CASIA OpenIR

浏览/检索结果: 共27条,第1-10条 帮助

已选(0)清除 条数/页:   排序方式:
安全强化学习综述 期刊论文
自动化学报, 2023, 卷号: 49, 期号: 9, 页码: 1813-1835
作者:  王雪松;  王荣荣;  程玉虎
Adobe PDF(1356Kb)  |  收藏  |  浏览/下载:9/5  |  提交时间:2024/04/24
安全强化学习  约束马尔科夫决策过程  学习过程  学习目标  离线强化学习  
Large-scale Multi-modal Pre-trained Models: A Comprehensive Survey 期刊论文
Machine Intelligence Research, 2023, 卷号: 20, 期号: 4, 页码: 447-482
作者:  Xiao Wang;  Guangyao Chen;  Guangwu Qian;  Pengcheng Gao;  Xiao-Yong Wei;  Yaowei Wang;  Yonghong Tian;  Wen Gao
Adobe PDF(3540Kb)  |  收藏  |  浏览/下载:16/3  |  提交时间:2024/04/23
Multi-modal (MM), pre-trained model (PTM), information fusion, representation learning, deep learning  
Semantic Image Synthesis via Conditional Cycle-Generative Adversarial Networks 会议论文
, Beijing, China, August 20-24, 2018
作者:  Xiyan Liu;  Gaofeng Meng;  Shiming Xiang;  Chunhong Pan
Adobe PDF(4929Kb)  |  收藏  |  浏览/下载:102/42  |  提交时间:2022/01/24
Image synthesis  Text-to-image  Generative adversarial networks  
F-0-Noise-Robust Glottal Source and Vocal Tract Analysis Based on ARX-LF Model 期刊论文
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2021, 卷号: 29, 页码: 3375-3383
作者:  Li, Yongwei;  Tao, Jianhua;  Erickson, Donna;  Liu, Bin;  Akagi, Masato
收藏  |  浏览/下载:124/0  |  提交时间:2021/12/28
Speech recognition  Iterative methods  Production  Estimation  Brain modeling  Shape  Low-frequency noise  Glottal source  vocal tract  source-filter model  ARX-LF model  
Motor-Cortex-Like Recurrent Neural Network and Multi-Tasks Learning for the Control of Musculoskeletal Systems 期刊论文
IEEE Transactions on Cognitive and Developmental Systems, 2020, 卷号: 暂无, 期号: 暂无, 页码: 暂无
作者:  Jiahao Chen;  Hong Qiao
Adobe PDF(1958Kb)  |  收藏  |  浏览/下载:168/46  |  提交时间:2021/06/01
Biologically inspired  Musculoskeletal system  Neuromuscular control,  Motor cortex  Muscle synergy  Recurrent neural network  
A Time/Space Separation Based 3D Fuzzy Modeling Approach for Nonlinear Spatially Distributed Systems 期刊论文
International Journal of Automation and Computing, 2018, 卷号: 15, 期号: 1, 页码: 52-65
作者:  Xian-Xia Zhang;  Zhi-Qiang Fu;  Shao-Yuan Li;  Tao Zou;  Bing Wang
Adobe PDF(3207Kb)  |  收藏  |  浏览/下载:101/31  |  提交时间:2021/02/23
Spatially distributed system (SDS)  system identification  3D fuzzy system  Karhunen-Love decomposition  particle swarm optimization (PSO).  
Simultaneous Estimation of Glottal Source Waveforms and Vocal Tract Shapes from Speech Signals Based on ARX-LF Model 期刊论文
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2020, 卷号: 92, 期号: 8, 页码: 831-838
作者:  Li, Yongwei;  Sakakibara, Ken-Ichi;  Akagi, Masato
收藏  |  浏览/下载:177/0  |  提交时间:2020/08/03
Glottal source waveform  Vocal tract shape  ARX-LF model  
Self-Attention Aligner: A Latency-Control End-to-End Model for ASR using Self-attention Network and Chunk-hopping 会议论文
, Brighton, United Kingdom, 2019-05
作者:  Dong, Linhao;  Wang, Feng;  Xu, Bo
Adobe PDF(930Kb)  |  收藏  |  浏览/下载:237/42  |  提交时间:2020/06/13
speech recognition  self-attention network  encoder-decoder  end-to-end  latency-control  
A monocular vision-based perception approach for unmanned aerial vehicle close proximity transmission tower inspection 期刊论文
INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS, 2019, 卷号: 16, 期号: 1, 页码: 20
作者:  Bian, Jiang;  Hui, Xiaolong;  Zhao, Xiaoguang;  Tan, Min
浏览  |  Adobe PDF(1859Kb)  |  收藏  |  浏览/下载:432/94  |  提交时间:2019/07/12
Close proximity inspection of transmission tower  tower localization  UAV self-positioning  monocular vision  
低资源语言的多语言语音识别建模方法研究 学位论文
, 北京: 中国科学院研究生院, 2018
作者:  周世玉
Adobe PDF(2353Kb)  |  收藏  |  浏览/下载:1137/8  |  提交时间:2018/12/20
语音识别  多语言  低资源  跨语言  端到端  多语言语音识别  中 英混合语音识别  Asr  Multilingual  Low-resource  Cross-language  Sequence-to-sequence  Multilingual Speech Recognition  English-mandarin Bilingual Speech Recognition