检索结果-内蒙古大学图书馆

26th International Conference on Computational Linguistics, COLING 2016

作者： Fung, Pascale Dey, Anik Bin Siddique, Farhad Lin, Ruixi Yang, Yang Bertero, Dario Yan, Wan Yin, Ricky Chan Ho Wu, Chien-Sheng Human Language Technology Center Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong

ISBN: (纸本)9784879747037

Zara, or 'Zara the Supergirl' is a virtual robot, that can exhibit empathy while interacting with an user, with the aid of its built in facial and emotion recognition, sentiment analysis, and speech module. At the end of the 5-10 minute conversation, Zara can give a personality analysis of the user based on all the user utterances. We have also implemented a real-time emotion recognition, using a CNN model that detects emotion from raw audio without feature extraction, and have achieved an average of 65.7% accuracy on six different emotion classes, which is an impressive 4.5% improvement from the conventional feature based SVM classification. Also, we have described a CNN based sentiment analysis module trained using out-of-domain data, that recognizes sentiment from the speech recognition transcript, which has a 74.8 F-measure when tested on human-machine dialogues. © COLING 2016 - 26th International Conference on Computational Linguistics, Proceedings of COLING 2016: System Demonstrations.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

The RWTH Aachen University English-Romanian Machine Translation System for WMT 2016 1

The RWTH Aachen University English-Romanian Machine Translat...

引用

1st Conference on Machine Translation, WMT 2016, held at the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016

作者： Peter, Jan-Thorsten Alkhouli, Tamer Guta, Andreas Ney, Hermann Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University AachenD-52056 Germany

ISBN: (纸本)9781945626104

This paper describes the statistical machine translation system developed at RWTH Aachen University for the English→Romanian translation task of the ACL 2016 First Conference on Machine Translation (WMT 2016). We combined three different state-of the- art systems in a system combination: A phrase-based system, a hierarchical phrase-based system and an attentionbased neural machine translation system. The phrase-based and the hierarchical phrase-based systems make use of a language model trained on all available data, a language model trained on the bilingual data and a word class language model. In addition, we utilized a recurrent neural network language model and a bidirectional recurrent neural network translation model for reranking the output of both systems. The attention-based neural machine translation system was trained using all bilingual data together with the backtranslated data from the News Crawl 2015 corpora. © 2016 Association for Computational Linguistics.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Speaker segmentation using deep speaker vectors for fast speaker change scenarios

Speaker segmentation using deep speaker vectors for fast spe...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Renyu Wang Mingliang Gu Lantian Li Mingxing Xu Thoms Fang Zheng School of Linguistic Science Jiangsu Normal University Xuzhou 221116 China Center for Speech and Language Technologies Division of Technical Innovation and Development Tsinghua National Laboratory for Information Science and Technology Research Institute of Information Technology Department of Computer Science and Technology

ISBN: (纸本)9781509041183

A novel speaker segmentation approach based on deep neural network is proposed and investigated. This approach uses deep speaker vectors (d-vectors) to represent speaker characteristics and to find speaker change points. The d-vector is a kind of frame-level speaker discriminative feature, whose discriminative training process corresponds to the goal of discriminating a speaker change point from a single speaker speech segment in a short time window. Following the traditional metric-based segmentation, each analysis window contains two sub-windows and is shifting along the audio stream to detect speaker change points, where the speaker characteristics are represented by the means of deep speaker vectors for all frames in each window. Experimental investigations conducted in fast speaker change scenarios show that the proposed method can detect speaker change points more quickly and more effectively than the commonly used segmentation methods.

关键词： Speaker segmentation deep neural networks speaker vector Loudspeakers

来源：评论

学校读者我要写书评

暂无评论

development of tactile-proprioceptive display and effect evaluation of local area vibration presentation method

Development of tactile-proprioceptive display and effect eva...

