检索结果-内蒙古大学图书馆

2010 IEEE Workshop on Spoken Language technology, SLT 2010

作者： Naptali, Welly Tsuchiya, Masatoshi Nakagawa, Seiichi Department of Computer Science and Engineering Toyohashi University of Technology Japan Information and Media Center Toyohashi University of Technology Japan

ISBN: (纸本)9781424479030

A topic dependent class (TDC) language model (LM) is a topic-based LM that uses a semantic extraction method to reveal latent topic information from noun-document relation. Then a clustering for a given context is performed to define topics. Finally, a fixed window of word history is observed to decide the topic of the current event through voting in online manner. Previously, we have shown that TDC overperforms several state-of-the-art baselines in terms of perplexity. In this paper we evaluate TDC on automatic speech recognition experiment (ASR) for rescoring task. Experiments on read speech Wall Street Journal (English ASR system) and Mainichi Shimbun (Japanese ASR system) show that TDC LM improves both perplexity and word-error-rate (WER). The result shows that the proposed model gives improvements 3.0% relative on perplexity and 15.2% relative on WER for English ASR system, and 16.4% relative on perplexity and 24.3% relative on WER for Japanese ASR system. ©2010 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Integration of cache-based model and topic dependent class model with soft clustering and soft voting

Integration of cache-based model and topic dependent class m...

引用

A topic dependent class (TDC) [1] language model (LM) is a topic-based LM that uses a semantic extraction method to reveal latent topic information from nouns relation. Then a clustering for a given context is performed to define topics. Finally, a fixed window of word history is observed to decide the topic of the current event through voting in online manner. Previously, we have shown that TDC overperforms several state-of-the-art baselines. There are two separate points that we would like to introduce in this paper. First, we improves the TDC further by incorporating cache-based LM through unigram scaling. The combination is possible since TDC only tried to capture topical words, and does not models re-occurring words, such as functional words, very well. Experiments on Wall Street Journal (WSJ) and Japanese newspaper (Mainichi Shimbun) corpora show that this combination improves the model significantly in terms of perplexity. Second, TDC stand-alone model suffers from shrinking training corpus size when the number of topics is increased. We solved this problem by performing soft-clustering and soft-voting on the training and test phase. Experiments result on WSJ corpus shows that TDC performance over perform the baseline without being needed to be interpolated with the word-based n-gram. © 2010 ISCA.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Effective covariance tracker based on adaptive changing of tracking window

Effective covariance tracker based on adaptive changing of t...

引用

作者： Lee, Jin-Wook Cho, Jae-Soo Department of Information Media Engineering Korea University of Technology and Education Cheonan Korea Republic of School of Computer and Science Engineering Korea University of Technology and Education Cheonan Korea Republic of

ISBN: (纸本)9781424474530

In this paper, we present an effective covariance tracking algorithm based on adaptive size changing of tracking window. Recent researches have advocated the use of a covariance matrix of object image features for tracking objects instead of the conventional histogram object representation models used in popular algorithms. The general covariance tracking algorithm has some problem of scale change of moving objects. Since the scale of the moving object often changes in time, the tracking(or object) window should be updated accordingly. In addition, the covariance matrix of moving objects should be adaptively changed considering the tracking window size. We propose a novel solution to this problem by segmenting the moving object from the background pixels in the tracking window. The proposed method will improve the tracking performance of the conventional covariance tracking. Our several simulations prove the effectiveness of the proposed one. ©ICROS.

