助手标题  
全文文献 工具书 数字 学术定义 翻译助手 学术趋势 更多
查询帮助
意见反馈
   sign language model 的翻译结果: 查询用时:0.107秒
图标索引 在分类学科中查询
所有学科
计算机软件及计算机应用
更多类别查询

图标索引 历史查询
 

sign language model
相关语句
  相似匹配句对
     Synonyms in Sign Language
     手语中的同义词
短句来源
     Language. Sign. Communication
     语言·符号·交流——谈布拉格学派的传播思想
短句来源
     of language.
     通过语言可以研究文化,通过文化可以研究语言。
短句来源
     G Language
     G语言
短句来源
     On the Statistical Model for Sign Language Understanding
     手语理解的统计模型研究
短句来源
查询“sign language model”译词为用户自定义的双语例句

    我想查看译文中含有:的双语例句
例句
没有找到相关例句


As intelligent human computer interface is being studied,and research on signl anguage synthesis has been paid more and more attention to.But current researches are almost all on graphics about American Sign Language and Japanese Sign Language.In this paper we analyze and compare the features of syntax and semantics of Chinese and the Chinese Sign Language.The Chinese Sign Language model is presented.According to features of syntax and semantics of Chinese and the Chinese...

As intelligent human computer interface is being studied,and research on signl anguage synthesis has been paid more and more attention to.But current researches are almost all on graphics about American Sign Language and Japanese Sign Language.In this paper we analyze and compare the features of syntax and semantics of Chinese and the Chinese Sign Language.The Chinese Sign Language model is presented.According to features of syntax and semantics of Chinese and the Chinese Sign Language a translation from Chinese to the Chinese Sign Language is implemented by adopting the method of translating to intermediate language based on rules.Furthermore a text driven Chinese Sign Language synthesis system is implemented by driving the model with parameters.Sign Language synthesis is valuable to multimedia data expression and intelligent human computer interface.

随着智能人机接口研究的兴起,手语合成的研究在国际上越来越受到重视。但是现有的研究几乎都是关于美国手语和日本手语的侧重于计算机图形学方面的研究。本文从语言学角度分析并比较汉语和汉语手语各自的语法和语义特点,提出了汉语手语模型。并针对汉语和汉语手语各自的语法和语义特征采用基于规则变换到中间语言的方法实现了由汉语至汉语手语的转换。进而用参数驱动模型,采用图形学方法在计算机上实现了一个由文本驱动的汉语手语合成系统。对多媒体数据表达和智能人机接口,手语合成都非常有意义。

Sign language is a language used not only by deaf mutes but also by sound people and its basic grammar information is conveyed by space position and change of hands and arms. This paper presents the design and realization of a sign language synthesis system as an output merging subsystem of a multi function perception machine which inputs text information and outputs synthesized sign language and a hand gesture model and a sign language model as well, discusses ways and means to put the motion of hands...

Sign language is a language used not only by deaf mutes but also by sound people and its basic grammar information is conveyed by space position and change of hands and arms. This paper presents the design and realization of a sign language synthesis system as an output merging subsystem of a multi function perception machine which inputs text information and outputs synthesized sign language and a hand gesture model and a sign language model as well, discusses ways and means to put the motion of hands and arms and control the key state method upon which the gesture database is based and Gesture Description Language(GDL) developed to define and describe gesture and introdues a computer graphics method synthesizing sign language based upon these models.

SignLanguageSynthesisinMulti┐functionPerceptionMachineXULinGAOWen(徐琳)(高文)(Dept.ofComputerScienceandEngineering,HarbinInstitut...

The traditional method of training HMM(Hidden Markov Models)is based on MLE(maximum likelihood estimation).When training samples are sufficient enough,the method can principally gain the optimal result.However,it is too difficult to get such large data sets practically,especially in sign language recognition.Discriminative training method can improve the error rate of MLE,which is caused by insufficient training data and similarities among sign language models.Maximum mutual information...

The traditional method of training HMM(Hidden Markov Models)is based on MLE(maximum likelihood estimation).When training samples are sufficient enough,the method can principally gain the optimal result.However,it is too difficult to get such large data sets practically,especially in sign language recognition.Discriminative training method can improve the error rate of MLE,which is caused by insufficient training data and similarities among sign language models.Maximum mutual information estimation as one of discriminative training methods has been widely applied in speech recognition.By taking competition models into account and setting up mixture sets appropriately,MMIE method was improved and applied both in signer-dependent and signer-independent sign language recognition.A great number of experiments had been taken,showing that this method greatly promoted the ability of the traditional MLE system.

传统的隐马尔科夫模型(HMM)的训练方法基于统计概率的最大似然准则(MLE),在训练样本数目足够大的情况下,这种方法在理论上可以得到最优的结果.在手语识别研究中,采集足够大的训练样本十分困难.区分性训练可以很好地弥补由于训练样本的缺乏以及手语模型之间的近似而造成的识别系统的缺陷.最大交互信息准则(MMIE)作为区分性训练准则的一种已经被广泛的应用于语音识别领域.文中通过合理的构建手语识别中的竞争模型和易混集,提出了MMIE准则的改进形式,并将其应用于特定人与非特定人手语识别.实验证明,使用改进的MMIE准则对识别系统性能有很大的提高.

 
图标索引 相关查询

 


 
CNKI小工具
在英文学术搜索中查有关sign language model的内容
在知识搜索中查有关sign language model的内容
在数字搜索中查有关sign language model的内容
在概念知识元中查有关sign language model的内容
在学术趋势中查有关sign language model的内容
 
 

CNKI主页设CNKI翻译助手为主页 | 收藏CNKI翻译助手 | 广告服务 | 英文学术搜索
版权图标  2008 CNKI-中国知网
京ICP证040431号 互联网出版许可证 新出网证(京)字008号
北京市公安局海淀分局 备案号:110 1081725
版权图标 2008中国知网(cnki) 中国学术期刊(光盘版)电子杂志社