跳到主要导航
跳到搜索
跳到主要内容
西北工业大学 国内
English
中文
国内
简介
研究单位
科研成果
按专业知识、名称或附属进行搜索
Speech-driven video-realistic talking head synthesis using BLSTM-RNN
Shan Yang, Bo Fan,
Lei Xie
, Lijuan Wang, Geping Song
计算机学院
Northwestern Polytechnical University Xian
Microsoft USA
科研成果
:
期刊稿件
›
文章
›
同行评审
3
引用 （Scopus）
综述
指纹
指纹
探究 'Speech-driven video-realistic talking head synthesis using BLSTM-RNN' 的科研主题。它们共同构成独一无二的指纹。
分类
加权
按字母排序
Computer Science
Acoustic Feature
20%
active appearance model
40%
Bidirectional Long Short-Term Memory Network
100%
Long Short-Term Memory Network
20%
Network Architecture
20%
Neural Network
20%
Neural Network Architecture
20%
Neural Network Model
20%
Range Dependency
20%
Recurrent Neural Network
100%
Temporal Sequence
20%
Engineering
Acoustic Feature
16%
Appearance Model
33%
Feedforward
33%
Long Short-Term Memory
100%
Model Parameter
16%
Network Model
16%
Neural Network Architecture
16%
Nodes
16%
Recurrent Neural Network
100%