arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.04527eess.AS
收藏

基于Transformer网络的语音驱动的语义感知上人脸生成

Transformer Network for Semantically-Aware and Speech-Driven Upper-Face Generation

Mireille Fares, Catherine Pelachaud, Nicolas Obin

摘要:

我们提出了一个语义感知的语音驱动模型,以产生表现力和自然的上面部和头部运动的会话代理(ECA)。在这项工作中,我们的目标是产生自然和连续的头部运动和上面部手势与语音同步。我们提出了一个模型,生成这些手势的多模态输入功能的基础上:第一模态是文本,第二个是语音韵律。我们的模型利用Transformers和卷积映射的多模态特征,对应于连续的眉毛和头部姿态的话语。我们进行主观和客观的评估,以验证我们的方法,并将其与最先进的。

英文摘要:

We propose a semantically-aware speech driven model to generate expressive and natural upper-facial and head motion for Embodied Conversational Agents (ECA). In this work, we aim to produce natural and continuous head motion and upper-facial gestures synchronized with speech. We propose a model that generates these gestures based on multimodal input features: the first modality is text, and the second one is speech prosody. Our model makes use of Transformers and Convolutions to map the multimodal features that correspond to an utterance to continuous eyebrows and head gestures. We conduct subjective and objective evaluations to validate our approach and compare it with state of the art.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