mlsanityData to 14 Oct 2026

Controllable Accent Normalization via Discrete Diffusion

arXiv 2603.14275 ↗First posted 15 Mar 2026eess.AS cs.AI cs.SDcited by 0

On the map: Diffusion models → Audio, speech and music

Abstract (arXiv)

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. The implementation is available at https://github.com/P1ping/DLM-AN

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 53 of its 71 references that are in the map. First posted on arXiv 15 Mar 2026.

Builds on

53 of 71 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models13 Dec
  2. 2023Matcha-TTS: A fast TTS architecture with conditional flow matching6 Sep

Other references · 51

  1. 2022Scalable Diffusion Models with Transformerscited by 6,054
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  3. 2022Classifier-Free Diffusion Guidancecited by 5,847
  4. 2022Flow Matching for Generative Modelingcited by 5,702
  5. 2017Neural Discrete Representation Learningcited by 4,712
  6. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  7. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  8. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  9. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,719
  10. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
  11. 2022MaskGIT: Masked Generative Image Transformercited by 1,099
  12. 2025Large Language Diffusion Modelscited by 912
38 more
  1. 2024Simple and Effective Masked Diffusion Language Modelscited by 848
  2. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distributioncited by 745
  3. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 574
  4. 2021Generative Spoken Language Modeling from Raw Audiocited by 340
  5. 2024Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generationcited by 204
  6. 2025Remasking Discrete Diffusion Models with Inference-Time Scalingcited by 189
  7. 2025Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inferencecited by 178
  8. 2024LLaMA-Omni: Seamless Speech Interaction with Large Language Modelscited by 173
  9. 2023Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervisioncited by 169
  10. 2024MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformercited by 161
  11. 2021Direct speech-to-speech translation with discrete unitscited by 149
  12. 2025Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmaskingcited by 131
  13. 2023LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpuscited by 101
  14. 2024Self-Supervised Speech Representations are More Phonetic than Semanticcited by 71
  15. 2025Discrete Diffusion in Large Language and Multimodal Models: A Surveycited by 61
  16. 2026LLaDA2.1: Speeding Up Text Diffusion via Token Editingcited by 54
  17. 2025Don't Settle Too Early: Self-Reflective Remasking for Diffusion Language Modelscited by 37
  18. 2025Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglementcited by 35
  19. 2021Textless Speech Emotion Conversion using Discrete and Decomposed Representationscited by 29
  20. 2020Any-to-One Sequence-to-Sequence Voice Conversion using Self-Supervised Discrete Speech Representationscited by 18
  21. 2022Voice-preserving Zero-shot Multiple Accent Conversioncited by 17
  22. 2025Metis: A Foundation Speech Generation Model with Masked Generative Pre-trainingcited by 12
  23. 2023HiFTNet: A Fast High-Quality Neural Vocoder with Harmonic-plus-Noise Filter and Inverse Short Time Fourier Transformcited by 11
  24. 2024Convert and Speak: Zero-shot Accent Conversion with Minimum Supervisioncited by 11
  25. 2025Corrective Diffusion Language Modelscited by 11
  26. 2022TTS-Guided Training for Accent Conversion Without Parallel Datacited by 9
  27. 2024High-Fidelity Neural Phonetic Posteriorgramscited by 9
  28. 2024DurFlex-EVC: Duration-Flexible Emotional Voice Conversion Leveraging Discrete Representations without Text Alignmentcited by 8
  29. 2024Exploring SSL Discrete Tokens for Multilingual ASRcited by 6
  30. 2020Improving Accent Conversion with Reference Encoder and End-To-End Text-To-Speechcited by 5
  31. 2024Transfer the linguistic representations from TTS to accent conversion with non-parallel datacited by 5
  32. 2024Accent conversion using discrete units with parallel data synthesized from controllable accented TTScited by 5
  33. 2024Improving Pronunciation and Accent Conversion through Knowledge Distillation And Synthetic Ground-Truth from Native TTScited by 5
  34. 2025Accent Normalization Using Self-Supervised Discrete Tokens with Non-Parallel Datacited by 4
  35. 2025Scalable Controllable Accented TTScited by 4
  36. 2024Exploring SSL Discrete Speech Features for Zipformer-based Contextual ASRcited by 2
  37. 2025FAC-FACodec: Controllable Zero-Shot Foreign Accent Conversion with Factorized Speech Codeccited by 2
  38. 2026Advanced Modeling of Interlanguage Speech Intelligibility Benefit with L1-L2 Multi-Task Learning Using Differentiable K-Means for Accent-Robust Discrete Token-Based ASRcited by 2

50 most cited of 51 All 51 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026TokAN: Accent Normalization Using Self-Supervised Speech Tokens
  2. 2026Multi Codec Discrete Diffusion Model for Text Guided Speech Inpainting and Editing
  3. 2025Language translation, and change of accent for speech-to-speech task using diffusion model
  4. 2025CLARITY: Contextual Linguistic Adaptation and Accent Retrieval for Dual-Bias Mitigation in Text-to-Speech Generation
  5. 2026Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech Recognition
  6. 2026DiTAR+: Dual Optimization for Robust Autoregressive Diffusion Speech Synthesis
  7. 2025Audio Palette: A Diffusion Transformer with Multi-Signal Conditioning for Controllable Foley Synthesis
  8. 2024Improving Robustness of Diffusion-Based Zero-Shot Speech Synthesis via Stable Formant Generation