Speech-driven Personalized Gesture Synthetics: Harnessing Automatic Fuzzy Feature Inference

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Fan, Wang, Zhaohan, Lyu, Xin, Zhao, Siyuan, Li, Mengjian, Geng, Weidong, Ji, Naye, Du, Hui, Gao, Fuxing, Wu, Hao, Li, Shunman
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929279359516672
author Zhang, Fan
Wang, Zhaohan
Lyu, Xin
Zhao, Siyuan
Li, Mengjian
Geng, Weidong
Ji, Naye
Du, Hui
Gao, Fuxing
Wu, Hao
Li, Shunman
author_facet Zhang, Fan
Wang, Zhaohan
Lyu, Xin
Zhao, Siyuan
Li, Mengjian
Geng, Weidong
Ji, Naye
Du, Hui
Gao, Fuxing
Wu, Hao
Li, Shunman
contents Speech-driven gesture generation is an emerging field within virtual human creation. However, a significant challenge lies in accurately determining and processing the multitude of input features (such as acoustic, semantic, emotional, personality, and even subtle unknown features). Traditional approaches, reliant on various explicit feature inputs and complex multimodal processing, constrain the expressiveness of resulting gestures and limit their applicability. To address these challenges, we present Persona-Gestor, a novel end-to-end generative model designed to generate highly personalized 3D full-body gestures solely relying on raw speech audio. The model combines a fuzzy feature extractor and a non-autoregressive Adaptive Layer Normalization (AdaLN) transformer diffusion architecture. The fuzzy feature extractor harnesses a fuzzy inference strategy that automatically infers implicit, continuous fuzzy features. These fuzzy features, represented as a unified latent feature, are fed into the AdaLN transformer. The AdaLN transformer introduces a conditional mechanism that applies a uniform function across all tokens, thereby effectively modeling the correlation between the fuzzy features and the gesture sequence. This module ensures a high level of gesture-speech synchronization while preserving naturalness. Finally, we employ the diffusion model to train and infer various gestures. Extensive subjective and objective evaluations on the Trinity, ZEGGS, and BEAT datasets confirm our model's superior performance to the current state-of-the-art approaches. Persona-Gestor improves the system's usability and generalization capabilities, setting a new benchmark in speech-driven gesture synthesis and broadening the horizon for virtual human technology. Supplementary videos and code can be accessed at https://zf223669.github.io/Diffmotion-v2-website/
format Preprint
id arxiv_https___arxiv_org_abs_2403_10805
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Speech-driven Personalized Gesture Synthetics: Harnessing Automatic Fuzzy Feature Inference
Zhang, Fan
Wang, Zhaohan
Lyu, Xin
Zhao, Siyuan
Li, Mengjian
Geng, Weidong
Ji, Naye
Du, Hui
Gao, Fuxing
Wu, Hao
Li, Shunman
Sound
Artificial Intelligence
Computer Vision and Pattern Recognition
Graphics
Human-Computer Interaction
Audio and Speech Processing
Speech-driven gesture generation is an emerging field within virtual human creation. However, a significant challenge lies in accurately determining and processing the multitude of input features (such as acoustic, semantic, emotional, personality, and even subtle unknown features). Traditional approaches, reliant on various explicit feature inputs and complex multimodal processing, constrain the expressiveness of resulting gestures and limit their applicability. To address these challenges, we present Persona-Gestor, a novel end-to-end generative model designed to generate highly personalized 3D full-body gestures solely relying on raw speech audio. The model combines a fuzzy feature extractor and a non-autoregressive Adaptive Layer Normalization (AdaLN) transformer diffusion architecture. The fuzzy feature extractor harnesses a fuzzy inference strategy that automatically infers implicit, continuous fuzzy features. These fuzzy features, represented as a unified latent feature, are fed into the AdaLN transformer. The AdaLN transformer introduces a conditional mechanism that applies a uniform function across all tokens, thereby effectively modeling the correlation between the fuzzy features and the gesture sequence. This module ensures a high level of gesture-speech synchronization while preserving naturalness. Finally, we employ the diffusion model to train and infer various gestures. Extensive subjective and objective evaluations on the Trinity, ZEGGS, and BEAT datasets confirm our model's superior performance to the current state-of-the-art approaches. Persona-Gestor improves the system's usability and generalization capabilities, setting a new benchmark in speech-driven gesture synthesis and broadening the horizon for virtual human technology. Supplementary videos and code can be accessed at https://zf223669.github.io/Diffmotion-v2-website/
title Speech-driven Personalized Gesture Synthetics: Harnessing Automatic Fuzzy Feature Inference
topic Sound
Artificial Intelligence
Computer Vision and Pattern Recognition
Graphics
Human-Computer Interaction
Audio and Speech Processing
url https://arxiv.org/abs/2403.10805