引用

作者： Sakai, Tadahiro Handa, Takuya Sakajiri, Masatsugu Shimizu, Toshihiro Hiruma, Nobuyuki Onishi, Junji Advanced Technology Development and Research Division NHK Engineering System Inc. 1-10-11 Kinuta Setagaya-ku Tokyo Japan Human Interface Research Division NHK Science and Technology Research Laboratories 1-10-11 Kinuta Setagaya-ku Tokyo Japan Department of Computer Science Faculty of Faculty of Health Science Tsukuba University of Technology 4-12-7 Kasuga Tsukuba Ibaraki305-8521 Japan

We propose a new method of presenting two-dimensional information, such as figures and graphs, on a tactile display so that visually impaired people are able to perceive them quickly and accurately. The new presentation method is developed for a tactile-proprioceptive display, which can present information on not only conventional "concave-convex" tactile display, but also vibration presentation in arbitrary area on a tactile display and mechanical leading presentation by mechanically leading user's fingers using haptic device. In this paper, we outline the abovementioned two presentation method and the developed tactile-prop display, and objectively evaluate the effects of the local area vibration presentation method as an integral part of the tactile-prop display in comparison with the conventional "concave-convex" presentation method. We conducted experiments to evaluate the effects of the proposed local area vibration presentation method using two typical content patterns. In Experiment 1, discreetly dispersed objects are searched, and in Experiment 2, the cross graphs of line segments are distinguished and perceived. The experiments have proved that the method is effective in reducing search and cognitive time as well as identifying the correct cognition of cross graphs, as compared to the "concave-convex" tactile presentation method.

关键词： Display devices

来源：评论

学校读者我要写书评

暂无评论

Correction to: A lightweight signcryption scheme for defense against fragment duplication attack in the 6LoWPAN networks

引用

Peer-to-Peer Networking and Applications 2018年第1期12卷 227-227页

作者： Nikravan, Mohammad Movaghar, Ali Hosseinzadeh, Mehdi Faculty of Electrical and Computer Engineering Islamic Azad University Science and Research Branch Tehran Iran Department of Computer Engineering Sharif University of Technology Tehran Iran Iran University of Medical Sciences Tehran Iran Computer Science University of Human Development Sulaimaniyah Iraq

The Publisher regrets an incorrect figure was placed in the pdf version of the article.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Genetic analysis of over 1 million people identifies 535 new loci associated with blood pressure traits (vol 50, pg 1412, 2018)

