检索结果-内蒙古大学图书馆

International Conference on Knowledge, Information and Creativity Support Systems (KICSS)

作者： Prasert Luekhong Rattasit Sukhauta Peerachet Porkaew Taneth Ruangrajitpakorn Thepchai Supnithi College of Integrated Science and Technology Rajamangala University of Technology Lanna Chiang Mai Thailand Computer Science Department Chiang Mai University Chiang Mai Thailand Language and Semantic Technology Laboratory National Electronics and Computer Technology Center Thailand National Electronics and Computer Technology Center Pathum Thani Pathum Thani TH

To set an appropriate goal of SMT research for Thai-based translation, the comparative study of potential and suitability between phrase-based translation (PBT) and hierarchical phrase-based translation (HPBT) becomes an initial question. Thai-Chinese language-pair is chosen as experimental subject since they share most of common syntactic pattern and Chinese resource is numerous. Based on standard setting, we gain a result that 3-gram HPBT gains significantly better BLEU point over 3-gram PBT while 3-gram HPBT is approximately equal to 5-gram PBT. Moreover, from the results, a Chinese-to-Thai translation obtains better accuracies than a Thai-to-Chinese translation from every approach.

关键词： Hidden Markov models Training Decoding Pragmatics Training data Feature extraction Syntactics

来源：评论

学校读者我要写书评

暂无评论

Poster abstracts

引用

Sleep and Biological Rhythms 2016年第1期5卷 A1-A189页

作者： J. Ferrie M. Shipley F. Cappuccio E. Brunner M. Miller M. Kumari M. Marmot A. Coenen J. L. Castillo F. Araya G. Bustamante L. Montecino C. Torres S. Oporto J. Gronli E. Fiske R. Murison B. Bjorvatn E. Sorensen R. Ursin C. M. Portas S. Rajaraman A. Gribok N. Wesensten T. Balkin J. Reifman N. Dursunoglu S. Ozkurt S. Baser O. Delen S. Sarikaya P. Sadler P. Mitchell D. Françon M. Decobert B. Herve A. Richard G. Griebel P. Avenet B. Scatton G. L. Fur D. Eckert A. Jordan A. Wellman S. Smith A. Malhotra D. White D. Bruck I. Thomas A. Kritikos W. Oertel K. Stiasny-Kolster D. Garcia-Borreguero W. Poewe B. Hoegl R. Kohnen E. Schollmayer J. Keffel C. Trenkwalder A. Valle S. Roizenblatt F. Fregni P. Boggio S. Tufik K. Ward L. Robertson L. Palmer P. Eastwood D. Hillman J. Lee S. Mukherjee V. de Padova G. Barbato G. Ficca I. Zilli P. Salzarulo M. Veldi T. Hion V. Vasar M. Kull L. Nowak J. Davis Y. Latzer O. Tzischinsky S. Crowley M. Carskadon M. Anca-Herschkovitsch D. Frey J. Ortega C. Wiseman C. Farley K. Wright A. Campbell A. Neill K. Spiegel R. Leproult E. Tasali N. Scherberg E. van Cauter A. T. Noradina N. A. Karim I. Norlinah A. A. Raymond R. Sahathevan B. Hamidon E. Werth R. Poryazova R. Khatami C. Bassetti R. G. Beran L. Ainley G. Holand J. Duncan H. Kinney B. Davis B. Hood S. Frey C. Schmidt M. Hofstetter P. Peigneux C. Cajochen W.-P. Hu J.-D. Li C. Zhang L. Boehmer J. Siegel Q.-Y. Zhou Y. Sagawa H. Kondo T. Takemura H. Kanayama Y. Kaneko M. Sato T. Kanbayashi Y. Hishikawa T. Shimizu A. Viola L. James L. Schlangen D.-J. Dijk R. Andretic Y.-C. Kim K.-A. Han F. Jones R. Greenspan L. Sanford L. Yang X. Tang K. Dieter E. Uta H. Sven M. Richard N. Oyane S. Pallesen F. Holsten Y. Inoue M. Fujita N. Emura K. Kuroda N. Uchimura A. Johnston J. Astbury G. Kennedy K. Hoedlmoser M. Schabus T. Pecherstorfer S. Moser G. Gruber P. Anderer W. Klimesch N. Naidoo M. Ferber A. Pack D. Neu O. Mairesse G. Hoffmann A. Dris L. Lambrecht P. Linkowski P. Verbanck O. Le Bon N. Matsuura M. Yamao N. Adachi R. Aritomi Y. Komada H. Tanaka S. Shirak University College London London UK University College London London USA Warwick Medical School London UK Warwick Medical School Coventry USA Radboud University Nijmegen Nijmegen Netherlands Department of Neurology University of Chile Santiago Chile Neurology Service Hospital del Salvador Santiago Chile Family Health Center Juan Pablo II Santiago Chile Department of Biomedicine Section on Physiology Univeristy of Bergen Bergen Norway Department of Public Health and Primary Health Care Univeristy of Bergen Bergen Norway Department of Public Health and Primary Health Care University of Bergen Bergen Norway Norwegian Competence Center for Sleep Disorders Haukeland University Hospital Bergen Norway Department of Child and Adolescent Psychiatry Haukeland University Hospital Univeristy of Bergen Bergen Norway Department of Biomedicine University of Bergen Bergen Norway US Army Medical Research and Materiel Command Fort Detrick Frederick USA Walter Reed Army Institute of Research Silver Spring USA Department of Behavioral Biology Walter Reed Army Institute of Research Silver Spring USA Faculty Department of Pulmonology Pamukkale University Medical Denizli Turkey University of Ballarat Ballarat Australia Sanofi-Aventis Recherche et Developpement Paris France Brigham and Women’s Hospital Harvard Medical School Boston USA The University of Queensland Adelaide Australia School of Psychology University of Queensland Brisbane Australia The University of Queensland Brisbane Australia Victoria University Melbourne Australia Department of Psychology Victoria University Melbourne Australia School of Psychology Victoria University Melbourne Australia Philips-Universität Marburg Germany Philips-Universitaet-Marburg Marburg Germany Instituto de Investigaciones del Sueno Madrid Spain Universitätsklinik für Neurologie Innsbruck Austria Universitaetsklinik fuer Neurologie Innsbruck Austria IMEREM GmbH Nuernberg Germany Schwarz Pharma AG Monheim Germany

