基于云服务的AI玩偶的研究及在教育教学中的应用  

AI avatar based on cloud services and its educational application

作　　者：叶枫[1,2] 胡程 黄倩 陈勇[2] YE Feng;HU Cheng;HUANG Qian;CHEN Yong(College of Computer and Information,Hohai University,Nanjing 211100;Postdoctoral Centre,Nanjing Longyuan Micro-Electronic Company,Nanjing 211106,China)

机构地区：[1]河海大学计算机与信息学院,江苏南京211100 [2]南京龙渊微电子科技有限公司博士后工作站,江苏南京211106

出　　处：《计算机工程与科学》2018年第A01期72-80,共9页Computer Engineering & Science

基　　金：国家自然科学基金(61300122);2017江苏省"六大人才高峰"项目(XYDXX-078);2017江苏省博士后科研资助计划(1701020C)

摘　　要：在人工智能时代,以"会说话的汤姆猫"应用为代表的虚拟化、智能化的玩偶软件愈加得到人们的青睐。从教育的角度,它们能提供儿童陪伴、辅助学习等功能。但是,对于教育领域的研究人员而言,受限于AI技术的复杂性、智能终端的硬件和网络条件,构建功能丰富、用户体验良好的AI玩偶应用较为困难。针对该问题,提出了快速构建一个Android平台AI玩偶应用软件的解决方案,并集成了多个第三方提供的云服务实现了人脸合成3D玩偶、语音转换、语音评测及社交分享等功能。通过性能测试和与相关研究做比较,该AI玩偶应用框架适用于主流的Android终端,具有良好的响应速度和用户体验,能成为辅助教育教学的工具。In AI age, the virtual and intelligent avater software applications represented by Talking Tom increasingly attract more and more attention. From an educational perspective, they can provide company for children, auxiliary learning and other functions. However, constrained by the complexity of related technologies, hardware and networks, it is very difficult for average education researchers to develop AI avatar applications which can offer rich functions and friendly user experience. Aiming at the problem, we propose a solution to developing a framework for AI avatar applications rapidly. It integrates the multiple cloud services from third-party providers, and implements virtual 3D avatar with human face synthesis, speech conversion, speech evaluation and social sharing. System testing and comparison with other related works show that the framework is suitable for common Android mobile devices and has the good response speed and friendly user experience, thus it becomes an auxiliary education teaching tool.

关 键 词：玩偶 云服务 人工智能 教育教学 

分 类 号：G642.4[文化科学—高等教育学]