期刊文献+

基于云服务的AI玩偶的研究及在教育教学中的应用 被引量:3

AI avatar based on cloud services and its educational application
下载PDF
导出
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.
作者 叶枫 胡程 黄倩 陈勇 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)
出处 《计算机工程与科学》 CSCD 北大核心 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)
关键词 玩偶 云服务 人工智能 教育教学 avatar cloud service AI education and teaching
  • 相关文献

参考文献10

二级参考文献152

  • 1朱道立,陈佩林,马以桐,王康乐,蒋建国.多元立体化教学模式的实践与思索[J].辽宁教育研究,2007(12):55-58. 被引量:57
  • 2赵静,夏良正,舒志强,赵一凡.不同光照条件下特征脸方法的改进研究[J].计算机应用研究,2005,22(6):240-242. 被引量:5
  • 3孙鑫,刘兵,刘本永.基于分块PCA的人脸识别[J].计算机工程与应用,2005,41(27):80-82. 被引量:14
  • 4Wang R H,Chen S H, Tao J, et al. Mandarin Text- To-Speech Synthesis[C]//Advances in Chinese Spoken Language Processing. Beijing: World Scientific Pub-lishing, 2007.
  • 5Campbell W N, Black A W. Prosody and the selection of source units for concatenative synthesis[J]. Pro- gress in Speech Synthesis, 1996: 279-282.
  • 6Iwahashi N, Kaiki N, SagisakaY. Concatenative speech synthesis by minimum distortion criteria[C]// International Conference on Acoustics, Speech, andSignal Processing. 1992, 2 : 65-68.
  • 7Wang R H, Ma Z K, Zhu D L. A corpus-based Chi- nese speech synthesis with contextual-dependant unit selection [C]//International Conference on SpokenLanguage Processing. 2000: 391-394.
  • 8Donovan R E. Trainable speech synthesis[D]. Ph. D Dissertation, Cambridge University, 1996.
  • 9Tokuda K, Zen H, Black A W. HMM-based approach to multilingual speech synthesis[C]//Text to Speech Synthesis: New Paradigms and Advances. New York:Prentice Hall, 2004.
  • 10Hu Y, Liu Q F, Wang R H. Prosody generation in Chinese synthesis using the template of quantified pro- sodic unit and base intonation contour[C]//Interna-tional Conference on Spoken Language Processing. 2000: 55-58.

共引文献818

同被引文献16

引证文献3

二级引证文献2

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部