LatentSync: Audio Conditioned Latent Diffusion Models for Lip Sync

• URL: http://arxiv.org/abs/2412.09262v1
• Date: Thu, 12 Dec 2024 13:20:52 GMT
• Title: LatentSync: Audio Conditioned Latent Diffusion Models for Lip Sync
• Authors: Chunyu Li, Chao Zhang, Weikai Xu, Jinghui Xie, Weiguo Feng, Bingyue Peng, Weiwei Xing,
• Abstract summary: LatentSync is an end-to-end lip sync framework based on audio conditioned latent diffusion models without any intermediate motion representation.<n>Our framework can leverage the powerful capabilities of Stable Diffusion to model complex audio-visual correlations.<n>We significantly improve the accuracy of SyncNet from 91% to 94% on the HDTF test set.
• Score: 13.480681141520638
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present LatentSync, an end-to-end lip sync framework based on audio conditioned latent diffusion models without any intermediate motion representation, diverging from previous diffusion-based lip sync methods based on pixel space diffusion or two-stage generation. Our framework can leverage the powerful capabilities of Stable Diffusion to directly model complex audio-visual correlations. Additionally, we found that the diffusion-based lip sync methods exhibit inferior temporal consistency due to the inconsistency in the diffusion process across different frames. We propose Temporal REPresentation Alignment (TREPA) to enhance temporal consistency while preserving lip-sync accuracy. TREPA uses temporal representations extracted by large-scale self-supervised video models to align the generated frames with the ground truth frames. Furthermore, we observe the commonly encountered SyncNet convergence issue and conduct comprehensive empirical studies, identifying key factors affecting SyncNet convergence in terms of model architecture, training hyperparameters, and data preprocessing methods. We significantly improve the accuracy of SyncNet from 91% to 94% on the HDTF test set. Since we did not change the overall training framework of SyncNet, our experience can also be applied to other lip sync and audio-driven portrait animation methods that utilize SyncNet. Based on the above innovations, our method outperforms state-of-the-art lip sync methods across various metrics on the HDTF and VoxCeleb2 datasets.

