中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共6条，第1-6条 帮助

限定条件                        
已选(0)清除 条数/页：   排序方式：
FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularization 会议论文
, Brno, Czechia, 30 August – 3 September
作者:  Zhengkun Tian;  Jiangyan Yi;  Ye Bai;  Jianhua Tao;  Shuai Zhang;  Zhengqi Wen
Adobe PDF(839Kb)  |  收藏  |  浏览/下载：220/52  |  提交时间：2022/06/14
epsilon-k anonymization and adversarial training of graph neural networks for privacy preservation in social networks 期刊论文
ELECTRONIC COMMERCE RESEARCH AND APPLICATIONS, 2021, 卷号: 50, 页码: 17
作者:  Tian, Hu;  Zheng, Xiaolong;  Zhang, Xingwei;  Zeng, Daniel Dajun
Adobe PDF(2484Kb)  |  收藏  |  浏览/下载：311/104  |  提交时间：2021/12/28
Privacy preservation  Anonymization  Graph neural networks  Social network  
You Only Search Once: Single Shot Neural Architecture Search via Direct Sparse Optimization 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 卷号: 43, 期号: 9, 页码: 2891-2904
作者:  Zhang, Xinbang;  Huang, Zehao;  Wang, Naiyan;  Xiang, Shiming;  Pan, Chunhong
Adobe PDF(1271Kb)  |  收藏  |  浏览/下载：327/66  |  提交时间：2021/11/02
Computer architecture  Optimization  Learning (artificial intelligence)  Task analysis  Acceleration  Evolutionary computation  Convolution  Neural architecture search(NAS)  convolution neural network  sparse optimization  
Text Style Transfer With Decorative Elements 会议论文
International Conference on Multimedia Information Processing and Retrieval, Tokyo, Japan, September 10, 2021
作者:  Yuting,Ma;  Fan,Tang;  Weiming,Dong;  Changsheng,Xu
Adobe PDF(8683Kb)  |  收藏  |  浏览/下载：341/81  |  提交时间：2021/06/17
text style transfer, decorative elements extraction, decoration recomposition  
CTNet: Conversational Transformer Network for Emotion Recognition 期刊论文
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2021, 期号: 29, 页码: 985-1000
作者:  Lian, Zheng;  Liu, Bin;  Tao, Jianhua
Adobe PDF(2230Kb)  |  收藏  |  浏览/下载：402/63  |  提交时间：2021/05/06
Emotion recognition  Context modeling  Feature extraction  Fuses  Speech processing  Data models  Bidirectional control  Context-sensitive modeling  conversational transformer network (CTNet)  conversational emotion recognition  multimodal fusion  speaker-sensitive modeling  
Gated Recurrent Fusion With Joint Training Framework for Robust End-to-End Speech Recognition 期刊论文
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2021, 期号: 29, 页码: 198-209
作者:  Fan, Cunhang;  Yi, Jiangyan;  Tao, Jianhua;  Tian, Zhengkun;  Liu, Bin;  Wen, Zhengqi
Adobe PDF(2534Kb)  |  收藏  |  浏览/下载：437/58  |  提交时间：2021/03/08
Speech enhancement  Speech recognition  Training  Noise measurement  Logic gates  Acoustic distortion  Task analysis  Gated recurrent fusion  robust end-to-end speech recognition  speech distortion  speech enhancement  speech transformer