Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling

• URL: http://arxiv.org/abs/2604.23586v1
• Date: Sun, 26 Apr 2026 07:48:47 GMT
• Title: Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling
• Abstract summary: We propose Talker-T2AV, an autoregressive diffusion framework where high-level cross-modal modeling occurs in a shared backbone.<n>A shared autoregressive language model jointly reasons over audio and video in a unified patch-level token space.<n> Experiments on talking portrait benchmarks show Talker-T2AV outperforms dual-branch baselines in lip-sync accuracy, video quality, and audio quality.
• Score: 59.97930201616015
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Joint audio-video generation models have shown that unified generation yields stronger cross-modal coherence than cascaded approaches. However, existing models couple modalities throughout denoising via pervasive attention, treating high-level semantics and low-level details in a fully entangled manner. This is suboptimal for talking head synthesis: while audio and facial motion are semantically correlated, their low-level realizations (acoustic signals and visual textures) follow distinct rendering processes. Enforcing joint modeling across all levels causes unnecessary entanglement and reduces efficiency. We propose Talker-T2AV, an autoregressive diffusion framework where high-level cross-modal modeling occurs in a shared backbone, while low-level refinement uses modality-specific decoders. A shared autoregressive language model jointly reasons over audio and video in a unified patch-level token space. Two lightweight diffusion transformer heads decode the hidden states into frame-level audio and video latents. Experiments on talking portrait benchmarks show Talker-T2AV outperforms dual-branch baselines in lip-sync accuracy, video quality, and audio quality, achieving stronger cross-modal consistency than cascaded pipelines.

Related papers

• OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation [73.57253966578186]
  We present OmniVAE, a jointly trained audio-video VAE that learns fine-grained semantic alignment between audio and video latent representations.<n>Experiments show that both objectives consistently improve the learnability of the latent spaces.
  arXiv  Detail & Related papers  (2026-07-26T21:51:28Z)
• LTX-2: Efficient Joint Audio-Visual Foundation Model [3.1804093402153506]
  LTX-2 is an open-source model capable of generating temporally synchronized audiovisual content.<n>We employ a multilingual text encoder for broader prompt understanding.<n>LTX-2 produces rich, coherent audio tracks that follow the characters, environment, style, and emotion of each scene.
  arXiv  Detail & Related papers  (2026-01-06T18:24:41Z)
• Omni2Sound: Towards Unified Video-Text-to-Audio Generation [56.11583645408007]
  Training a unified model integrating video-to-audio (V2A), text-to-audio (T2A) and joint video-text-to-audio (VT2A) generation offers significant application flexibility.<n>SoundAtlas is a large-scale dataset (470k pairs) that significantly outperforms existing benchmarks and even human experts in quality.<n>We propose Omni2Sound, a unified VT2A diffusion model supporting flexible input modalities.
  arXiv  Detail & Related papers  (2026-01-06T05:49:41Z)
• StableDub: Taming Diffusion Prior for Generalized and Efficient Visual Dubbing [63.72095377128904]
  The visual dubbing task aims to generate mouth movements synchronized with the driving audio.<n>Audio-only driving paradigms inadequately capture speaker-specific lip habits.<n>Blind-inpainting approaches produce visual artifacts when handling obstructions.
  arXiv  Detail & Related papers  (2025-09-26T05:23:31Z)
• Landmark-guided Diffusion Model for High-fidelity and Temporally Coherent Talking Head Generation [22.159117464397806]
  We introduce a two-stage diffusion-based model for talking head generation. The first stage involves generating synchronized facial landmarks based on the given speech. In the second stage, these generated landmarks serve as a condition in the denoising process, aiming to optimize mouth jitter issues and generate high-fidelity, well-synchronized, and temporally coherent talking head videos.
  arXiv  Detail & Related papers  (2024-08-03T10:19:38Z)
• MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation [70.74377373885645]
  We propose the first joint audio-video generation framework that brings engaging watching and listening experiences simultaneously. MM-Diffusion consists of a sequential multi-modal U-Net for a joint denoising process by design. Experiments show superior results in unconditional audio-video generation, and zero-shot conditional tasks.
  arXiv  Detail & Related papers  (2022-12-19T14:11:52Z)
• FastLTS: Non-Autoregressive End-to-End Unconstrained Lip-to-Speech Synthesis [77.06890315052563]
  We propose FastLTS, a non-autoregressive end-to-end model which can directly synthesize high-quality speech audios from unconstrained talking videos with low latency. Experiments show that our model achieves $19.76times$ speedup for audio generation compared with the current autoregressive model on input sequences of 3 seconds.
  arXiv  Detail & Related papers  (2022-07-08T10:10:39Z)

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.