收藏本站
收藏 | 手机打开
二维码
手机客户端打开本文

An End-to-end Speech Recognition Algorithm based on Attention Mechanism

Jia-nan Chen  Shuang Gao  Han-zhe Sun  Xiao-hui Liu  Zi-ning Wang  Yan Zheng  
【摘要】:End-to-end speech recognition system is a major research field in speech recognition. The most typical model is the end-to-end speech recognition system based on CTC where RNN mining to and time sequence information are adopted, and a series of assumptions of HMM are discarded to obtain a good recognition rate. However, the CTC-based model is more dependent on the speech model and have a longer training cycle. Therefore, in the framework of traditional acoustic model, this paper proposes to train a feature extraction network of spectrogram based on attention mechanism by using prior knowledge. Firstly, it was spliced in the front end based on CTC model, and then the number of layers of cyclic neural network based on CTC model was reduced. Finally, it was combined to retrain. The experimental results show that the training time of the combined model is effectively reduced, and the accuracy of speech recognition is further improved.

知网文化
【相似文献】
中国期刊全文数据库 前20条
1 ;The 10th IEEE International Conference on Automatic Face and Gesture Recognition[J];计算机应用;2012年09期
2 ;Research on Radar Emitter Attribute Recognition Method[J];Geo-Spatial Information Science;2006年01期
3 ;High-Temperature Target Recognition Based on Spectral Radiation Information[J];Engineering Sciences;2006年01期
4 费万春;白伦;;Pattern Recognition of Non-Stationary Time Series with Finite Length[J];Tsinghua Science and Technology;2006年05期
5 ;Bio-character Recognition Will Substitute for Cipher Key-Multi-module Bio-character Identification System[J];Science Foundation in China;2006年02期
6 ;Multimode Biometric Recognition System Praised by MOE[J];Tsinghua Science and Technology;2005年05期
7 ;A Smart Mathematic Morphology Method for Recognition and Understanding of Airfield[J];Wuhan University Journal of Natural Sciences;2005年05期
8 ;Information Fusing Recognition of Traditional Chinese Medicine (TCM) Pulse State Based on Stochastic Fuzzy Neural Network[J];Chinese Journal of Biomedical Engineering(English Edition);2005年03期
9 ;Pattern Recognition and Forecast of Coal and Gas Outburst[J];Journal of China University of Mining & Technology;2005年03期
10 谢湘,匡镜明;Mandarin Digits Speech Recognition Using Support Vector Machines[J];Journal of Beijing Institute of Technology(English Edition);2005年01期
11 ;Design of a Fault Diagnosis System for the Power Device Based on Ferrography and Image Recognition Technology[J];International Journal of Plant Engineering and Management;2005年01期
12 ;Recognition of a Life Distribution Based on a Neural Network[J];International Journal of Plant Engineering and Management;2004年01期
13 许超,曹志刚;Robust Speech Recognition Using a Harmonic Model[J];Tsinghua Science and Technology;2004年02期
14 ;Molecular Mechanisms of Cell-cell Recognition[J];生物化学与生物物理进展;2004年05期
15 ;Study on the Essence of Optimal Statistically Uncorrelated Discriminant Vectors and Its Application to Face Recognition[J];Engineering Sciences;2004年02期
16 ;Molecularly Imprinted Polymer for Theophylline Retention and Molecular Recognition Properties in Capillary Electrochromatography[J];Wuhan University Journal of Natural Sciences;2004年03期
17 ;A New Method for Target Recognition[J];The Journal of China Universities of Posts and Telecommunications;2004年03期
18 ;Development of Enantioselective Fluorescent Sensors for Chiral Recognition[J];合成化学;2004年S1期
19 ;The Synthesis of a Fluorescent Chemosensor Containing Two Thiourea Groups and Its Recognition Behavior for Dicarboxylate Anions[J];Wuhan University Journal of Natural Sciences;2004年06期
20 赵军辉,谢湘,匡镜明;Linear Discriminant Analysis and Kernel Vector Quantization for Mandarin Digits Recognition[J];Journal of Beijing Institute of Technology(English Edition);2004年04期
中国重要会议论文全文数据库 前20条
1 Rui Han;Weiwu Yan;Shuangrui Liu;Bo Ye;;3D-Mask-Tiramisu Network: Lung Nodule Recognition Based on Instance Segmentation[A];第31届中国过程控制会议(CPCC 2020)摘要集[C];2020年