引用

NATURE GENETICS 2018年第12期50卷 1755-1755页

作者： Evangelou, Evangelos Warren, Helen R. Mosen-Ansorena, David Mifsud, Borbala Pazoki, Raha Gao, He Ntritsos, Georgios Dimou, Niki Cabrera, Claudia P. Karaman, Ibrahim Fu Liang Ng Evangelou, Marina Witkowska, Katarzyna Tzanis, Evan Hellwege, Jacklyn N. Giri, Ayush Edwards, Digna R. Velez Sun, Yan V. Cho, Kelly Gaziano, J. Michael Wilson, Peter W. F. Tsao, Philip S. Kovesdy, Csaba P. Esko, Tonu Magi, Reedik Milani, Lili Almgren, Peter Boutin, Thibaud Debette, Stephanie Ding, Jun Giulianini, Franco Holliday, Elizabeth G. Jackson, Anne U. Li-Gao, Ruifang Lin, Wei-Yu Luan, Jian'an Mangino, Massimo Oldmeadow, Christopher Prins, Bram Peter Qian, Yong Sargurupremraj, Muralidharan Shah, Nabi Surendran, Praveen Theriault, Sebastien Verweij, Niek Willems, Sara M. Zhao, Jing-Hua Amouyel, Philippe Connell, John de Mutsert, Renee Doney, Alex S. F. Farrall, Martin Menni, Cristina Morris, Andrew D. Noordam, Raymond Pare, Guillaume Poulter, Neil R. Shields, Denis C. Stanton, Alice Thom, Simon Abecasis, Goncalo Amin, Najaf Arking, Dan E. Ayers, Kristin L. Barbieri, Caterina M. Batini, Chiara Bis, Joshua C. Blake, Tineka Bochud, Murielle Boehnke, Michael Boerwinkle, Eric Boomsma, Dorret I. Bottinger, Erwin P. Braund, Peter S. Brumat, Marco Campbell, Archie Campbell, Harry Chakravarti, Aravinda Chambers, John C. Chauhan, Ganesh Ciullo, Marina Cocca, Massimiliano Collins, Francis Cordell, Heather J. Davies, Gail de Borst, Martin H. de Geus, Eco J. Deary, Ian J. Deelen, Joris Del Greco, Fabiola M. Demirkale, Cumhur Yusuf Dorr, Marcus Ehret, Georg B. Elosua, Roberto Enroth, Stefan Erzurumluoglu, A. Mesut Ferreira, Teresa Franberg, Mattias Franco, Oscar H. Gandin, Ilaria Gasparini, Paolo Giedraitis, Vilmantas Gieger, Christian Girotto, Giorgia Goel, Anuj Gow, Alan J. Gudnason, Vilmundur Guo, Xiuqing Gyllensten, Ulf Hamsten, Anders Harris, Tamara B. Harris, Sarah E. Hartman, Catharina A. Havulinna, Aki S. Hicks, Andrew A. Hofer, Edith Hofman, Albert Hottenga, Jouke-Jan Huffman, Jennifer E. Hwang, Shih-Jen Ingelsson, Erik James, Alan Jansen Department of Epidemiology and Biostatistics Imperial College London London UK Department of Hygiene and Epidemiology University of Ioannina Medical School Ioannina Greece William Harvey Research Institute Barts and The London School of Medicine and Dentistry Queen Mary University of London London UK National Institute for Health Research Barts Cardiovascular Biomedical Research Center Queen Mary University of London London UK MRC-PHE Centre for Environment and Health Imperial College London London UK Department of Mathematics Imperial College London London UK Division of Epidemiology Department of Medicine Institute for Medicine and Public Health Vanderbilt Genetics Institute Vanderbilt University Medical Center Tennessee Valley Healthcare System (626)/Vanderbilt University Nashville TN USA Vanderbilt Genetics Institute Vanderbilt Epidemiology Center Department of Obstetrics and Gynecology Vanderbilt University Medical Center Tennessee Valley Health Systems VA Nashville TN USA Department of Epidemiology Emory University Rollins School of Public Health Atlanta GA USA Department of Biomedical Informatics Emory University School of Medicine Atlanta GA USA Massachusetts Veterans Epidemiology Research and Information Center (MAVERIC) VA Boston Healthcare System Boston MA USA Division of Aging Department of Medicine Brigham and Women’s Hospital Department of Medicine Harvard Medical School Boston MA USA Atlanta VAMC and Emory Clinical Cardiovascular Research Institute Atlanta GA USA VA Palo Alto Health Care System Division of Cardiovascular Medicine Stanford University School of Medicine Stanford CA USA Nephrology Section Memphis VA Medical Center and University of Tennessee Health Science Center Memphis TN USA Estonian Genome Center University of Tartu Tartu Estonia Program in Medical and Population Genetics Broad Institute of Harvard and MIT Cambridge MA USA Department Clinical Sciences Malmö Lund University Malmö Sweden MRC Human Genetics Un

High blood pressure is a highly heritable and modifiable risk factor for cardiovascular disease. We report the largest genetic association study of blood pressure traits (systolic, diastolic and pulse pressure) to date in over 1 million people of European ancestry. We identify 535 novel blood pressure loci that not only offer new biological insights into blood pressure regulation but also highlight shared genetic architecture between blood pressure and lifestyle exposures. Our findings identify new biological pathways for blood pressure regulation with potential for improved cardiovascular disease prevention in the future.

关键词： Cardiovascular diseases Genome informatics Genome-wide association studies

来源：评论

学校读者我要写书评

暂无评论

Dijkstra algorithm applied: Design and implementation of a framework to find nearest hotels and booking systems in Iraqi

Dijkstra algorithm applied: Design and implementation of a f...

