中文版 | English

在结果中检索

CASIA OpenIR
（本次检索基于用户作品认领结果）

浏览/检索结果: 共5条，第1-5条 帮助

限定条件            
已选(0)清除 条数/页：   排序方式：
Multi-aspect self-supervised learning for heterogeneous information network 期刊论文
KNOWLEDGE-BASED SYSTEMS, 2021, 卷号: 233, 页码: 14
作者:  Che, Feihu;  Tao, Jianhua;  Yang, Guohua;  Liu, Tong;  Zhang, Dawei
Adobe PDF(2661Kb)  |  收藏  |  浏览/下载：258/52  |  提交时间：2021/12/28
Heterogeneous information network  Self-supervised  Contrastive learning  Graph neural network  
Self-supervised graph representation learning via bootstrapping 期刊论文
NEUROCOMPUTING, 2021, 卷号: 456, 页码: 88-96
作者:  Che, Feihu;  Yang, Guohua;  Zhang, Dawei;  Tao, Jianhua;  Liu, Tong
Adobe PDF(1379Kb)  |  收藏  |  浏览/下载：405/70  |  提交时间：2021/11/03
Graph representation learning  Self-supervised  Bootstrapping  Graph neural network  
Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERT 期刊论文
IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021, 期号: 29, 页码: 1897 - 1911
作者:  Ye Bai;  Jiangyan Yi;  Jianhua Tao;  Zhengkun Tian;  Zhengqi Wen;  Shuai Zhang
Adobe PDF(1163Kb)  |  收藏  |  浏览/下载：214/67  |  提交时间：2021/06/25
端到端语音识别、迁移学习、知识蒸馏、老师-学生学习、BERT、非自回归语音识别  
DECN: Dialogical Emotion Correction Network for Conversational Emotion Recognition 期刊论文
Neurocomputing, 2021, 期号: 0, 页码: 0
作者:  Zheng Lian;  Bin Liu;  Jianhua Tao
Adobe PDF(2238Kb)  |  收藏  |  浏览/下载：180/37  |  提交时间：2021/06/16
Emotion recognition in conversations (ERC)  Context-sensitive modeling  Dialogical Emotion Correction Network (DECN)  Interaction modeling  
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：403/63  |  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