2 Jun Wang;Xiaoling Chen;Guoqing Wang;;Hand-Dorsa Vein Recognition Based on Weighted Pooling of Complementary Features[A];第31届中国过程控制会议(CPCC 2020)摘要集[C];2020年
3 Qiang Guan;Ming Gao;Li Sheng;;Recognition of SET micro-seismic events based on convolutional neural network[A];第31届中国过程控制会议(CPCC 2020)摘要集[C];2020年
4 Gang Li;Shengjie Yang;Jianxun Li;;Edge and Node Graph Convolutional Neural Network for Human Action Recognition[A];第32届中国控制与决策会议论文集(2)[C];2020年
5 Ruoshi Wang;Zhigang Liu;Ziyang Yin;;Jointly Learning Multi-view Features for Human Action Recognition[A];第32届中国控制与决策会议论文集(2)[C];2020年
6 Yinan Zhao;Zihao Zhang;Zhaolin Zhang;;Multi-Angle Data Cube Action Recognition Based on Millimeter Wave Radar[A];第32届中国控制与决策会议论文集(2)[C];2020年
7 Xiaoxian Wang;Jun Guo;Siliang Lu;;A Two-Step Method for PMSG Bearing Fault Recognition under Varying Speed Condition[A];第32届中国控制与决策会议论文集(2)[C];2020年
8 Qian Hu;Chengdong Wu;Jianning Chi;Xiaosheng Yu;Huan Wang;;Multi-level Feature Fusion Facial Expression Recognition Network[A];第32届中国控制与决策会议论文集(2)[C];2020年
9 Jie Li;Jin Xu;Xianlun Tang;Yingjie Chen;Qing Liu;;Adaptive Structure Evolution Convolutional Neural Network for Image Recognition[A];第32届中国控制与决策会议论文集(2)[C];2020年
10 SHEN Hanxu;LI Yue;CHEN Hao;LIU Qiongyang;YANG Xiaonan;WEI Yongquan;GONG Jun;;Research on Human Action Recognition Based on Improved Pooling Algorithm[A];第32届中国控制与决策会议论文集(1)[C];2020年
11 Shun Xu;Wenwen Shen;;Discriminative Weighted Non-negative Sparse Low-rank Representation Classifier for Robust Face Recognition[A];第32届中国控制与决策会议论文集(1)[C];2020年
12 Shuai Wang;Jinyuan Shen;Runjie Liu;;A Real-time Deep Convolution Image Recognition Method Based on Data Mining[A];第32届中国控制与决策会议论文集(1)[C];2020年
13 Ming-hai Jiao;Wei-ming Duan;Jue Wang;Ben-dong Luo;Chi Zhang;Xiang-yu Sun;;Research on Person Recognition Model of Domain Adaptive Learning[A];第32届中国控制与决策会议论文集(3)[C];2020年
14 GONG Wen-bin;SHI Zhang-song;JI Qiang;;Non-Segmented Chinese License Plate Recognition Algorithm based on Deep neural Networks[A];第32届中国控制与决策会议论文集(3)[C];2020年
15 FangGuo Li;BeiKe Zhang;Dong Gao;;Chinese Named Entity Recognition for Hazard And Operability Analysis Text[A];第32届中国控制与决策会议论文集(3)[C];2020年
16 Qiaojie Sun;Dali Chen;Sen Wang;Shixin Liu;;Recognition Method for Handwritten Steel Billet Identification Number Based on Yolo Deep Convolutional Neural Network[A];第32届中国控制与决策会议论文集(3)[C];2020年
17 Dongmei Feng;Peng Wang;Lei Zu;;Design of Attendance Checking Management System for College Classroom Students Based on Fingerprint Recognition[A];第32届中国控制与决策会议论文集(3)[C];2020年
18 Yanyan Cheng;Zhongjian Dai;Ye Ji;Simin Li;Zhiyang Jia;Kaoru Hirota;Yaping Dai;;Student Action Recognition Based on Deep Convolutional Generative Adversarial Network[A];第32届中国控制与决策会议论文集(3)[C];2020年
19 Yang Liu;Wei Meng;Humin Zong;;Jellyfish Recognition and Density Calculation Based on Image Processing and Deep Learning[A];第32届中国控制与决策会议论文集(4)[C];2020年
20 Zhongyu Bai;Qichuan Ding;Jiawei Tan;;Two-Steam Fully Connected Graph Convolutional Network for Skeleton-Based Action Recognition[A];第32届中国控制与决策会议论文集(4)[C];2020年
中国博士学位论文全文数据库 前10条
1 Jamshaid UL Rahman;[D];中国科学技术大学;2020年
2 宋凤义;非控制条件下的人脸分析与验证[D];南京航空航天大学;2014年
3 柯兰(Khawlah Hussein Ali);视频序列中人的动作和身份识别[D];华中科技大学;2015年
4 龚培渝;通过对话寻求承认[D];吉林大学;2011年
5 李和佳;霍耐特承认理论研究[D];南京师范大学;2008年
6 何坤;人脸识别理论关键技术的研究[D];四川大学;2006年
7 赵淑欢;欠完备采样环境下面向数据的稀疏表示人脸识别研究[D];燕山大学;2016年
8 刘青山;人脸跟踪与识别的研究[D];中国科学院研究生院(自动化研究所);2003年
9 Shahryar Shafique Qureshi;[D];北京邮电大学;2012年
10 郝相钦;社会变革的道德透视[D];北京师范大学;2008年
中国硕士学位论文全文数据库 前9条
1 Tsering Shrestha;[D];湖南大学;2006年
2 巴雅尔;[D];内蒙古师范大学;2012年
3 Antoine GAMBI;[D];北京邮电大学;2017年
4 Boakye-Yiadom Adwoa Agyeiwaa;[D];西南科技大学;2020年
5 Hamza Mehdi Khan;基于神经网络的SAR图像船舶识别[D];上海交通大学;2019年
6 温研东;基于稀疏表示与深度学习的人脸识别研究[D];华南理工大学;2016年
7 Kim JungTae(金正泰);[D];华东理工大学;2015年
8 郭姗姗;澳大利亚职业学校先前学习认定研究[D];西南大学;2008年
9 郑献春;基于梯度导数的人脸识别的研究与实现[D];西安电子科技大学;2011年
中国重要报纸全文数据库 前1条
1 王飞;员工激励中的5“R”[N];中国商报;2012年
中国知网广告投放
 快捷付款方式  订购知网充值卡  订购热线  帮助中心
  • 400-819-9993
  • 010-62982499
  • 010-62783978