引用

2017 International Conference on Current Research in computer science and Information Technology, ICCIT 2017

作者： Ahmed, Aram M. Ahmed, Sarkar Hasan Ahmed, Omed Hassan Kurdistan Institution for Strategic Studies and Scientific Research Department of Information Technology 10 Alley 60 Gullabax 335 Shorsh St. Opp. Shoresh Hosp. Sulaimani Kurdistan Region Iraq Sulaimani Polytechnic University Computer Science Institute Qirga Wrme St. Mardin 327 Alley 76 Iraq University of Human Development College of Science and Technology Kurdistan Region Binary Goizha Sulaimani Iraq

ISBN: (纸本)9781538629550

This paper was primarily conducted to develop an Online Booking System where users can search for different varieties of hotels and are able to sort them according to their price, number of stars or their location distance to any particular place in the city. Once the hotel is selected, Users are able to guess the fastest routes to all the tourist attraction places and restaurants nearby each hotel using Dijkstra algorithm. The system is more designed to help Iraqi tourists to prior explore and reserve rooms during peak times, Therefore, one if the main goal of the system is to adopt a payment agent that fits situation. This is because banking systems is not as efficient as it supposed to be. Hence, users are able to do the payment process through Visa cards or through their cell phones using payment services providers like Asia hawala or Zain Cash. Agile methodology, as one of the software engineering models has been used to design and implement this approach. © 2017 IEEE.

关键词： Hotels

来源：评论

学校读者我要写书评

暂无评论

Real-time speech emotion and sentiment recognition for interactive dialogue systems

Real-time speech emotion and sentiment recognition for inter...

引用

2016 Conference on Empirical Methods in Natural language Processing, EMNLP 2016

作者： Bertero, Dario Siddique, Farhad Bin Wu, Chien-Sheng Wan, Yan Chan, Ricky Ho Yin Fung, Pascale Human Language Technology Center Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Clear Water Bay Hong Kong

ISBN: (纸本)9781945626258

In this paper, we describe our approach of enabling an interactive dialogue system to recognize user emotion and sentiment in real-time. These modules allow otherwise conventional dialogue systems to have "empathy" and answer to the user while being aware of their emotion and intent. Emotion recognition from speech previously consists of feature engineering and machine learning where the first stage causes delay in decoding time. We describe a CNN model to extract emotion from raw speech input without feature engineering. This approach even achieves an impressive average of 65.7% accuracy on six emotion categories, a 4.5% improvement when compared to the conventional feature based SVM classification. A separate, CNN-based sentiment analysis module recognizes sentiments from speech recognition results, with 82.5 F-measure on human-machine dialogues when trained with out-of-domain data. © 2016 Association for Computational Linguistics

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Dijkstra algorithm applied: Design and implementation of a framework to find nearest hotels and booking systems in Iraqi

Dijkstra algorithm applied: Design and implementation of a f...

引用

International Conference on Current Research in computer science and Information Technology (ICCIT)

作者： Aram M. Ahmed Sarkar Hasan Ahmed Omed Hassan Ahmed Department of Information Technology Kurdistan Institution for Strategic Studies and Scientific Research Sulaimani Kurdistan Region Iraq Sulaimani Polytechnic University Computer Science Institute College of Science and Technology University of Human Development Sulaimani Kurdistan Region Iraq

ISBN: (纸本)9781538629567

关键词： Algorithm design and analysis Software computer science Databases Information technology Asia Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

A long short-term memory framework for predicting humor in dialogues 15

A long short-term memory framework for predicting humor in d...

引用

15th Conference of the North American Chapter of the Association for Computational Linguistics: human language Technologies, NAACL HLT 2016

作者： Bertero, Dario Fung, Pascale Human Language Technology Center Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Clear Water Bay Hong Kong Hong Kong

ISBN: (纸本)9781941643914

We propose a first-ever attempt to employ a Long Short-Term memory based framework to predict humor in dialogues. We analyze data from a popular TV-sitcom, whose canned laughters give an indication of when the audience would react. We model the setup-punchline relation of conversational humor with a Long Short-Term Memory, with utterance encodings obtained from a Convolutional Neural Network. Out neural network framework is able to improve the F-score of 8% over a Conditional Random Field baseline. We show how the LSTM effectively models the setup-punchline relation reducing the number of false positives and increasing the recall. We aim to employ our humor prediction model to build effective empathetic machine able to understand jokes. ©2016 Association for Computational Linguistics.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：