首页> 外国专利> 3 Medium storing a Computer Program with a Function of Lip-sync and Emotional Expression on 3D Scanned Real Facial Image during Realtime Text to Speech Conversion and Online Game Email Chatting Broadcasting and Foreign Language Learning Method using the Same

3 Medium storing a Computer Program with a Function of Lip-sync and Emotional Expression on 3D Scanned Real Facial Image during Realtime Text to Speech Conversion and Online Game Email Chatting Broadcasting and Foreign Language Learning Method using the Same

机译：3在实时文本到语音转换和在线游戏电子邮件聊天广播以及使用该方法的外语学习方法中，在3D扫描的真实面部图像上存储具有口型同步和情感表达功能的计算机程序的介质

页面导航

摘要
著录项
相似文献

摘要

PURPOSE: A recording medium storing a computer program realizing lip-sync and expression, and a method for an online game, e-mail, chatting and foreign language learning by using the same are provided to realize the lip shape of a speaking shape by detecting a vowel of each character in the text and applying a lip-sync program to the 3D(Dimensional) scanned real face image. CONSTITUTION: The voice data matched with each character is stored in a T2S(Text-to-Speech) database. A formula for modifying a position, a size and an angle of important elements in the image data is stored in an expression database. The formula for modifying a position, a size and an angle of important elements during the lip-sync is stored in a lip-sync database. The 3D image and the sampled voice of a member are stored in a basic database. The text for the voice output and the expression is stored. The text is loaded on a memory(S301) and it is decided whether the first character is a functional character or not(S302). If the character is the functional character, the process is branched to an expression program(S304). If not, a T2S program and the lip-sync program are operated(S310).

机译：目的：提供一种存储用于实现口形同步和表情的计算机程序的记录介质，以及用于通过使用该记录介质进行在线游戏，电子邮件，聊天和外语学习的方法，以通过检测来实现说话形状的唇形在文本中每个字符的元音，然后将唇形同步程序应用于3D（三维）扫描的真实面部图像。构成：与每个字符匹配的语音数据存储在T2S（文本到语音）数据库中。用于修改图像数据中重要元素的位置，大小和角度的公式存储在表达数据库中。在口形同步数据库中存储用于在口形同步期间修改重要元素的位置，大小和角度的公式。成员的3D图像和采样的语音存储在基本数据库中。语音输出和表达的文本被存储。将文本加载到存储器上（S301），并确定第一个字符是否是功能字符（S302）。如果字符是功能字符，则处理分支到表达式程序（S304）。如果否，则操作T2S程序和口形同步程序（S310）。

著录项

公开/公告号KR20030039019A

专利类型
公开/公告日2003-05-17

原文格式PDF
申请/专利权人 SHIN SUN HAE;
展开▼

申请/专利号KR20010069819
发明设计人 SHIN SUN HAE;
展开▼

申请日2001-11-09
分类号G06F17/00;
国家 KR
入库时间 2022-08-21 23:47:10

相似文献

专利
外文文献