mlsanityData to 14 Oct 2026

DLLM-TTS: Block Discrete Diffusion Language Model for Text-to-Speech Synthesis

arXiv 2608.00011 ↗First posted 19 Jun 2026cs.CL cs.AIcited by 0

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

Abstract (arXiv)

Current text-to-speech systems face a trade-off: autoregres- sive codec language models produce highly intelligible speech but require large-scale models and training data and decode tokens sequentially, while non-autoregressive approaches im- prove speed at the cost of linguistic accuracy. We present DLLM-TTS, a framework that formulates TTS as conditional block discrete diffusion over X-Codec2 neural audio codec to- kens. The model decomposes sequences into blocks and applies masked diffusion within each block while processing blocks se- quentially, learning both local acoustic coherence and global text-speech alignment. During inference, parallel token pre- diction within blocks enables efficient generation with a real- time factor (RTF) of 0.15. A 0.6B-parameter model trained on 20K hours achieves competitive performance on the Seed- TTS-eval benchmark, demonstrating that block discrete diffu- sion language models enable practical and data-efficient speech synthesis with parallel generation.

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 28 of its 29 references that are in the map. First posted on arXiv 19 Jun 2026.

Builds on

28 of 29 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training23 May
  2. 2025MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis26 Feb
  3. 2025DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation6 Feb
  4. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching9 Oct
  5. 2024NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models5 Mar
  6. 2023StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models13 Jun

Other references · 22

  1. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  2. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  3. 2024Qwen2 Technical Reportcited by 2,120
  4. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
  5. 2025Large Language Diffusion Modelscited by 912
  6. 2024Simple and Effective Masked Diffusion Language Modelscited by 848
  7. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 752
  8. 2025Qwen2.5-Omni Technical Reportcited by 736
  9. 2022High Fidelity Neural Audio Compressioncited by 687
  10. 2025Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Modelscited by 409
  11. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 379
  12. 2024CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokenscited by 334
10 more
  1. 2024Seed-TTS: A Family of High-Quality Versatile Speech Generation Modelscited by 300
  2. 2024Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generationcited by 204
  3. 2024MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformercited by 161
  4. 2024VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizerscited by 122
  5. 2023SoundStorm: Efficient Parallel Audio Generationcited by 114
  6. 2025IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speechcited by 90
  7. 2024Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Modelcited by 72
  8. 2025Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesiscited by 70
  9. 2024Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesiscited by 48
  10. 2026CodecMOS-Accent: A MOS Benchmark of Resynthesized and TTS Speech from Neural Codecs Across English Accentscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026DELTA-TTS: Adapting Autoregressive Model into Diffusion Language Model for Text-to-Speech
  2. 2023High-Fidelity Speech Synthesis with Minimal Supervision: All Using Diffusion Models
  3. 2025DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation
  4. 2025From Text to Talk: Audio-Language Model Needs Non-Autoregressive Joint Training
  5. 2025Fast-dLLM v2: Efficient Block-Diffusion LLM
  6. 2024Autoregressive Diffusion Transformer for Text-to-Speech Synthesis
  7. 2025Discrete Diffusion for Generative Modeling of Text-Aligned Speech Tokens
  8. 2026LLaDA-TTS: Unifying Speech Synthesis and Zero-Shot Editing via Masked Diffusion Modeling