检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Tiago Fernandes Tavares Jayme Garcia Arnal Barbedo Romis Attux Amauri Lopes School of Electrical and Computer Engineering University of Campinas Campinas Sao Paulo Brazil Embrapa Agricultural Informatics Campinas Sao Paulo Brazil

ISBN: (纸本)9781479903573

A common approach to the detection of simultaneous musical notes in an acoustic recording involves defining a function that yields activation levels for each candidate musical note over time. These levels tend to be high when the note is active and low when it is not. Therefore, by applying a simple threshold decision process, it is possible to decide whether each note is active or not at a given time. Such a threshold, in general, is hard to set and has no physical meaning. In this paper, it is shown that the rhythmic characteristic of the musical signal may be used to obtain a suitable threshold. The proposed method for obtaining the threshold is shown to have a greater generalization capability over different databases.

关键词： Databases Training Speech Signal processing algorithms Speech processing Educational institutions

来源：评论

学校读者我要写书评

暂无评论

Lossless compression with moderate error probability

Lossless compression with moderate error probability

引用

IEEE International Symposium on Information Theory

作者： Yücel Altuğ Aaron B. Wagner Ioannis Kontoyiannis School of Electrical and Computer Engineering Cornell University Ithaca NY USA Department of Informatics Athens University of Economics and Business Athens Greece

ISBN: (纸本)9781479904440

For the problem of lossless compression of a memoryless source, we give a detailed, precise characterization of the best achievable error probability, in the “moderate error probability” regime. This is the asymptotic setting where the probability of error decays to zero while at the same time the rate converges to the entropy at a speed no faster than 1/√N. These results combine some of the essential benefits of earlier analyses in terms of error exponents and of Gaussian approximation. Analogous results for the problem of hypothesis testing are also established.

关键词： Error probability Channel coding Source coding Educational institutions Entropy

来源：评论

学校读者我要写书评

暂无评论

Resource allocation for WWAN video multicast with cooperative local repair

Resource allocation for WWAN video multicast with cooperativ...

引用

IEEE International Conference on Communications (ICC)

作者： Zhi Liu Yu Mao Ning Lu Yusheng Ji Xuemin Sherman Shen The Graduate University for Advanced Studies National Institute of Informatics Tokyo Japan Department of Electrical and Computer Engineering University of Waterloo Ontario Canada

The current coding standard employs differential coding to reduce the coding rate. Decoding error may propagate in the following frames after a loss-unrecoverable frame. Since most of the current electronic devices are implemented with multiple interfaces, such as the 3G and WiFi, one way to solve the error propagation problem is to use cooperative strategies, which leverage on the `uncorrelatedness' of the clients' channels (different channels may experience different channel losses). The cooperative strategies helping to repair the primary network's (base station to client) losses via the neighboring clients' packets sharing (client to client) through the second network interface and optimally allocating the modulation and coding schemes to the limited network resource can improve the clients' received quality massively. The inherent problem is how to solve the resource allocation problem with the cooperative strategies. In this paper, we jointly consider the resource allocation and the cooperative repair for the video streaming. We formulate the problem into the optimization problem, i.e. maximizing the clients' received video quality, and apply the structured network coding to further improve the overall performance. Simulation results show that the proposed approach outperforms the other competing schemes by at least 1.5dB in term of the received video quality in typical network scenarios.

关键词： Maintenance engineering Encoding Streaming media Base stations Resource management Forward error correction Wireless LAN

来源：评论

学校读者我要写书评

暂无评论

A novel approach based on joint optimization of alignment and statistical surface representation with wavelet transform for CBCT segmentation

A novel approach based on joint optimization of alignment an...

引用

9th International Meeting on Computational Intelligence Methods for Bioinformatics and Biostatistics, CIBB 2012

作者： Chang, Yu-Bing Yuan, Peng Kuo, Tai-Hong Xiong, Zixiang Gateno, Jaime Xia, James J. Zhou, Xiaobo Department of Electrical and Computer Engineering Texas A and M University College Station TX 77841 United States Department of Oral and Maxillofacial Surgery Methodist Hospital Research Institute Houston TX 77030 United States Department of Mechanical Engineering National Cheng Kung University Tainan Taiwan Center for Biotechnology and Informatics Methodist Hospital Research Institute Houston TX 77030 United States

ISBN: (纸本)9783642383410

Cone-beam computed tomography (CBCT) can provide true 3D information of anatomical structures, with advantages of much thinner slice thickness and significantly lowered effective dose of radiation. However, CBCT images are extremely low contract and noisy. It is very difficult to segment thin bones. It usually takes 4-5 hours to manually segment a set of CBCT data. To this end, we developed a novel approach based on the joint optimization of alignment and statistical surface representation with wavelet transform for segmentation of CBCT images. It included two main steps: customized wavelet base initialization (CWBI) and base invariant wavelet active shape model (BIWASM). We validated our approach with others by comparing the surface deviation between segmented shape to the ground truth. The results showed that our approach outperformed the others in accuracy and computing time. © 2013 Springer-Verlag.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Accurate acoustic echo reduction with residual echo power estimation for long reverberation

Accurate acoustic echo reduction with residual echo power es...