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

Image watermarking based on adaptive models of human visual perception

IEEJ Transactions on Electronics, Information and Systems

引用

IEEJ Transactions on Electronics, information and Systems 2010年第9期130卷 1644-1656+19页

作者： Khawne, Amnach Hamamoto, Kazuhiko Chitsobhuk, Orachat Department of Information Media Technology School of Science and Technology Tokai University 4-1-1 Kitakaname Hiratsuka-shi Kanagawa 259-1292 Japan School of Computer Engineering Faculty of Engineering King Mongkut's Institute of Technology Ladkrabang 3 M 2 Chalongkrung Ladkrabang Bangkok 10520 Thailand

This paper proposes a digital image watermarking based on adaptive models of human visual perception. The algorithm exploits the local activities estimated from wavelet coefficients of each subband to adaptively control the luminance masking. The adaptive luminance is thus delicately combined with the contrast masking and edge detection and adopted as a visibility threshold. With the proposed combination of adaptive visual sensitivity parameters, the proposed perceptual model can be more appropriate to the different characteristics of various images. The weighting function is chosen such that the fidelity, imperceptibility and robustness could be preserved without making any perceptual difference to the image quality. © 2010 The Institute of Electrical Engineers of Japan.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

Extending the concept of tensor product modelling for delayed systems

Extending the concept of tensor product modelling for delaye...

引用

8th IEEE International Symposium on Intelligent Systems and Informatics, SIISY 2010

作者： Galambos, Péter Baranyi, Péter Korondi, Péter Computer and Automation Research Institute Hungarian Academy of Sciences Budapest Hungary Department of Manufacturing Science and Technology Budapest University of Technology and Economics Hungary Department of Telecommunications and Media Informatics Budapest University of Technology and Economics Hungary Department of Mechatronics Optics and Information Engineering Budapest University of Technology and Economics Hungary

ISBN: (纸本)9781424473946

Feedback delays are inherent attributes of distributed control systems that usually cause unfavorable effect on the stability of the controlled process. Modelling of such systems is essential for traceable controller synthesis. In this paper we apply the TP Model Transformation to derive a polytopic representation of an LPV model where the time-delay is considered as parameter. The method is introduced via a single degree of freedom impedance model with feedback delay. The resulted model is validated by simulation. ©2010 IEEE.

关键词： Distributed parameter control systems

来源：评论

学校读者我要写书评

暂无评论

Cooperative MIMO transmission scheme for the DVB-T2 system

Cooperative MIMO transmission scheme for the DVB-T2 system

引用

2010 International Conference on information and Communication technology Convergence, ICTC 2010

作者： Ji, Soonbae Kim, Junghyun You, Cheolwoo Cho, Sunghyun Kim, Dongho Lee, Yehoon Department of Information and Communication Engineering Myong-Ji University Yongin Korea Republic of Department of Computer Science Gyeongsang National University Jinju Korea Republic of Department of Media Engineering and Electronic and Information Engineering Seoul National University of Science and Technology Seoul Korea Republic of

ISBN: (纸本)9781424498062

The Digital Video Broadcasting second generation Terrestrial (DVB-T2)standard purposes to provide high definition digital video and high rate services forthe same spectrum allocation of the current Digital Video Broadcasting Terrestrial (DVB-T)*** implementation guideline is provided by the DVB-T2standardization community,the Digital Video Broadcasting(DVB) *** DVB Project is requesting the many submission technologies which could be considered as candidates for asecond generation terrestrial transmission system. The most challenging requirements introduced by the DVB-T2 specification are an Fast Fourier Transform (FFT) size of up to 32k samples, 256-Quadrature amplitude modulation (QAM) and Low-Density Parity-Check (LDPC) coding with ablock size of 64k *** increasing concern in Multiple-Input Multiple-Output (MIMO) systems has given riseto numerous research activities in recent *** this paper,we propose the MIMO architecture and coded cooperative MIMO transmission scheme for DVB-T2 system. The simulation result of the proposal MIMO architecture in DVB-T2 system shows a definite performance improvement forcoded cooperative MIMO system. © 2010 IEEE.

