Pith. sign in

REVIEW 11 cited by

Autoregressive Diffusion Transformer for Text-to-Speech Synthesis

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.05551 v1 pith:ZEXA2VSG submitted 2024-06-08 eess.AS cs.AIcs.CLcs.LGcs.SD

Autoregressive Diffusion Transformer for Text-to-Speech Synthesis

classification eess.AS cs.AIcs.CLcs.LGcs.SD
keywords audiomodelssteparditcontinuousdiffusionsequencesspeech
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Audio language models have recently emerged as a promising approach for various audio generation tasks, relying on audio tokenizers to encode waveforms into sequences of discrete symbols. Audio tokenization often poses a necessary compromise between code bitrate and reconstruction accuracy. When dealing with low-bitrate audio codes, language models are constrained to process only a subset of the information embedded in the audio, which in turn restricts their generative capabilities. To circumvent these issues, we propose encoding audio as vector sequences in continuous space $\mathbb R^d$ and autoregressively generating these sequences using a decoder-only diffusion transformer (ARDiT). Our findings indicate that ARDiT excels in zero-shot text-to-speech and exhibits performance that compares to or even surpasses that of state-of-the-art models. High-bitrate continuous speech representation enables almost flawless reconstruction, allowing our model to achieve nearly perfect speech editing. Our experiments reveal that employing Integral Kullback-Leibler (IKL) divergence for distillation at each autoregressive step significantly boosts the perceived quality of the samples. Simultaneously, it condenses the iterative sampling process of the diffusion model into a single step. Furthermore, ARDiT can be trained to predict several continuous vectors in one step, significantly reducing latency during sampling. Impressively, one of our models can generate $170$ ms of $24$ kHz speech per evaluation step with minimal degradation in performance. Audio samples are available at http://ardit-tts.github.io/ .

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. HoliDubber: Holistic Video Dubbing for Complex Acoustic Scenes via Text-Guided Audio Synthesis

    eess.AS 2026-06 unverdicted novelty 7.0

    HoliDubber introduces a patch-based autoregressive diffusion transformer for joint text-guided synthesis of speech and ambient audio in video dubbing, with a new benchmark showing outperformance over prior speech-only...

  2. V.O.I.C.E (Voice, Ownership, Identity, Control, Expression): Risk Taxonomy of Synthetic Voice Generation From Empirical Data

    cs.CR 2026-04 unverdicted novelty 7.0

    V.O.I.C.E is a new taxonomy that organizes synthetic voice risks into five categories and shows how they interact with exposure, visibility, and legal context using empirical incident data.

  3. ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusion Models

    cs.SD 2026-07 conditional novelty 6.5

    Hierarchical multi-prompt representation generation plus generalized flow matching yields high-quality single-stage waveform diffusion from 12.5 Hz latents and efficient LDM TTS.

  4. Stable Autoregressive Speech Generation with Low-Frame-Rate High-Dimensional Continuous Tokens

    eess.AS 2026-07 conditional novelty 6.0

    Autoregressive TTS from 8-Hz, 768-dimensional continuous tokens works when the tokenizer shapes its latent space with a low-dimensional core and an energy hierarchy, and the generator separates guidance into local, se...

  5. dots.tts Technical Report

    cs.SD 2026-06 unverdicted novelty 6.0

    dots.tts reports SOTA benchmark results on Seed-TTS-Eval and other tests via continuous latent-space autoregressive modeling with three listed innovations and code release.

  6. Taming Audio VAEs via Target-KL Regularization

    cs.SD 2026-05 unverdicted novelty 6.0

    The paper introduces target-KL regularization to train audio VAEs at specific bitrates, enabling rate-distortion curves and comparison to discrete audio codecs for improved text-to-sound generation.

  7. INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling

    cs.CV 2026-04 unverdicted novelty 6.0

    INSPATIO-WORLD is a real-time framework for high-fidelity 4D scene generation and navigation from monocular videos via STAR architecture with implicit caching, explicit geometric constraints, and distribution-matching...

  8. Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion

    cs.CV 2025-06 unverdicted novelty 6.0

    Self Forcing trains autoregressive video diffusion models by performing autoregressive rollout with KV caching during training to close the exposure bias gap, using a holistic video-level loss and few-step diffusion f...

  9. Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey

    cs.CV 2026-04 accept novelty 5.0

    MLLM-enabled video translation is usefully framed as three roles—Semantic Reasoner, Expressive Performer, and Visual Synthesizer—rather than a cascade of ASR, MT, TTS, and lip-sync.

  10. F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching

    eess.AS 2024-10 unverdicted novelty 5.0

    F5-TTS generates natural speech from text via flow matching on DiT with simple text padding, ConvNeXt refinement, and sway sampling, trained on 100K hours multilingual data.

  11. Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey

    cs.CV 2026-04 unverdicted novelty 4.0

    The paper offers the first focused review of MLLM-based video translation organized by a three-role taxonomy of Semantic Reasoner, Expressive Performer, and Visual Synthesizer, plus open challenges.