SyncLipMAE: Contrastive Masked Pretraining for Audio-Visual Talking-Face Representation

• URL: http://arxiv.org/abs/2510.10069v1
• Date: Sat, 11 Oct 2025 07:12:44 GMT
• Title: SyncLipMAE: Contrastive Masked Pretraining for Audio-Visual Talking-Face Representation
• Abstract summary: We introduce SyncLipMAE, a self-supervised pretraining framework for talking-face video.<n>It learns synchronization-aware and transferable facial dynamics from unlabeled audio-visual streams.
• Score: 18.719993633325522
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce SyncLipMAE, a self-supervised pretraining framework for talking-face video that learns synchronization-aware and transferable facial dynamics from unlabeled audio-visual streams. Our approach couples masked visual modeling with cross-modal contrastive alignment and employs three per-frame prompt tokens that explicitly encode the essential factors of a talking-face frame - identity, vocal motion (speech-synchronized facial dynamics), and ambient motion (audio-agnostic movements such as blinks and head pose). The contrastive objective uses time-aligned vocal-motion and audio tokens as positives and misaligned pairs as negatives, driving both modalities into a shared embedding space and yielding token-level audio-visual stream synchronization. After pretraining, the aligned audio tokens together with the visual prompt tokens (identity, vocal motion, ambient motion) form a unified interface for four disparate downstream settings: (i) audio-visual stream synchronization; (ii) facial emotion and head/face action recognition; (iii) visual speech recognition; and (iv) visual dubbing, for which we enable indistinguishable audio- or video-driven control within a single model. Across four task families that require distinct capabilities, SyncLipMAE achieves state-of-the-art results, underscoring the effectiveness of synchronization-aware, factorized self-supervised pretraining.

Related papers

• FacePlex: Full-Duplex Joint Speech-Facial Motion Generation for Conversational Avatars [21.261785501498196]
  FacePlex is a unified streaming framework with two key components.<n>We show that FacePlex enables full-face fidelity speech-facial motion generation under online streaming constraints.
  arXiv  Detail & Related papers  (2026-06-29T11:22:50Z)
• PTalker: Personalized Speech-Driven 3D Talking Head Animation via Style Disentanglement and Modality Alignment [19.347893658924367]
  "PTalker" is a novel framework for personalized 3D talking head animation.<n>It preserves speaking style through style disentanglement from audio and facial motion sequences.<n>It enhances lip-synchronization accuracy through a three-level alignment mechanism between audio and mesh modalities.
  arXiv  Detail & Related papers  (2025-12-27T14:14:14Z)
• StreamingTalker: Audio-driven 3D Facial Animation with Autoregressive Diffusion Model [73.30619724574642]
  Speech-driven 3D facial animation aims to generate realistic and synchronized facial motions driven by speech inputs.<n>Recent methods have employed audio-conditioned diffusion models for 3D facial animation.<n>We propose a novel autoregressive diffusion model that processes audio in a streaming manner.
  arXiv  Detail & Related papers  (2025-11-18T07:55:16Z)
• Text2Lip: Progressive Lip-Synced Talking Face Generation from Text via Viseme-Guided Rendering [53.2204901422631]
  Text2Lip is a viseme-centric framework that constructs an interpretable phonetic-visual bridge.<n>We show that Text2Lip outperforms existing approaches in semantic fidelity, visual realism, and modality robustness.
  arXiv  Detail & Related papers  (2025-08-04T12:50:22Z)
• Face2VoiceSync: Lightweight Face-Voice Consistency for Text-Driven Talking Face Generation [14.036076647627553]
  Given a face image and text to speak, we generate talking face animation and its corresponding speeches.<n>We propose a novel framework, Face2VoiceSync, with several novel contributions.<n> Experiments show Face2VoiceSync achieves both visual and audio state-of-the-art performances on a single 40GB GPU.
  arXiv  Detail & Related papers  (2025-07-25T12:49:06Z)
• 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.<n>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)
• LinguaLinker: Audio-Driven Portraits Animation with Implicit Facial Control Enhancement [8.973545189395953]
  This study focuses on the creation of visually compelling, time-synchronized animations through diffusion-based techniques. We process audio features separately and derive the corresponding control gates, which implicitly govern the movements in the mouth, eyes, and head, irrespective of the portrait's origin. The significant improvements in the fidelity of animated portraits, the accuracy of lip-syncing, and the appropriate motion variations achieved by our method render it a versatile tool for animating any portrait in any language.
  arXiv  Detail & Related papers  (2024-07-26T08:30:06Z)
• Speech2UnifiedExpressions: Synchronous Synthesis of Co-Speech Affective Face and Body Expressions from Affordable Inputs [67.27840327499625]
  We present a multimodal learning-based method to simultaneously synthesize co-speech facial expressions and upper-body gestures for digital characters. Our approach learns from sparse face landmarks and upper-body joints, estimated directly from video data, to generate plausible emotive character motions.
  arXiv  Detail & Related papers  (2024-06-26T04:53:11Z)
• SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization [29.53063463863921]
  We present SyncVSR, an end-to-end learning framework that leverages quantized audio for frame-level crossmodal supervision. By integrating a projection layer that synchronizes visual representation with acoustic data, our encoder learns to generate discrete audio tokens from a video sequence in a non-autoregressive manner. Our empirical evaluations show that it not only achieves state-of-the-art results but also reduces data usage by up to ninefold.
  arXiv  Detail & Related papers  (2024-06-18T03:14:22Z)
• FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio [45.71036380866305]
  We abstract the process of people hearing speech, extracting meaningful cues, and creating dynamically audio-consistent talking faces from a single audio. Specifically, it involves two critical challenges: one is to effectively decouple identity, content, and emotion from entangled audio, and the other is to maintain intra-video diversity and inter-video consistency. We introduce the Controllable Coherent Frame generation, which involves the flexible integration of three trainable adapters with frozen Latent Diffusion Models.
  arXiv  Detail & Related papers  (2024-03-04T09:59:48Z)
• Cooperative Dual Attention for Audio-Visual Speech Enhancement with Facial Cues [80.53407593586411]
  We focus on leveraging facial cues beyond the lip region for robust Audio-Visual Speech Enhancement (AVSE) We propose a Dual Attention Cooperative Framework, DualAVSE, to ignore speech-unrelated information, capture speech-related information with facial cues, and dynamically integrate it with the audio signal for AVSE.
  arXiv  Detail & Related papers  (2023-11-24T04:30:31Z)
• VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency [111.55430893354769]
  Given a video, the goal is to extract the speech associated with a face in spite of simultaneous background sounds and/or other human speakers. Our approach jointly learns audio-visual speech separation and cross-modal speaker embeddings from unlabeled video. It yields state-of-the-art results on five benchmark datasets for audio-visual speech separation and enhancement.
  arXiv  Detail & Related papers  (2021-01-08T18:25:24Z)

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.