Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion

• URL: http://arxiv.org/abs/2312.04466v2
• Date: Mon, 1 Apr 2024 08:56:59 GMT
• Title: Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion
• Authors: Kiran Chhatre, Radek Daněček, Nikos Athanasiou, Giorgio Becherini, Christopher Peters, Michael J. Black, Timo Bolkart,
• Abstract summary: Existing methods for synthesizing 3D human gestures from speech have shown promising results. We present AMUSE, an emotional speech-driven body animation model based on latent diffusion.
• Score: 45.081371413693425
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing methods for synthesizing 3D human gestures from speech have shown promising results, but they do not explicitly model the impact of emotions on the generated gestures. Instead, these methods directly output animations from speech without control over the expressed emotion. To address this limitation, we present AMUSE, an emotional speech-driven body animation model based on latent diffusion. Our observation is that content (i.e., gestures related to speech rhythm and word utterances), emotion, and personal style are separable. To account for this, AMUSE maps the driving audio to three disentangled latent vectors: one for content, one for emotion, and one for personal style. A latent diffusion model, trained to generate gesture motion sequences, is then conditioned on these latent vectors. Once trained, AMUSE synthesizes 3D human gestures directly from speech with control over the expressed emotions and style by combining the content from the driving speech with the emotion and style of another speech sequence. Randomly sampling the noise of the diffusion model further generates variations of the gesture with the same emotional expressivity. Qualitative, quantitative, and perceptual evaluations demonstrate that AMUSE outputs realistic gesture sequences. Compared to the state of the art, the generated gestures are better synchronized with the speech content, and better represent the emotion expressed by the input speech. Our code is available at amuse.is.tue.mpg.de.

Related papers

• DEEPTalk: Dynamic Emotion Embedding for Probabilistic Speech-Driven 3D Face Animation [14.07086606183356]
  Speech-driven 3D facial animation has garnered lots of attention thanks to its broad range of applications. Current methods fail to capture the nuanced emotional undertones conveyed through speech and produce monotonous facial motion. We introduce DEEPTalk, a novel approach that generates diverse and emotionally rich 3D facial expressions directly from speech inputs.
  arXiv  Detail & Related papers  (2024-08-12T08:56:49Z)
• CSTalk: Correlation Supervised Speech-driven 3D Emotional Facial Animation Generation [13.27632316528572]
  Speech-driven 3D facial animation technology has been developed for years, but its practical application still lacks expectations. Main challenges lie in data limitations, lip alignment, and the naturalness of facial expressions. This paper proposes a method called CSTalk that models the correlations among different regions of facial movements and supervises the training of the generative model to generate realistic expressions.
  arXiv  Detail & Related papers  (2024-04-29T11:19:15Z)
• Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generation [43.04371187071256]
  We present a novel method to generate vivid and emotional 3D co-speech gestures in 3D avatars. We use the ChatGPT-4 and an audio inpainting approach to construct the high-fidelity emotion transition human speeches. Our method outperforms the state-of-the-art models constructed by adapting single emotion-conditioned counterparts.
  arXiv  Detail & Related papers  (2023-11-29T11:10:40Z)
• Emotional Speech-Driven Animation with Content-Emotion Disentanglement [51.34635009347183]
  We propose EMOTE, which generates 3D talking-head avatars that maintain lip-sync from speech while enabling explicit control over the expression of emotion. EmOTE produces speech-driven facial animations with better lip-sync than state-of-the-art methods trained on the same data.
  arXiv  Detail & Related papers  (2023-06-15T09:31:31Z)
• EmotionGesture: Audio-Driven Diverse Emotional Co-Speech 3D Gesture Generation [24.547098909937034]
  EmotionGesture is a novel framework for vivid and diverse emotional co-speech 3D gestures from audio. Our framework outperforms the state-of-the-art, achieving vivid and diverse emotional co-speech 3D gestures.
  arXiv  Detail & Related papers  (2023-05-30T09:47:29Z)
• Generating Holistic 3D Human Motion from Speech [97.11392166257791]
  We build a high-quality dataset of 3D holistic body meshes with synchronous speech. We then define a novel speech-to-motion generation framework in which the face, body, and hands are modeled separately.
  arXiv  Detail & Related papers  (2022-12-08T17:25:19Z)
• Audio-Driven Co-Speech Gesture Video Generation [92.15661971086746]
  We define and study this challenging problem of audio-driven co-speech gesture video generation. Our key insight is that the co-speech gestures can be decomposed into common motion patterns and subtle rhythmic dynamics. We propose a novel framework, Audio-driveN Gesture vIdeo gEneration (ANGIE), to effectively capture the reusable co-speech gesture patterns.
  arXiv  Detail & Related papers  (2022-12-05T15:28:22Z)
• Freeform Body Motion Generation from Speech [53.50388964591343]
  Body motion generation from speech is inherently difficult due to the non-deterministic mapping from speech to body motions. We introduce a novel freeform motion generation model (FreeMo) by equipping a two-stream architecture. Experiments demonstrate the superior performance against several baselines.
  arXiv  Detail & Related papers  (2022-03-04T13:03:22Z)
• EMOVIE: A Mandarin Emotion Speech Dataset with a Simple Emotional Text-to-Speech Model [56.75775793011719]
  We introduce and publicly release a Mandarin emotion speech dataset including 9,724 samples with audio files and its emotion human-labeled annotation. Unlike those models which need additional reference audio as input, our model could predict emotion labels just from the input text and generate more expressive speech conditioned on the emotion embedding. In the experiment phase, we first validate the effectiveness of our dataset by an emotion classification task. Then we train our model on the proposed dataset and conduct a series of subjective evaluations.
  arXiv  Detail & Related papers  (2021-06-17T08:34:21Z)

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.