基于虚拟和物理化身的中文文本信息具体化

Embodiment of Chinese Textual Messages Based on Virtual/Physical Avatar

提出了基于虚拟和物理机器人化身的文本信息具体化概念。传统的基于文字的文本信息终端界面难以有效表达文本承载的全部信息。提出将文字语音化,同时将隐含在文本中的人类感情和意图等非语言信息通过虚拟或物理机器人具体化为适当的语调、面部表情和身体语言。虚拟或物理机器人称为文本信息提供者的化身。基于文本信息提供者化身的文字的终端界面能够表述文本承载的语言和非语言信息,提高文本传达信息的有效性。给出了基于虚拟化身的文本具体化系统原型。展望文本具体化应用前景。

A concept of embodying textual messages based on virtual/physical robotic avatars was proposed. Traditional interfaces of text based on the text cannot efficiently exchange information embedded in contexts. In the proposed interface, the text was changed into speeches. In the mean time, human emotions and intentions embedded in the contexts were expressed with tones, facial expressions, and body languages through virtual/physical robot. The robot is called the avatar of the person or agent who gives text. An avatar-based interface can efficiently exchange not only verbal information of text, but also nonverbal information embedded in the contexts. A prototype based on the viutual avatar was developed under the concept. The possible application of the concept was evaluated.