来源：评论

学校读者我要写书评

暂无评论

Text-Dependent Speaker Recognition with long-term features based on functional data analysis

Text-Dependent Speaker Recognition with long-term features b...

引用

International Symposium on Chinese Spoken language Processing

作者： Chenhao Zhang Thomas Fang Zheng Ruxin Chen Center for Speech and Language Technologies Division of Technical Innovation and Development Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing China Research and Development Sony Computer Entertainment America Foster City CA USA

Text-Dependent Speaker Recognition (TDSR) is widely used nowadays. The short-term features like Mel-Frequency Cepstral Coefficient (MFCC) have been the dominant features used in traditional Dynamic Time Warping (DTW) based TDSR systems. The short-term features capture better local portion of the significant temporal dynamics but worse in overall sentence statistical characteristics. Functional Data Analysis (FDA) has been proven to show significant advantage in exploring the statistic information of data, so in this paper, a long-term feature extraction based on MFCC and FDA theory is proposed, where the extraction procedure consists of the following steps: Firstly, the FDA theory is applied after the MFCC feature extraction; Secondly, for the purpose of compressing the redundant data information, new feature based on the Functional Principle Component Analysis (FPCA) is generated; Thirdly, the distance between train features and test features is calculated for the use of the recognition procedure. Compared with the existing MFCC plus DTW method, experimental results show that the new features extracted with the proposed method plus the cosine similarity measure demonstrates better performance.

关键词： Mel frequency cepstral coefficient Feature extraction Speech Speech recognition Speaker recognition Data analysis Fitting

来源：评论

学校读者我要写书评

暂无评论

Asymmetric acoustic model for accented speech recognition

Asymmetric acoustic model for accented speech recognition

引用

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference 2011, APSIPA ASC 2011

作者： Zhang, Chao Liu, Yi Zheng, Thomas Fang Tsinghua National Laboratory for Information Science and Technology Division of Technology Innovation and Development Center for Speech and Language Technologies Beijing China Department of Computer Science and Technology Tsinghua University Beijing China

We propose to improve accented speech recognition performance by using asymmetric acoustic model. Our proposed model is generated based on reliable accent specific units and acoustic model reconstruction. The reliable units are extracted with time alignment recognition to cover accent variations at both acoustic and phonetic levels. The asymmetric acoustic model is obtained through selective decision tree merging together with dynamic Gaussian component selection in model reconstruction. The improved resolution of our proposed model is able to handle different levels of accented variations at different degrees. The effectiveness of our approach was evaluated on a typical Chinese accent. Our system outperforms traditional acoustic model reconstruction and MAP adaptation approaches by 8.28% and 7.14%, relatively on Syllable Error Rate (SER) reduction without sacrificing the performance on standard Mandarin speech.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

An in-car Chinese noise corpus for speech recognition

An in-car Chinese noise corpus for speech recognition

引用

2011 International Conference on Asian language Processing, IALP 2011

作者： Hou, Jue Liu, Yi Zhang, Chao Huang, Shilei Center for Speech and Language Technologies Division of Technology Innovation and Development Tsinghua National Laboratory for Information Science and Technology Beijing China Department of Computer Science and Technology Tsinghua University Beijing China Shenzhen Key Laboratory of Intelligent Media and Speech Shenzhen China

ISBN: (纸本)9780769545547

In this paper, we present an in-car Chinese noise corpus that can be used in simulating complicated car environment for robust speech recognition research and experiment. The corpus was collected in mainland China in 2009 and 2010. The corpus includes a diversity of car conditions including different car speed, open/close windows, weather conditions as well as environment conditions. Specially, the rumble strips are also taken into account due to the typical noise generated as the car is passing on. In order to use the corpus efficiently, we performed some acoustic signal analyses on those noise data, mainly focused on stationary properties and energy distribution in the frequency domain. We also performed ASR experiments using selected noise data from the corpus, by adding noise data to clean speech to simulate the in-car environment. The corpus is the first of its kind for in-car Chinese noise corpus, providing abundant and diversified samples for car noise speech recognition task. © 2011 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

A development of knowledge representation for Thalassemia prevention and control program

A development of knowledge representation for Thalassemia pr...

