Content and Style Aware Audio-Driven Facial Animation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Liu, Qingju, Kim, Hyeongwoo, Bharaj, Gaurav
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914912780943360
author Liu, Qingju
Kim, Hyeongwoo
Bharaj, Gaurav
author_facet Liu, Qingju
Kim, Hyeongwoo
Bharaj, Gaurav
contents Audio-driven 3D facial animation has several virtual humans applications for content creation and editing. While several existing methods provide solutions for speech-driven animation, precise control over content (what) and style (how) of the final performance is still challenging. We propose a novel approach that takes as input an audio, and the corresponding text to extract temporally-aligned content and disentangled style representations, in order to provide controls over 3D facial animation. Our method is trained in two stages, that evolves from audio prominent styles (how it sounds) to visual prominent styles (how it looks). We leverage a high-resource audio dataset in stage I to learn styles that control speech generation in a self-supervised learning framework, and then fine-tune this model with low-resource audio/3D mesh pairs in stage II to control 3D vertex generation. We employ a non-autoregressive seq2seq formulation to model sentence-level dependencies, and better mouth articulations. Our method provides flexibility that the style of a reference audio and the content of a source audio can be combined to enable audio style transfer. Similarly, the content can be modified, e.g. muting or swapping words, that enables style-preserving content editing.
format Preprint
id arxiv_https___arxiv_org_abs_2408_07005
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Content and Style Aware Audio-Driven Facial Animation
Liu, Qingju
Kim, Hyeongwoo
Bharaj, Gaurav
Sound
Graphics
Audio and Speech Processing
Audio-driven 3D facial animation has several virtual humans applications for content creation and editing. While several existing methods provide solutions for speech-driven animation, precise control over content (what) and style (how) of the final performance is still challenging. We propose a novel approach that takes as input an audio, and the corresponding text to extract temporally-aligned content and disentangled style representations, in order to provide controls over 3D facial animation. Our method is trained in two stages, that evolves from audio prominent styles (how it sounds) to visual prominent styles (how it looks). We leverage a high-resource audio dataset in stage I to learn styles that control speech generation in a self-supervised learning framework, and then fine-tune this model with low-resource audio/3D mesh pairs in stage II to control 3D vertex generation. We employ a non-autoregressive seq2seq formulation to model sentence-level dependencies, and better mouth articulations. Our method provides flexibility that the style of a reference audio and the content of a source audio can be combined to enable audio style transfer. Similarly, the content can be modified, e.g. muting or swapping words, that enables style-preserving content editing.
title Content and Style Aware Audio-Driven Facial Animation
topic Sound
Graphics
Audio and Speech Processing
url https://arxiv.org/abs/2408.07005