CASIA OpenIR

Browse/Search Results:  1-10 of 138 Help

Selected(0)Clear Items/Page:    Sort:
多通道语音增强优化建模方法研究 学位论文
, 中科院自动化研究所: 中国科学院大学, 2021
Authors:  李冠君
Adobe PDF(5732Kb)  |  Favorite  |  View/Download:21/1  |  Submit date:2021/06/07
多通道语音增强,非点源噪声场景,点源噪声场景,复杂噪声场景,自动语音识别  
Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-resource Speech Recognition 期刊
创刊日期: 2021, 收录类别: SCI,
Sponsors:  Yi C(易澄)
Adobe PDF(487Kb)  |  Favorite  |  View/Download:4/1  |  Submit date:2021/06/05
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
Authors:  Fan, Cunhang;  Yi, Jiangyan;  Tao, Jianhua;  Tian, Zhengkun;  Liu, Bin;  Wen, Zhengqi
Adobe PDF(2534Kb)  |  Favorite  |  View/Download:18/1  |  Submit date: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  
基于回归方法的单目相机人脸重建研究 学位论文
工学博士, 中国科学院自动化研究所: 中国科学院大学, 2020
Authors:  王鹏睿
Adobe PDF(7276Kb)  |  Favorite  |  View/Download:91/3  |  Submit date:2020/09/10
三维人脸重建  弱监督学习  明暗成形  网格形变  单目相机  
基于编解码框架的端到端语音识别技术研究 学位论文
工学博士, 中国科学院自动化研究所: 中国科学院大学, 2020
Authors:  董林昊
Adobe PDF(5860Kb)  |  Favorite  |  View/Download:145/13  |  Submit date:2020/06/13
语音识别技术  神经网络  编解码框架  端到端建模  
复杂场景语音前端增强与分离算法研究 学位论文
工学学位, 北京: 中国科学院自动化研究所, 2020
Authors:  李晨星
Adobe PDF(11281Kb)  |  Favorite  |  View/Download:109/5  |  Submit date:2020/07/20
语音去混响  语音增强  语音分离  远场语音识别  
面向数据失配的鲁棒性声学建模方法研究 学位论文
, 中科院自动化研究所: 中国科学院大学, 2020
Authors:  刘斌
Adobe PDF(2027Kb)  |  Favorite  |  View/Download:102/4  |  Submit date:2020/06/09
鲁棒性声学建模  语音识别  对抗学习  语音唤醒  
FOCUSING ON ATTENTION: PROSODY TRANSFER AND ADAPTATIVE OPTIMIZATION STRATEGY FOR MULTI-SPEAKER END-TO-END SPEECH SYNTHESIS 会议论文
, 网上虚拟会议, 2020-5
Authors:  Fu, Ruibo;  Tao, Jianhua;  Wen, Zhengqi;  Yi, Jiangyan;  Wang, Tao
View  |  Adobe PDF(154Kb)  |  Favorite  |  View/Download:126/51  |  Submit date:2020/06/27
prosody transfer  optimization strategy  speaker adaptation  attention  speech synthesis  
CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition 会议论文
, 在线会议, 2020-05
Authors:  Dong, Linhao;  Xu, Bo
View  |  Adobe PDF(641Kb)  |  Favorite  |  View/Download:69/16  |  Submit date:2020/06/13
continuous integrate-and-fire  end-to-end model  soft and monotonic alignment  online speech recognition  acoustic boundary positioning  
Synchronous Speech Recognition and Speech-to-Text Translation with Interactive Decoding 会议论文
, New York, USA, Feb. 7-12, 2020
Authors:  Yuchen Liu;  Jiajun Zhang;  Hao Xiong;  Long Zhou;  Zhongjun He;  Hua Wu;  Haifeng Wang;  Chengqing Zong
Adobe PDF(618Kb)  |  Favorite  |  View/Download:1/0  |  Submit date:2021/06/01