CASIA OpenIR

Browse/Search Results:  1-10 of 17 Help

  Show only claimed items
Selected(0)Clear Items/Page:    Sort:
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:151/13  |  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  
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:74/16  |  Submit date:2020/06/13
continuous integrate-and-fire  end-to-end model  soft and monotonic alignment  online speech recognition  acoustic boundary positioning  
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
Authors:  Dong, Linhao;  Wang, Feng;  Xu, Bo
View  |  Adobe PDF(930Kb)  |  Favorite  |  View/Download:62/7  |  Submit date:2020/06/13
speech recognition  self-attention network  encoder-decoder  end-to-end  latency-control  
Boosting Character-Based Chinese Speech Synthesis via Multi-Task Learning and Dictionary Tutoring 会议论文
, 奥地利, 2019.9.15-2019.9.19
Authors:  Zou, Yuxiang;  Dong, Linhao;  Xu, Bo
View  |  Adobe PDF(637Kb)  |  Favorite  |  View/Download:88/47  |  Submit date:2020/06/10
Extending Recurrent Neural Aligner for Streaming End-to-End Speech Recognition in Mandarin 会议论文
, Hyderabad, India, 2018-09
Authors:  Dong, Linhao;  Zhou, Shiyu;  Chen, Wei;  Xu, Bo
View  |  Adobe PDF(321Kb)  |  Favorite  |  View/Download:42/6  |  Submit date:2020/06/13
speech recognition  recurrent neural aligner  mandarin  end-to-end  
Speech-Transformer: A No-Recurrence Sequence-to-Sequence Model for Speech Recognition 会议论文
, Calgary, Canada, 2018-04
Authors:  Dong, Linhao;  Xu, Shuang;  Xu, Bo
View  |  Adobe PDF(640Kb)  |  Favorite  |  View/Download:396/298  |  Submit date:2020/06/13
speech recognition  sequence-to-sequence  attention  transformer  
Syllable-Based Acoustic Modeling with CTC for Multi-Scenarios Mandarin speech recognition 会议论文
, Rio de Janeiro, Brazil, 8-13, July, 2018
Authors:  Zhao YY(赵媛媛);  Linhao Dong;  Shuang Xu;  Bo Xu;  Yuanyuan Zhao
Favorite  |  View/Download:7/0  |  Submit date:2020/10/27
Multi-scenarios  Context-independent  Syllable-based Modeling  Mandarin Speech Recognition  Layer Normalization  
Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese 会议论文
Interspeech, 印度的海德拉巴, 2018
Authors:  Shiyu Zhou;  Linhao Dong;  Shuang Xu;  Bo Xu
Favorite  |  View/Download:3/0  |  Submit date:2020/10/27
Asr  Multi-head Attention  Syllable Based Acoustic Modeling  Sequence-to-sequence  
A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese 会议论文
ICONIP, Siem Reap, Cambodia, 2018
Authors:  Shiyu Zhou;  Linhao Dong;  Shuang Xu;  Bo Xu
Favorite  |  View/Download:3/0  |  Submit date:2020/10/27
Asr  Multi-head Attention  Modeling Units  Sequence-to-sequence  Transformer  
Kinematics and Dynamics Modelling of All Terrain Articulated Tracked Vehicles 会议论文
Proceedings of 12th World Congress on Intelligent Control and Automation, Guilin, China, 2016-6
Authors:  Hao Lin;  Wei Lin;  En Li;  Zize Liang
View  |  Adobe PDF(1678Kb)  |  Favorite  |  View/Download:187/46  |  Submit date:2016/06/29
Kinematics  Dynamics  All Terrain Articulated Tracked Vehicles