引用

134th Audio engineering Society Convention 2013

作者： Fukui, Masahiro Shimauchi, Suehiro Hioka, Yusuke Ohmuro, Hitoshi Haneda, Yoichi NTT Media Intelligence Laboratories NTT Corporation 3-9-11 Midori-cho Musashino-shi Tokyo 180-8585 Japan Department of Electrical and Computer Engineering University of Canterbury 20 Kirkwood Ave Ilam Christchurch 8041 New Zealand Faculty of Informatics and Engineering University of Electro-Communications 1-5-1 Chofugaoka Chofu-shi Tokyo 182-8585 Japan

ISBN: (纸本)9781627485715

This paper deals with the problem of estimating and reducing residual echo components that result from reverberant component beyond the length of FFT block. The residual echo reduction process suppresses the residual echo by applying a multiplicative gain calculated from the estimated residual echo power spectrum. However, the estimated power spectrum reproduces only a fraction of the echo-path impulse response and so all the reverberant component are not considered. To address this problem, we introduce a finite nonnegative convolution method by which each segment of echo-impulse response is convoluted with a received signal in a power spectral domain. With the proposed method, the power spectra of each segment of echo-impulse response are collectively estimated by solving the least-mean-squares problem between the microphone and the estimated-residual-echo power spectra. The performance of this method was demonstrated by simulation results in which speech distortions were decreased compared with the conventional method.

关键词： Impulse response

来源：评论

学校读者我要写书评

暂无评论

Multiple determination of chemical elements using a multi-objective evolutionary algorithm and multiple linear regression

Multiple determination of chemical elements using a multi-ob...

引用

2013 International Conference on Artificial Intelligence, ICAI 2013

作者： Soares, Anderson Da Silva De Lima, Telma Woerle De Lucena, Daniel Vitor Salvini, Rogerio Lopes Laureano, Gustavo Teodoro Coelho, Clarimar José Intitute of Informatics Federal University of Goiás Goiânia Brazil Department of Electrical Engineering University of São Paulo São Carlos Brazil Computer Science Departament Pontifical University Catholic of Goiás Goiânia Brazil

ISBN: (纸本)1601322488

The multiple determination task of chemical properties is a classical problem in analytical chemistry. The major problem is concerned in to find the best subset of variables that better represents the compounds. These variables are obtained by a spectrophotometer device. This device measure hundreds of correlated variables related with physicochemical properties and that can be used to estimate the component of interest. The problem is the selection of a subset informative and uncorrelated variables that help the minimization of prediction error. Classical algorithms select a subset of variables for each compound considered. In this work we propose the use of a multiobjective algorithm SPEA-II. We would like to show that the variable selection algorithm can selected just one subset used for multiple determination using multiple linear regression. For the case study is used wheat data obtained by NIR spectrometry where the objective is the determination of a variable subgroup with information about e Protein content (%), test weight (Kg/Hl), PSI (wheat kernel texture) (%) and farinograph water absorption (%). The results of traditional techniques of multivariate calibration as the Successive Projections Algorithm (SPA), Partial Least Square (PLS) and mono-objective genetic algorithm are presents for comparisons. For NIR spectral analysis of protein concentration on wheat, the number of variables selected from 775 spectral variables was reduced for just 10 in the SPEA-II algorithm. The prediction error decreased from 0.2 in the classical methods to 0.09 in proposed approach, a reduction of 37%. The model using variables selected by SPEA-II had better prediction performance than classical algorithms and full-spectrum partial least-squares (PLS).

关键词： Algorithms

来源：评论

学校读者我要写书评

暂无评论

Linear discriminant analysis based approachfor automatic speech recognition of urdu isolated words

Communications in Computer and Information Science

引用

Communications in computer and Information Science 2013年 414卷 24-34页

作者： Ali, Hazrat Ahmad, Nasir Zhou, Xianwei Ali, Muhammad Manjotho, Ali Asghar Department of Communication Engineering School of Computer and Communication Engineering University of Science and Technology Beijing Beijing10083 China Department of Computer Systems Engineering University of Engineering and Technology Peshawar Peshawar25120 Pakistan Department of Electrical and Computer Engineering North Dakota State University FargoND58108-6050 United States Department of Computer Systems Engineering Mehran University of Engineering and Technology Jamshoro Pakistan Machine Learning Group School of Informatics City University London LondonEC1V 0HB United Kingdom