引用

7th International Conference on Natural language Processing and Knowledge Engineering, NLP-KE 2011

作者： Assawamakin, Anunchai Chalortham, Nopphadol Ruangrajitpakorn, Taneth Limwongse, Chanin Supnithi, Thepchai Tongsima, Sissades Biostatistics and Informatics Laboratory Genome Institute National Center for Genetic Engineering and Biotechnology Pathumthani Thailand Department of Health-Related Informatics Faculty of Pharmacy Silpakorn University Nakornpathom Thailand Language and Semantic Technology Laboratory National Electronics and Computer Technology Center Pathumthani Thailand Department of Research and Development Faculty of Medicine Siriraj Hospital Mahidol University Bangkok Thailand

ISBN: (纸本)9781612847283

The spreading of thalassemia, the most common genetic disease in tropical areas, is increasing due to a migration thus the prevention and control program (PCP) of Thalassemia has been established. To better promote the yet unsuccessful PCP for thalassemia, ontology called PCPThalOnto is developed. The proposed ontology represents domain knowledge while a list of executable production rule is generated to represent operational knowledge. The PCPThalOnto consists of 1) class component to represent concepts of strategies, methodologies, techniques and activities of the PCP and 2) relation component to link between those classes or class and its instance. In the production rules, conditions for individual case determination are employed to execute a proper action. The well-constructed knowledge representation of PCP for thalassemia is developed as an electronic knowledge base for future applications to efficiently disseminate the underlying knowledge to people bridging the gap that deter the success of PCP. © 2011 IEEE.

关键词： Knowledge representation

来源：评论

学校读者我要写书评

暂无评论

Asymmetric Acoustic Model for Accented Speech Recognition

Asymmetric Acoustic Model for Accented Speech Recognition

引用

2011年亚太信号与信息处理协会年会

作者： Thomas Fang Zheng Center for Speech and Language Technologies Division of Technology Innovation and Development Tsinghua National Laboratory for Information Science and Technology Beijing

关键词： Gaussian frame Asymmetric Acoustic Model for Accented Speech Recognition Model

来源：评论

学校读者我要写书评

暂无评论

A Universal Phoneme-Set Based language Independent Short Utterance Speaker Recognition

A Universal Phoneme-Set Based Language Independent Short Utt...

引用

第十一届全国人机语音通讯学术会议(NCMMSC2011)

作者： Nakhat FATIMA Xiaojun Wu Thomas Fang ZHENG ZHANG Chenhao WANG Gang Center for Speech and Language Technologies Division of Technical Innovation and DevelopmentTsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology Tsinghua University

来源：评论

学校读者我要写书评

暂无评论

Discrimination-Emphasized Mel-Frequency-Warping for Time-Varying Speaker Recognition

Discrimination-Emphasized Mel-Frequency-Warping for Time-Var...

引用

2011年亚太信号与信息处理协会年会

作者： Thomas Fang Zheng Center for Speech and Language Technologies Division of Technical Innovation and Development Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology Tsinghua University

Performance degradation with time varying is a generally acknowledged phenomenon in speaker recognition and it is widely assumed that speaker models should be updated from time to time to maintain representativeness. However, it is costly, user-unfriendly, and sometimes, perhaps unrealistic, which hinders the technology from practical applications. From a pattern recognition point of view, the time-varying issue in speaker recognition requires such features that are speakerspecific, and as stable as possible across time-varying sessions. Therefore, after searching and analyzing the most stable parts of feature space, a Discrimination-emphasized Mel-frequencywarping method is proposed. In implementation, each frequency band is assigned with a discrimination score, which takes into account both speaker and session information, and Melfrequency-warping is done in feature extraction to emphasize bands with higher scores. Experimental results show that in the time-varying voiceprint database, this method can not only improve speaker recognition performance with an EER reduction of 19.1%, but also alleviate performance degradation brought by time varying with a reduction of 8.9%.

关键词： session Discrimination-Emphasized Mel-Frequency-Warping for Time-Varying Speaker Recognition Mel

来源：评论

学校读者我要写书评

暂无评论

A Universal Phoneme-Set Based language Independent Short Utterance Speaker Recognition

A Universal Phoneme-Set Based Language Independent Short Utt...

引用

第十一届全国人机语音通讯学术会议

作者： Nakhat FATIMA Thomas Fang ZHENG Center for Speech and Language Technologies Division of Technical Innovation and Development Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and TechnologyTsinghua University

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：