DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation

• URL: http://arxiv.org/abs/2510.12210v2
• Date: Wed, 15 Oct 2025 23:15:11 GMT
• Title: DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation
• Abstract summary: DISTAR is a zero-shot text-to-speech framework that operates entirely in a discrete residual vector quantization code space.<n>Experiments and ablations demonstrate that DISTAR surpasses state-of-the-art zero-shot TTS systems in robustness, naturalness, and speaker/style consistency.
• Score: 30.150846119894577
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent attempts to interleave autoregressive (AR) sketchers with diffusion-based refiners over continuous speech representations have shown promise, but they remain brittle under distribution shift and offer limited levers for controllability. We introduce DISTAR, a zero-shot text-to-speech framework that operates entirely in a discrete residual vector quantization (RVQ) code space and tightly couples an AR language model with a masked diffusion model, without forced alignment or a duration predictor. Concretely, DISTAR drafts block-level RVQ tokens with an AR language model and then performs parallel masked-diffusion infilling conditioned on the draft to complete the next block, yielding long-form synthesis with blockwise parallelism while mitigating classic AR exposure bias. The discrete code space affords explicit control at inference: DISTAR produces high-quality audio under both greedy and sample-based decoding using classifier-free guidance, supports trade-offs between robustness and diversity, and enables variable bit-rate and controllable computation via RVQ layer pruning at test time. Extensive experiments and ablations demonstrate that DISTAR surpasses state-of-the-art zero-shot TTS systems in robustness, naturalness, and speaker/style consistency, while maintaining rich output diversity. Audio samples are provided on https://anonymous.4open.science/w/DiSTAR_demo.

Related papers

• AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling [60.04959047453115]
  AURORA-LM is a continuous-latent language model that separates the construction of a decodable text representation from the modeling of its distribution.<n>AURORA-LM achieves the strongest performance among evaluated continuous and diffusion-based language models on OpenWebText free generation and XSum summarization.
  arXiv  Detail & Related papers  (2026-08-03T17:59:50Z)
• DSL-LLaDA: Scaling Continuous Denoising to 8B Masked Diffusion LMs [29.561307941602482]
  We show that a pretrained masked DLM can be lightly adapted to support continuous embedding-space denoising.<n>The adapted model supports continuous inference that evolves all positions jointly in embedding space.<n> DSL-LLaDA-SDE achieves the best ROUGE-1 on all four benchmarks.
  arXiv  Detail & Related papers  (2026-05-31T05:27:01Z)
• Chatterbox-Flash: Prior-Calibrated Block Diffusion for Streaming Zero-Shot TTS [2.6809014985508584]
  We present Chatterbox-Flash, a zero-shot text-to-speech model obtained by fine-tuning a pretrained autoregressive TTS decoder into a block-diffusion decoder.<n>We find that naively transferring mainstream block-diffusion decoding to discrete speech tokens degrades quality.<n>We introduce two inference-time techniques: prior-calibrated scoring, which subtracts the block-level marginal token distribution, and an early-decoding schedule, which adaptively terminates iteration based on calibrated confidence.
  arXiv  Detail & Related papers  (2026-05-29T02:25:02Z)
• CRoCoDiL: Continuous and Robust Conditioned Diffusion for Language [21.764828393078886]
  Masked Diffusion Models (MDMs) provide an efficient non-causal alternative to autoregressive generation.<n>We address these limitations by shifting the diffusion process into a continuous sentence-level semantic space.
  arXiv  Detail & Related papers  (2026-03-02T12:50:55Z)
• Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling [87.34677262370924]
  Standard discrete diffusion models treat all unobserved states identically by mapping them to an absorbing [MASK] token.<n>This creates an 'information void' where semantic information that could be inferred from unmasked tokens is lost between denoising steps.<n>We introduce Continuously Augmented Discrete Diffusion, a framework that augments the discrete state space with a paired diffusion in a continuous latent space.
  arXiv  Detail & Related papers  (2025-10-01T18:00:56Z)
• DiFlow-TTS: Discrete Flow Matching with Factorized Speech Tokens for Low-Latency Zero-Shot Text-To-Speech [8.537791317883576]
  Zero-shot Text-to-Speech (TTS) aims to synthesize high-quality speech that mimics the voice of an unseen speaker using only a short reference sample.<n>Recent approaches based on language models, diffusion, and flow matching have shown promising results in zero-shot TTS, but still suffer from slow inference and repetition artifacts.<n>We introduce DiFlow-TTS, which is the first model to explore purely Discrete Flow Matching for speech synthesis.
  arXiv  Detail & Related papers  (2025-09-11T17:16:52Z)
• Blockwise SFT for Diffusion Language Models: Reconciling Bidirectional Attention and Autoregressive Decoding [60.06816407728172]
  Discrete diffusion language models have shown strong potential for text generation.<n>Standard supervised fine-tuning misaligns with semi-autoregressive inference.<n>We propose Blockwise SFT, which partitions responses into fixed-size blocks.
  arXiv  Detail & Related papers  (2025-08-27T02:49:33Z)
• Next Tokens Denoising for Speech Synthesis [51.320443764269726]
  Dragon-FM is a novel text-to-speech (TTS) design that unifies AR and flow-matching.<n>It processes 48 kHz audio tokens in chunks at a compact rate of 12.5 tokens per second.<n>Experiments on podcast datasets demonstrate its capability to efficiently generate high-quality zero-shot podcasts.
  arXiv  Detail & Related papers  (2025-07-30T15:03:36Z)
• Pseudo-Autoregressive Neural Codec Language Models for Efficient Zero-Shot Text-to-Speech Synthesis [64.12708207721276]
  We introduce a novel pseudo-autoregressive (PAR) language modeling approach that unifies AR and NAR modeling.<n>Building on PAR, we propose PALLE, a two-stage TTS system that leverages PAR for initial generation followed by NAR refinement.<n>Experiments demonstrate that PALLE, trained on LibriTTS, outperforms state-of-the-art systems trained on large-scale data.
  arXiv  Detail & Related papers  (2025-04-14T16:03:21Z)
• ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation [21.335983674309475]
  Diffusion models suffer from slow inference due to an excessive number of queries to the underlying denoising network per generation. We introduce ConsistencyTTA, a framework requiring only a single non-autoregressive network query. We achieve so by proposing "CFG-aware latent consistency model," which adapts consistency generation into a latent space.
  arXiv  Detail & Related papers  (2023-09-19T16:36:33Z)
• Streaming End-to-End ASR based on Blockwise Non-Autoregressive Models [57.20432226304683]
  Non-autoregressive (NAR) modeling has gained more and more attention in speech processing. We propose a novel end-to-end streaming NAR speech recognition system. We show that the proposed method improves online ASR recognition in low latency conditions.
  arXiv  Detail & Related papers  (2021-07-20T11:42:26Z)
• Any-to-Many Voice Conversion with Location-Relative Sequence-to-Sequence Modeling [61.351967629600594]
  This paper proposes an any-to-many location-relative, sequence-to-sequence (seq2seq), non-parallel voice conversion approach. In this approach, we combine a bottle-neck feature extractor (BNE) with a seq2seq synthesis module. Objective and subjective evaluations show that the proposed any-to-many approach has superior voice conversion performance in terms of both naturalness and speaker similarity.
  arXiv  Detail & Related papers  (2020-09-06T13:01:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.