Controllable Accent Normalization via Discrete Diffusion

arXiv:2603.14275 · eess.AS, cs.AI, cs.SD · Submitted 2026-03-15 · Read on arXiv

eess.AS, cs.AI, cs.SD

Submitted: 2026-03-15

Updated: 2026-10-02

Code: https://github.com/P1ping/DLM-AN

Project page: https://p1ping.github.io/dlman-demo

Terminology

• Diffusion Process — 1× in this paper · explained in 2 episodes

Sources

• Improving Accent Conversion with Reference Encoder and End-To-End Text-To-Speech
• Large Language Diffusion Models
• LLaMA-Omni: Seamless Speech Interaction with Large Language Models
• Discrete Diffusion in Large Language and Multimodal Models: A Survey
• Corrective Diffusion Language Models
• Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference
• LLaDA2.1: Speeding Up Text Diffusion via Token Editing
• HiFTNet: A Fast High-Quality Neural Vocoder with Harmonic-plus-Noise Filter and Inverse Short Time Fourier Transform
• BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
• CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models
• Don't Settle Too Early: Self-Reflective Remasking for Diffusion Language Models

Related papers

• Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs
• X-VC: Zero-shot Streaming Voice Conversion in Codec Space
• Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers
• VM-ARRAYDPS: Virtual Microphone Augmented Diffusion Posterior Sampling for Unsupervised Blind Speech Separation
• Conditional Flow Matching for Visually-Guided Acoustic Highlighting
• Anonymization, Not Elimination: Utility-Preserved Speech Anonymization