UniTalking: A Unified Audio-Video Framework for Talking Portrait Generation

• URL: http://arxiv.org/abs/2603.01418v1
• Date: Mon, 02 Mar 2026 03:46:53 GMT
• Title: UniTalking: A Unified Audio-Video Framework for Talking Portrait Generation
• Authors: Hebeizi Li, Zihao Liang, Benyuan Sun, Zihao Yin, Xiao Sha, Chenliang Wang, Yi Yang,
• Abstract summary: We introduce UniTalking, a unified, end-to-end diffusion framework for generating high-fidelity speech and lip-synchronized video.<n>By leveraging powerful priors from a pre-trained video generation model, our framework ensures state-of-the-art visual fidelity while enabling efficient training.
• Score: 9.86219488808079
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While state-of-the-art audio-video generation models like Veo3 and Sora2 demonstrate remarkable capabilities, their closed-source nature makes their architectures and training paradigms inaccessible. To bridge this gap in accessibility and performance, we introduce UniTalking, a unified, end-to-end diffusion framework for generating high-fidelity speech and lip-synchronized video. At its core, our framework employs Multi-Modal Transformer Blocks to explicitly model the fine-grained temporal correspondence between audio and video latent tokens via a shared self-attention mechanism. By leveraging powerful priors from a pre-trained video generation model, our framework ensures state-of-the-art visual fidelity while enabling efficient training. Furthermore, UniTalking incorporates a personalized voice cloning capability, allowing the generation of speech in a target style from a brief audio reference. Qualitative and quantitative results demonstrate that our method produces highly realistic talking portraits, achieving superior performance over existing open-source approaches in lip-sync accuracy, audio naturalness, and overall perceptual quality.

Related papers

• JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation [112.614973927778]
  Joint audio-video generation (JAVG) produces synchronized and semantically aligned sound and vision from textual descriptions.<n>This paper presents JavisDiT++, a framework for unified modeling and optimization of JAVG.<n>Our model achieves state-of-the-art performance merely with around 1M public training entries.
  arXiv  Detail & Related papers  (2026-02-22T12:44:28Z)
• AlignDiT: Multimodal Aligned Diffusion Transformer for Synchronized Speech Generation [65.06374691172061]
  multimodal-to-speech task has gained increasing attention due to its wide range of applications, such as film production, dubbing, and virtual avatars.<n>Existing methods still suffer from limitations in speech intelligibility, audio-video synchronization, speech naturalness, and voice similarity to the reference speaker.<n>We propose AlignDiT, a multimodal Aligned Diffusion Transformer that generates accurate, synchronized, and natural-sounding speech from aligned multimodal inputs.
  arXiv  Detail & Related papers  (2025-04-29T10:56:24Z)
• OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking [22.337906095079198]
  We present OmniTalker, a unified framework that jointly generates synchronized talking audio-video content from input text.<n>Our framework adopts a dual-branch diffusion transformer (DiT) architecture, with one branch dedicated to audio generation and the other to video synthesis.
  arXiv  Detail & Related papers  (2025-04-03T09:48:13Z)
• Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction [9.101978573666546]
  Baichuan-Audio is an end-to-end audio large language model that seamlessly integrates audio understanding and generation.<n>It features a text-guided aligned speech generation mechanism, enabling real-time speech interaction with both comprehension and generation capabilities.
  arXiv  Detail & Related papers  (2025-02-24T15:16:34Z)
• PortraitTalk: Towards Customizable One-Shot Audio-to-Talking Face Generation [48.94486508604052]
  We introduce a novel, customizable one-shot audio-driven talking face generation framework, named PortraitTalk.<n>Our proposed method utilizes a latent diffusion framework consisting of two main components: IdentityNet and AnimateNet.<n>Key innovation of PortraitTalk is the incorporation of text prompts through decoupled cross-attention mechanisms.
  arXiv  Detail & Related papers  (2024-12-10T18:51:31Z)
• Video-to-Audio Generation with Hidden Alignment [27.11625918406991]
  We offer insights into the video-to-audio generation paradigm, focusing on vision encoders, auxiliary embeddings, and data augmentation techniques.<n>We demonstrate our model exhibits state-of-the-art video-to-audio generation capabilities.
  arXiv  Detail & Related papers  (2024-07-10T08:40:39Z)
• Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners [69.70590867769408]
  Video and audio content creation serves as the core technique for the movie industry and professional users. Existing diffusion-based methods tackle video and audio generation separately, which hinders the technique transfer from academia to industry. In this work, we aim at filling the gap, with a carefully designed optimization-based framework for cross-visual-audio and joint-visual-audio generation.
  arXiv  Detail & Related papers  (2024-02-27T17:57:04Z)
• Improving Audio-Visual Speech Recognition by Lip-Subword Correlation Based Visual Pre-training and Cross-Modal Fusion Encoder [58.523884148942166]
  We propose two novel techniques to improve audio-visual speech recognition (AVSR) under a pre-training and fine-tuning training framework. First, we explore the correlation between lip shapes and syllable-level subword units in Mandarin to establish good frame-level syllable boundaries from lip shapes. Next, we propose an audio-guided cross-modal fusion encoder (CMFE) neural network to utilize main training parameters for multiple cross-modal attention layers.
  arXiv  Detail & Related papers  (2023-08-14T08:19:24Z)
• CLIPSonic: Text-to-Audio Synthesis with Unlabeled Videos and Pretrained Language-Vision Models [50.42886595228255]
  We propose to learn the desired text-audio correspondence by leveraging the visual modality as a bridge. We train a conditional diffusion model to generate the audio track of a video, given a video frame encoded by a pretrained contrastive language-image pretraining model.
  arXiv  Detail & Related papers  (2023-06-16T05:42:01Z)

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.