Urdu is amongst the five largest languages of the world and enjoys extreme importance by sharing its vocabulary with several other languages of the Indo-Pak. However, there has not been any significant research in the area of Automatic Speech Recognition of Urdu. This paper presents the statistical based classification technique to achieve the task of Automatic Speech Recognition of isolated words in Urdu. For each isolated word, 52 Mel Frequency Cepstral Coefficients have been extracted and based upon these coefficients;the classification has been achieved using Linear Discriminant Analysis. As a prototype, the system has been trained with audio samples of seven speakers including male/female, native/non-native and speakers with different ages while the testing has been done using audio samples of three speakers. It was determined that majority of words exhibit a percentage error of less than 33%. Words with 100% error were declared to be bad words. The work reported in this paper may serve as a strong baseline for future research work on Urdu ASR, especially for continuous speech recognition of Urdu. © Springer International Publishing Switzerland 2014.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Multilayer processing architecture of RAM based neural network with memory optimization for navigation system

Multilayer processing architecture of RAM based neural netwo...

引用

Joint International Conference on Rural Information & Communication Technology and Electric-Vehicle Technology (rICT & ICeV-T)

作者： Ahmad Zarkasi Aciek Ida Wuryandari Rizki Fauzian Study Program Computer System Sriwijaya University South Sumatera Indonesia School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia

Robots also have been trusted to help human to complete difficult jobs, for example, finding for the earthquake, a fire, or a sinking ship victims. The robot must be reliable, clever and moving automatically. The aim of this study is to develop and apply the application of artificial RAM-based neural networks (WNNs) on a mobile robot using a multilayer processing architecture with memory optimizations on to address and input pattern, so that producing smart navigation model which it has a simpler computational load and faster execution time. The gained result from the first study was the percentage of memory optimization in the amount of 50%. This result obtained from the formerly RAM using 8 bit data width has been optimized to 4 bits. Both of the percentage of data optimization pattern is 93.75%. This percentage is obtained from the optimization pattern (pattern taken is 4 bits MSB), each 1 bit data can handle 15 unseen patterns.

关键词： Random access memory Optimization Sensors Nonhomogeneous media Mobile robots Decoding Biological neural networks

来源：评论

学校读者我要写书评

暂无评论

Maximum Hands-Off Control and L~1 Optimality

Maximum Hands-Off Control and L~1 Optimality

引用

IEEE Annual Conference on Decision and Control

作者： Masaaki Nagahara Daniel E. Quevedo Dragan Nesic Graduate School of Informatics Kyoto University Kyoto 606-8501 Japan School of Electrical Engineering & Computer Science The University of Newcastle NSW 2308 Australia Department of Electrical and Electronic Engineering The University of Melbourne Victoria 3010 Australia

ISBN: (纸本)9781467357159

In this article, we propose a new paradigm of control, called a maximum hands-off control. A hands-off control is defined as a control that has a much shorter support than the horizon length. The maximum hands-off control is the minimum support (or sparsest) control among all admissible controls. We first prove that a solution to an L~1-optimal control problem gives a maximum hands-off control, and vice versa. This result rationalizes the use of L~1 optimality in computing a maximum hands-off control. The solution has in general the "bang-off-bang" property, and hence the control may be discontinuous. We then propose an L~1/L~2-optimal control to obtain a continuous hands-off control. Examples are shown to illustrate the effectiveness of the proposed control method.

关键词： Standing Orders Control Methods optimality LU1 Discontinuous Admissible Control

来源：评论

学校读者我要写书评

暂无评论

Query expansion with a little help from twitter

Communications in Computer and Information Science

引用

Communications in computer and Information Science 2013年 384卷 20-29页

作者： Anagnostopoulos, Ioannis Razis, Gerasimos Mylonas, Phivos Anagnostopoulos, Christos-Nikolaos Computer Science and Biomedical Informatics Dpt. University of Thessaly Greece Electrical and Computer Engineering School National Technical University of Athens Greece Cultural Technology and Communication Dpt. University of the Aegean Greece

With the advent and rapid spread of microblogging services, web information management finds a new research topic. Although classical information retrieval methods and techniques help search engines and services to present an adequate precision in lower recall levels (top-k results), the constantly evolving information needs of microblogging users demand a different approach, which has to be adapted to the dynamic nature of On-line Social Networks (OSNs). In this work, we use Twitter as microblogging service, aiming to investigate the query expansion provision that can be extracted from large graphs, and compare it against classical query expansion methods that require mainly prior knowledge, such as browsing history records or access and management of search logs. We provide a direct comparison with mainstream media services, such as Google, Yahoo!, Bing, NBC and Reuters, while we also evaluate our approach by subjective comparisons in respect to the Google Hot Searches service. © Springer-Verlag Berlin Heidelberg 2013.

关键词： Social networking (online)

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：