Related papers

• MirrorMe: Towards Realtime and High Fidelity Audio-Driven Halfbody Animation [21.216297567167036]
  MirrorMe is a real-time, controllable framework built on the LTX video model.<n>MirrorMe compresses video spatially and temporally for efficient latent space denoising.<n> experiments on the EMTD Benchmark demonstrate MirrorMe's state-of-the-art performance in fidelity, lip-sync accuracy, and temporal stability.
  arXiv  Detail & Related papers  (2025-06-27T09:57:23Z)
• AsynFusion: Towards Asynchronous Latent Consistency Models for Decoupled Whole-Body Audio-Driven Avatars [65.53676584955686]
  Whole-body audio-driven avatar pose and expression generation is a critical task for creating lifelike digital humans.<n>We propose AsynFusion, a novel framework that leverages diffusion transformers to achieve cohesive expression and gesture synthesis.<n>AsynFusion achieves state-of-the-art performance in generating real-time, synchronized whole-body animations.
  arXiv  Detail & Related papers  (2025-05-21T03:28:53Z)
• DeepSound-V1: Start to Think Step-by-Step in the Audio Generation from Videos [4.452513686760606]
  We propose a framework for audio generation from videos, leveraging the internal chain-of-thought (CoT) of a multi-modal large language model (MLLM) A corresponding multi-modal reasoning dataset is constructed to facilitate the learning of initial reasoning in audio generation. In experiments, we demonstrate the effectiveness of the proposed framework in reducing misalignment (voice-over) in generated audio.
  arXiv  Detail & Related papers  (2025-03-28T07:56:19Z)
• SyncDiff: Diffusion-based Talking Head Synthesis with Bottlenecked Temporal Visual Prior for Improved Synchronization [32.220603714163026]
  Talking head synthesis, also known as speech-to-lip synthesis, reconstructs the facial motions that align with the given audio tracks. Recent studies demonstrate that GAN-based and diffusion-based models achieve state-of-the-art (SOTA) performance on this task. We propose SyncDiff, a simple yet effective approach to improve diffusion-based models using a temporal pose frame with information bottleneck and facial-informative audio features extracted from AVHuBERT.
  arXiv  Detail & Related papers  (2025-03-17T16:58:53Z)
• SwapTalk: Audio-Driven Talking Face Generation with One-Shot Customization in Latent Space [13.59798532129008]
  We propose an innovative unified framework, SwapTalk, which accomplishes both face swapping and lip synchronization tasks in the same latent space. We introduce a novel identity consistency metric to more comprehensively assess the identity consistency over time series in generated facial videos. Experimental results on the HDTF demonstrate that our method significantly surpasses existing techniques in video quality, lip synchronization accuracy, face swapping fidelity, and identity consistency.
  arXiv  Detail & Related papers  (2024-05-09T09:22:09Z)
• Audio-Visual Speech Representation Expert for Enhanced Talking Face Video Generation and Evaluation [51.92522679353731]
  We propose utilizing an audio-visual speech representation expert (AV-HuBERT) for calculating lip synchronization loss during training. We introduce three novel lip synchronization evaluation metrics, aiming to provide a comprehensive assessment of lip synchronization performance.
  arXiv  Detail & Related papers  (2024-05-07T13:55:50Z)
• Synchformer: Efficient Synchronization from Sparse Cues [100.89656994681934]
  Our contributions include a novel audio-visual synchronization model, and training that decouples extraction from synchronization modelling. This approach achieves state-of-the-art performance in both dense and sparse settings. We also extend synchronization model training to AudioSet a million-scale 'in-the-wild' dataset, investigate evidence attribution techniques for interpretability, and explore a new capability for synchronization models: audio-visual synchronizability.
  arXiv  Detail & Related papers  (2024-01-29T18:59:55Z)
• Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution [65.91317390645163]
  Upscale-A-Video is a text-guided latent diffusion framework for video upscaling. It ensures temporal coherence through two key mechanisms: locally, it integrates temporal layers into U-Net and VAE-Decoder, maintaining consistency within short sequences. It also offers greater flexibility by allowing text prompts to guide texture creation and adjustable noise levels to balance restoration and generation.
  arXiv  Detail & Related papers  (2023-12-11T18:54:52Z)
• 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)
• Audio-driven Talking Face Generation with Stabilized Synchronization Loss [60.01529422759644]
  Talking face generation aims to create realistic videos with accurate lip synchronization and high visual quality. We first tackle the lip leaking problem by introducing a silent-lip generator, which changes the lips of the identity reference to alleviate leakage. Experiments show that our model outperforms state-of-the-art methods in both visual quality and lip synchronization.
  arXiv  Detail & Related papers  (2023-07-18T15:50:04Z)
• VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation [88.49030739715701]
  This work presents a decomposed diffusion process via resolving the per-frame noise into a base noise that is shared among all frames and a residual noise that varies along the time axis. Experiments on various datasets confirm that our approach, termed as VideoFusion, surpasses both GAN-based and diffusion-based alternatives in high-quality video generation.
  arXiv  Detail & Related papers  (2023-03-15T02:16:39Z)
• On the Audio-visual Synchronization for Lip-to-Speech Synthesis [22.407313748927393]
  We show that the commonly used audio-visual datasets, such as GRID, TCD-TIMIT, and Lip2Wav, can have data asynchrony issues. Training lip-to-speech with such datasets may further cause the model asynchrony issue -- that is, the generated speech and the input video are out of sync.
  arXiv  Detail & Related papers  (2023-03-01T13:35:35Z)
• End to End Lip Synchronization with a Temporal AutoEncoder [95.94432031144716]
  We study the problem of syncing the lip movement in a video with the audio stream. Our solution finds an optimal alignment using a dual-domain recurrent neural network. As an application, we demonstrate our ability to robustly align text-to-speech generated audio with an existing video stream.
  arXiv  Detail & Related papers  (2022-03-30T12:00:18Z)
• Audio-Visual Synchronisation in the wild [149.84890978170174]
  We identify and curate a test set with high audio-visual correlation, namely VGG-Sound Sync. We compare a number of transformer-based architectural variants specifically designed to model audio and visual signals of arbitrary length. We set the first benchmark for general audio-visual synchronisation with over 160 diverse classes in the new VGG-Sound Sync video dataset.
  arXiv  Detail & Related papers  (2021-12-08T17:50:26Z)
• Looking into Your Speech: Learning Cross-modal Affinity for Audio-visual Speech Separation [73.1652905564163]
  We address the problem of separating individual speech signals from videos using audio-visual neural processing. Most conventional approaches utilize frame-wise matching criteria to extract shared information between co-occurring audio and video. We propose a cross-modal affinity network (CaffNet) that learns global correspondence as well as locally-varying affinities between audio and visual streams.
  arXiv  Detail & Related papers  (2021-03-25T15:39:12Z)

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.