AI killed the video star. Audio-driven diffusion model for expressive talking head generation

• URL: http://arxiv.org/abs/2511.22488v1
• Date: Thu, 27 Nov 2025 14:24:47 GMT
• Title: AI killed the video star. Audio-driven diffusion model for expressive talking head generation
• Authors: Baptiste Chopin, Tashvik Dhamija, Pranav Balaji, Yaohui Wang, Antitza Dantcheva,
• Abstract summary: Dimitra++ is a framework for audio-driven talking head generation.<n>We propose a conditional Motion Diffusion Transformer (cMDT) to model facial motion sequences.<n>The cMDT is conditioned on two inputs: a reference facial image, which determines appearance, as well as an audio sequence, which drives the motion.
• Score: 11.938371312877715
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We propose Dimitra++, a novel framework for audio-driven talking head generation, streamlined to learn lip motion, facial expression, as well as head pose motion. Specifically, we propose a conditional Motion Diffusion Transformer (cMDT) to model facial motion sequences, employing a 3D representation. The cMDT is conditioned on two inputs: a reference facial image, which determines appearance, as well as an audio sequence, which drives the motion. Quantitative and qualitative experiments, as well as a user study on two widely employed datasets, i.e., VoxCeleb2 and CelebV-HQ, suggest that Dimitra++ is able to outperform existing approaches in generating realistic talking heads imparting lip motion, facial expression, and head pose.

Related papers

• Supervising 3D Talking Head Avatars with Analysis-by-Audio-Synthesis [43.748379918040854]
  Speech-driven 3D head avatars must articulate their lips in accordance with speech.<n>The key problem is that deterministic models produce high-quality lip-sync but without rich expressions.<n>We propose THUNDER, a 3D talking head avatar framework that introduces a novel supervision mechanism via differentiable sound production.
  arXiv  Detail & Related papers  (2025-04-18T00:24:52Z)
• Dimitra: Audio-driven Diffusion model for Expressive Talking Head Generation [11.341242901688489]
  Dimitra is a framework for audio-driven talking head generation.<n>We train a conditional Motion Diffusion Transformer (cMDT) by modeling facial motion sequences with 3D representation.<n>By extracting additional features directly from audio, Dimitra is able to increase quality and realism of generated videos.
  arXiv  Detail & Related papers  (2025-02-24T14:31:20Z)
• FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models [85.16273912625022]
  We introduce FaceTalk, a novel generative approach designed for synthesizing high-fidelity 3D motion sequences of talking human heads from audio signal. To the best of our knowledge, this is the first work to propose a generative approach for realistic and high-quality motion synthesis of human heads.
  arXiv  Detail & Related papers  (2023-12-13T19:01:07Z)
• GSmoothFace: Generalized Smooth Talking Face Generation via Fine Grained 3D Face Guidance [83.43852715997596]
  GSmoothFace is a novel two-stage generalized talking face generation model guided by a fine-grained 3d face model. It can synthesize smooth lip dynamics while preserving the speaker's identity. Both quantitative and qualitative experiments confirm the superiority of our method in terms of realism, lip synchronization, and visual quality.
  arXiv  Detail & Related papers  (2023-12-12T16:00:55Z)
• VividTalk: One-Shot Audio-Driven Talking Head Generation Based on 3D Hybrid Prior [28.737324182301652]
  We propose a two-stage generic framework that supports generating high-visual quality talking head videos. In the first stage, we map the audio to mesh by learning two motions, including non-rigid expression motion and rigid head motion. In the second stage, we proposed a dual branch motion-vae and a generator to transform the meshes into dense motion and synthesize high-quality video frame-by-frame.
  arXiv  Detail & Related papers  (2023-12-04T12:25:37Z)
• Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video [91.92782707888618]
  We present a decomposition-composition framework named Speech to Lip (Speech2Lip) that disentangles speech-sensitive and speech-insensitive motion/appearance. We show that our model can be trained by a video of just a few minutes in length and achieve state-of-the-art performance in both visual quality and speech-visual synchronization.
  arXiv  Detail & Related papers  (2023-09-09T14:52:39Z)
• Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generation [54.68893964373141]
  Talking face generation has historically struggled to produce head movements and natural facial expressions without guidance from additional reference videos. Recent developments in diffusion-based generative models allow for more realistic and stable data synthesis. We present an autoregressive diffusion model that requires only one identity image and audio sequence to generate a video of a realistic talking human head.
  arXiv  Detail & Related papers  (2023-01-06T14:16:54Z)
• Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion [34.406907667904996]
  We propose an audio-driven talking-head method to generate photo-realistic talking-head videos from a single reference image. We first design a head pose predictor by modeling rigid 6D head movements with a motion-aware recurrent neural network (RNN) Then, we develop a motion field generator to produce the dense motion fields from input audio, head poses, and a reference image.
  arXiv  Detail & Related papers  (2021-07-20T07:22:42Z)
• Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation [96.66010515343106]
  We propose a clean yet effective framework to generate pose-controllable talking faces. We operate on raw face images, using only a single photo as an identity reference. Our model has multiple advanced capabilities including extreme view robustness and talking face frontalization.
  arXiv  Detail & Related papers  (2021-04-22T15:10:26Z)
• Audio-driven Talking Face Video Generation with Learning-based Personalized Head Pose [67.31838207805573]
  We propose a deep neural network model that takes an audio signal A of a source person and a short video V of a target person as input. We outputs a synthesized high-quality talking face video with personalized head pose. Our method can generate high-quality talking face videos with more distinguishing head movement effects than state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-02-24T10:02:10Z)

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.