SayAnything: Audio-Driven Lip Synchronization with Conditional Video Diffusion

• URL: http://arxiv.org/abs/2502.11515v1
• Date: Mon, 17 Feb 2025 07:29:36 GMT
• Title: SayAnything: Audio-Driven Lip Synchronization with Conditional Video Diffusion
• Authors: Junxian Ma, Shiwen Wang, Jian Yang, Junyi Hu, Jian Liang, Guosheng Lin, Jingbo chen, Kai Li, Yu Meng,
• Abstract summary: SayAnything is a conditional video diffusion framework that directly synthesizes lip movements from audio input. Our novel design effectively balances different condition signals in the latent space, enabling precise control over appearance, motion, and region-specific generation.
• Score: 78.77211425667542
• License:
• Abstract: Recent advances in diffusion models have led to significant progress in audio-driven lip synchronization. However, existing methods typically rely on constrained audio-visual alignment priors or multi-stage learning of intermediate representations to force lip motion synthesis. This leads to complex training pipelines and limited motion naturalness. In this paper, we present SayAnything, a conditional video diffusion framework that directly synthesizes lip movements from audio input while preserving speaker identity. Specifically, we propose three specialized modules including identity preservation module, audio guidance module, and editing control module. Our novel design effectively balances different condition signals in the latent space, enabling precise control over appearance, motion, and region-specific generation without requiring additional supervision signals or intermediate representations. Extensive experiments demonstrate that SayAnything generates highly realistic videos with improved lip-teeth coherence, enabling unseen characters to say anything, while effectively generalizing to animated characters.

Related papers

• MEMO: Memory-Guided Diffusion for Expressive Talking Video Generation [55.95148886437854]
  Memory-guided EMOtion-aware diffusion (MEMO) is an end-to-end audio-driven portrait animation approach to generate talking videos. MEMO generates more realistic talking videos across diverse image and audio types, outperforming state-of-the-art methods in overall quality, audio-lip synchronization, identity consistency, and expression-emotion alignment.
  arXiv  Detail & Related papers  (2024-12-05T18:57:26Z)
• S^3D-NeRF: Single-Shot Speech-Driven Neural Radiance Field for High Fidelity Talking Head Synthesis [14.437741528053504]
  We design a Single-Shot Speech-Driven Radiance Field (S3D-NeRF) method to tackle the three difficulties: learning a representative appearance feature for each identity, modeling motion of different face regions with audio, and keeping the temporal consistency of the lip area. Our S3D-NeRF surpasses previous arts on both video fidelity and audio-lip synchronization.
  arXiv  Detail & Related papers  (2024-08-18T03:59:57Z)
• High-fidelity and Lip-synced Talking Face Synthesis via Landmark-based Diffusion Model [89.29655924125461]
  We propose a novel landmark-based diffusion model for talking face generation. We first establish the less ambiguous mapping from audio to landmark motion of lip and jaw. Then, we introduce an innovative conditioning module called TalkFormer to align the synthesized motion with the motion represented by landmarks.
  arXiv  Detail & Related papers  (2024-08-10T02:58:28Z)
• Style-Preserving Lip Sync via Audio-Aware Style Reference [88.02195932723744]
  Individuals exhibit distinct lip shapes when speaking the same utterance, attributed to the unique speaking styles of individuals. We develop an advanced Transformer-based model adept at predicting lip motion corresponding to the input audio, augmented by the style information aggregated through cross-attention layers from style reference video. Experiments validate the efficacy of the proposed approach in achieving precise lip sync, preserving speaking styles, and generating high-fidelity, realistic talking face videos.
  arXiv  Detail & Related papers  (2024-08-10T02:46:11Z)
• OpFlowTalker: Realistic and Natural Talking Face Generation via Optical Flow Guidance [13.050998759819933]
  "OpFlowTalker" is a novel approach that utilizes predicted optical flow changes from audio inputs rather than direct image predictions. It smooths image transitions and aligns changes with semantic content. We also developed an optical flow synchronization module that regulates both full-face and lip movements.
  arXiv  Detail & Related papers  (2024-05-23T15:42:34Z)
• Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors [18.904856604045264]
  We introduce a simple and novel framework for one-shot audio-driven talking head generation. We probabilistically sample all the holistic lip-irrelevant facial motions to semantically match the input audio. Thanks to the probabilistic nature of the diffusion prior, one big advantage of our framework is it can synthesize diverse facial motion sequences.
  arXiv  Detail & Related papers  (2022-12-07T17:55:41Z)
• Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild [44.92322575562816]
  We propose a VAE-GAN architecture that learns to associate the lip and speech sequences amidst the variations. Our generator learns to synthesize speech in any voice for the lip sequences of any person. We conduct numerous ablation studies to analyze the effect of different modules of our architecture.
  arXiv  Detail & Related papers  (2022-09-01T17:50:29Z)
• StyleTalker: One-shot Style-based Audio-driven Talking Head Video Generation [47.06075725469252]
  StyleTalker is an audio-driven talking head generation model. It can synthesize a video of a talking person from a single reference image. Our model is able to synthesize talking head videos with impressive perceptual quality.
  arXiv  Detail & Related papers  (2022-08-23T12:49:01Z)
• SimulLR: Simultaneous Lip Reading Transducer with Attention-Guided Adaptive Memory [61.44510300515693]
  We study the task of simultaneous lip and devise SimulLR, a simultaneous lip Reading transducer with attention-guided adaptive memory. The experiments show that the SimulLR achieves the translation speedup 9.10 times times compared with the state-of-the-art non-simultaneous methods.
  arXiv  Detail & Related papers  (2021-08-31T05:54:16Z)

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.