activation Steering for Accent-Neutralized Zero-Shot Text-To-Speech](https://mlsanity.com/paper/2603.05977/) (2026)
- [X-Voice: Enabling Everyone to Speak 30 Languages via Zero-Shot Cross-Lingual Voice Cloning](https://mlsanity.com/paper/2605.05611/) (2026)
- [PFluxTTS: Hybrid Flow-Matching TTS with Robust Cross-Lingual Voice Cloning and Inference-Time Model Fusion](https://mlsanity.com/paper/2602.04160/) (2026)
- [CrossAccent-TTS: Cross-Lingual Accent-Intensity Controllable Text-to-Speech via Disentangled Speaker and Accent Representations](https://mlsanity.com/paper/2606.25403/) (2026)
- [Data-augmented cross-lingual synthesis in a teacher-student framework](https://mlsanity.com/paper/2204.00061/) (2022)
- [ERNIE-SAT: Speech and Text Joint Pretraining for Cross-Lingual Multi-Speaker Text-to-Speech](https://mlsanity.com/paper/2211.03545/) (2022)
- [CrossSpeech++: Cross-lingual Speech Synthesis with Decoupled Language and Speaker Generation](https://mlsanity.com/paper/2412.20048/) (2024)

## Abstract (arXiv)

Accent leakage remains a critical challenge in cross-lingual zero-shot text-to-speech (TTS), where models inadvertently transfer both the speaker's timbre and source-language accent into the target-language output. In mask-reconstruction TTS this is amplified by a train--inference mismatch: training reconstructs from same-language context, while inference conditions on cross-lingual context. We close this gap by concatenating utterances from two languages and placing the reconstruction mask relative to the language boundary, so training presents the cross-lingual prompting pattern the model encounters at inference. This requires no language IDs, accent labels, parallel same-speaker recordings, or architectural changes---only the mask geometry differs. In a listening study with native speakers, region-aware masking reduces perceived accent from 4.3 to 0.5 on a 0-5 scale against the unadapted baseline, and by 18-51% in seen regimes and 35-55% on unseen source languages against bilingual adaptation alone, with no measurable loss in intelligibility or naturalness. Comparing mask geometries shows that placement, not the amount masked, governs the balance between accent suppression and speaker preservation: masks confined to the reconstruction region suppress accent most but retain the reference speaker least reliably, whereas two-region masking achieves both. Mask geometry is thus a simple, effective lever for accent robustness.