关键词： Fast Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Control design for impedance model with feedback delay

Control design for impedance model with feedback delay

引用

19th International Workshop on Robotics in Alpe-Adria-Danube Region, RAAD 2010

ISBN: (纸本)9781424468867

In haptic and telemanipulation devices stability and transparency are contradicting requirements. Due to the network delay the control process may become unstable. In our research we consider the coupled impedance type control algorithms for force reflecting telemanipulation. There are several solutions in the control literature to handle constant time delay in feedback systems, but varying delay is still a challenge. This paper attempt to handle varying delay by a novel approach. We propose a control structure where the system with feedback delay is approximated by a non-delayed model with modified time constants. The controller is designed according to this non-delayed substitute system and the control signal is computed using its observed state vector. Tensor Product (TP) Model Transformation is utilized to make a compact polytopic representation of the observer and controller for various time delays. In this method the actual value of the feedback delay is considered as an input parameter of the TP type controller and observer. As example, a single degree of freedom impedance model with feedback delay is discussed. The results are confirmed by numerical simulation. © 2010 IEEE.

关键词： Time delay

来源：评论

学校读者我要写书评

暂无评论

An adaptive medium access control scheme for mobile ad hoc networks under self-similar traffic

An adaptive medium access control scheme for mobile ad hoc n...

引用

作者： Abu-Tair, Mamun Min, Geyong Ni, Qiang Liu, Hong Institute of Electronics Communications and Information Technology Queens University Belfast Belfast United Kingdom Department of Computing School of Computing Informatics and Media University of Bradford Bradford United Kingdom Electronic and Computer Engineering Division School of Engineering and Design Brunel University West London United Kingdom School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

An important function of wireless networks is to support mobile computing. Mobile Ad hoc NETworks (MANETs) consist of a collection of mobile stations communicating with each other without the use of any pre-existent infrastructure. The self-organization characteristic of MANETs makes them suitable for many real-world applications where network topology changes frequently. As a result, the development of efficient MAC (Medium Access Control) protocols in MANETs is extremely challenging. Self-similar traffic with scale-invariant burstiness can generate bursty network loads and thus seriously degrade the system performance. This paper presents an adaptive MAC scheme which dynamically adjusts the increasing function and resetting mechanism of contention window based on the status of network loads. The performance of this scheme is investigated in comparison with the legacy DCF (Distributed Coordination Function) under self-similar traffic and different mobility models. The performance results reveal that the proposed scheme is able to achieve the higher throughput and energy efficiency as well as lower end-to-end delay and packet drop probability than the legacy DCF. © 2009 Springer Science+Business media, LLC.

关键词： Medium access control

来源：评论

学校读者我要写书评

暂无评论

Load distribution algorithm based on transcoding time estimation for distributed transcoding servers

Load distribution algorithm based on transcoding time estima...

引用

2010 International Conference in information Science and Applications, ICISA 2010

作者： Seo, Dongmahn Kim, Jongwoo Jung, Inbum Imaging Media Center Robotics/Systems Division Korea Institute of Science and Technology Seoul 136-791 Korea Republic of Department of Computer and Communications Engineering College of Information Technology Kangwon National University Chuncheon Gangwon 200-701 Korea Republic of

ISBN: (纸本)9781424459438

As a result of improvements in wireless communication technologies, a multimedia data streaming service can be provided for mobile clients such as PDAs and cellular phones. Because mobile devices have low computing power and work on a low network bandwidth, a transcoding technology is needed to adapt the original streaming media for mobile environments. To provide quality of service, original encoded media are transcoded within limited time and transmitted to clients without ceasing and jittering phenomena. In particular, when large-scale mobile clients demand streaming services, load distribution methods among distributed transcoding servers have a tremendous impact on the total number of quality of service streams. In this paper, a new load distribution method is proposed based on transcoding time estimation with transcoding servers' information, movie information and target transcoding bit-rate. In experiments, the proposed method produces the best performance scalability according to the increase of transcoding servers. ©2010 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Topic dependent class based language model evaluation on automatic speech recognition

Topic dependent class based language model evaluation on aut...

引用

IEEE Spoken Language technology Workshop

作者： Welly Naptali Masatoshi Tsuchiya Seiichi Nakagawa Department of Computer Science and Engineering Toyohashi University of Technology Japan Information and Media Center Toyohashi University of Technology Japan

关键词： Speech recognition Training Hidden Markov models History Vocabulary Semantics Speech

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：