mlsanityData to 14 Oct 2026

Mask, Sample, Revise: A Revisable CTMC Inference Stack for Guided Discrete Flow Matching Text-to-Speech

arXiv 2606.13989 ↗First posted 12 Jun 2026cs.SD cs.AIcited by 0

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

Abstract (arXiv)

Recent alignment-free non-autoregressive (NAR) text-to-speech (TTS) models formulate synthesis as a conditional infilling task, bypassing explicit duration predictors and external aligners. When speech is represented with neural codec tokens, the infilling problem becomes discrete, making Discrete Flow Matching (DFM), a Continuous-Time Markov Chain (CTMC) framework for discrete generation, a natural fit. However, inference-time control for stable low-step conditional infilling remains underexplored. We propose Mask, Sample, Revise, an inference-time CTMC stack for alignment-free DFM-TTS. The stack combines predictor-free guidance to strengthen text conditioning, prompt-matched conditional coupling to align the probability path with the acoustic prompt, and SC-ReMask, a schedule-constrained remasking mechanism that introduces token-to-mask transitions so de-masking decisions can be revised. These components require no post-hoc fine-tuning and operate in a single tau-leaping sampler. Controlled ablations show that this stack improves intelligibility and robustness in the low-NFE prompted setting, outperforming unguided and guidance-only samplers with substantially more steps.

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 31 of its 37 references that are in the map. First posted on arXiv 12 Jun 2026.

Builds on

31 of 37 references.

Closest ancestors · 8

Same direction, newest first

  1. 2026Kinetic-Optimal Scheduling with Moment Correction for Metric-Induced Discrete Flow Matching in Zero-Shot Text-to-Speech10 May
  2. 2025Discrete Diffusion for Generative Modeling of Text-Aligned Speech Tokens24 Sep
  3. 2025Investigating Stochastic Methods for Prosody Modeling in Speech Synthesis30 Jun
  4. 2024CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models13 Dec
  5. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching9 Oct
  6. 2024DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors17 Jun
  7. 2024NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models5 Mar
  8. 2023Matcha-TTS: A fast TTS architecture with conditional flow matching6 Sep

Other references · 23

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2022Scalable Diffusion Models with Transformerscited by 6,054
  3. 2022Flow Matching for Generative Modelingcited by 5,702
  4. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  5. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  6. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
  7. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 752
  8. 2022UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022cited by 390
  9. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 379
  10. 2024Discrete Flow Matchingcited by 317
  11. 2024Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generationcited by 204
  12. 2025Remasking Discrete Diffusion Models with Inference-Time Scalingcited by 189
11 more
  1. 2024MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformercited by 161
  2. 2024E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTScited by 152
  3. 2024Unlocking Guidance for Discrete State-Space Diffusion and Flow Modelscited by 129
  4. 2025Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokenscited by 113
  5. 2025Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesiscited by 70
  6. 2024Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspectivecited by 57
  7. 2025Recent Advances in Discrete Speech Tokens: A Reviewcited by 43
  8. 2025FireRedTTS-2: Towards Long Conversational Speech Generation for Podcast and Chatbotcited by 35
  9. 2025TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modelingcited by 13
  10. 2024VoxSim: A perceptual voice similarity datasetcited by 10
  11. 2025Finite Scalar Quantization Enables Redundant and Transmission-Robust Neural Audio Compression at Low Bit-ratescited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026DSFlow: Dual Supervision and Step-Aware Architecture for One-Step Flow Matching Speech Synthesis
  2. 2026ARCHI-TTS: A flow-matching-based Text-to-Speech Model with Self-supervised Semantic Aligner and Accelerated Inference
  3. 2026DLLM-TTS: Block Discrete Diffusion Language Model for Text-to-Speech Synthesis
  4. 2026ReaFlow-TTS: Realization-Conditioned Flow Matching for High-Quality and Controllable Speech Synthesis
  5. 2025Towards Flow-Matching-based TTS without Classifier-Free Guidance
  6. 2026Enhancing Flow Matching with A Unified Guidance Framework for Efficient and Robust Speech Synthesis
  7. 2026Multi Codec Discrete Diffusion Model for Text Guided Speech Inpainting and Editing
  8. 2026Transcript-Free Flow-Matching Text-to-Speech via Speech Feature Conditioning