Audio-based head motion synthesis for Avatar-based telepresence systems
Audio-based head motion synthesis for Avatar-based telepresence systems
复制标题
用于基于 Avatar 的远程呈现系统的基于音频的头部运动合成
DOI：
--
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
U. Neumann
中科院分区：
文献类型：
--
作者：
Z. Deng;Shrikanth S. Narayanan;C. Busso;U. Neumann
在本文中，数据驱动的音频为基础的头部运动合成技术，提出了基于化身的远程呈现系统。首先，头部运动的人类主体发言的自定义语料库被捕获，并提取伴随的音频特征。基于音频特征和头部运动（音频头部运动）之间的对齐对，基于K-最近邻（KNN）的动态规划算法被用来合成新的头部运动给定新的音频输入。该方法还提供可选的直观关键帧（关键头部姿势）控制：在指定关键头部姿势之后，该方法将合成最大限度地满足语音和关键头部姿势两者的要求的适当头部运动序列。
In this paper, a data-driven audio-based head motion synthesis technique is presented for avatar-based telepresence systems. First, head motion of a human subject speaking a custom corpus is captured, and the accompanying audio features are extracted. Based on the aligned pairs between audio features and head motion (audio-headmotion), a K-Nearest Neighbors (KNN) based dynamic programming algorithm is used to synthesize novel head motion given new audio input. This approach also provides optional intuitive keyframe (key head poses) control: after key head poses are specified, this method will synthesize appropriate head motion sequences that maximally meet the requirements of both the speech and key head poses.