检索结果-内蒙古大学图书馆

IEEE GCC Conference & Exhibition

作者： Mehdi Yektaeian Rassoul Amirfattahi Digital Signal Processing Research Laboratory Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan Iran

Auditory masking is aggressively exploited by algorithms used for the lossy compression of audio signals. In compression of audio signals, the intent is to hide the noise introduced by the coding below the masking threshold, thus making the noise inaudible. This will render the coding process transparent, enabling better compression without audible degradation of the signal. In this article, we show that using masking properties of the hearing system allows for improved noise reduction. A novel method for noise reduction in speech signals is proposed. This method is shown to outperform non-auditory based methods, and compares well with other perceptually motivated noise reduction methods. It is found that the proposed method, Soulodre's PNRF combined with the ITU's PEAQ auditory model, have more musical noise but less signal distortion than the method proposed by Tsoukalas, which obtain marginally better results in informal testing results.

关键词： Signal to noise ratio Noise reduction Speech Speech enhancement Masking threshold

来源：评论

学校读者我要写书评

暂无评论

Noise reduction algorithm for robust speech recognition using MLP neural network

Noise reduction algorithm for robust speech recognition usin...

引用

Pacific-Asia Workshop on Computational Intelligence and Industrial Application, PACIIA

作者： Masoumeh P. Ghaemmaghami Farbod Razzazi Hossein Sameti Saeed Dabbaghchian Bagher BabaAli Department of Electrical Engineering Science & Research Branch Azad University Tehran Iran Speech Processing Laboratory Department of Computer Engineering Sharif University of Technology Iran Department of Computer Engineering Speech Processing Lab Tehran Iran

We propose an efficient and effective nonlinear feature domain noise suppression algorithm, motivated by the minimum mean square error (MMSE) optimization criterion. Multi layer perceptron (MLP) neural network in the log spectral domain minimizes the difference between noisy and clean speech. By using this method as a pre-processing stage of a speech recognition system, the recognition rate in noisy environments is improved. We can extend the application of the system to different environments with different noises without re-training it. We need only to train the preprocessing stage with a small portion of noisy data which is created by artificially adding different types of noises from the NOISEX-92 database to the TIMIT speech database. Experimental results show that the proposed method can achieve significant improvement of recognition rates.

关键词： Noise reduction Noise robustness Speech recognition Neural networks Working environment noise Speech enhancement Feature extraction Application software Speech processing Databases

来源：评论

学校读者我要写书评

暂无评论

Signal processing for neural spike trains

引用

Computational intelligence and neuroscience 2010年第1期2010卷 698751页

作者： Theodore W Berger Zhe Sage Chen Andrzej Cichocki Karim G Oweiss Rodrigo Quian Quiroga Nitish V Thakor Department of Biomedical Engineering Viterbi School of Engineering University of Southern California Los Angeles CA 90089 USA Neuroscience Statistics Research Laboratory Massachusetts Institute of Technology Cambridge MA 02139 USA Laboratory for Advanced Brain Signal Processing RIKEN Brain Science Institute Wako-shi Saitama 351-0198 Japan Department of Electrical and Computer Engineering Michigan State University MI 48824 USA Department of Engineering University of Leicester Leicester LE1 7RH UK School of Medicine Johns Hopkins University Baltimore MD 21205 USA

来源：评论

学校读者我要写书评

暂无评论

Fuzzy controller for cooperative object pushing with variable line contact

Fuzzy controller for cooperative object pushing with variabl...

引用

International Conference on Mechatronics (ICM)

作者： Mahsa Aliakbar Golkar Sarah Taghavi Namin Hossein Aminaiee Control and Intelligent Processing Center of Excellence Robotics and AI Laboratory Department of Electrical and Computer Engineering University of Tehran Iran

Designing an appropriate cooperation protocol in multi-robot systems such as multi-robot object manipulation systems is a challenging task. In this paper designing and implementing a cooperation protocol between two robots pushing an object toward an arbitrary goal configuration is investigated. The proposed method benefits from task decoupling which simplifies the cooperation protocol design. Each robot gets its proper action from a particular fuzzy inference system independently. The fuzzy controllers outputs are low-level robot commands by which the need to a robot path planning algorithm is eliminated. Simulation results show that robots could push the object to the goal configuration cooperatively. Experiments have been conducted to approve the proposed system.

关键词： Fuzzy control Robot kinematics Protocols Fuzzy systems Electric variables control Control systems Multirobot systems Path planning Inference algorithms Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Kernel-based Linear Spectral Mixture Analysis for hyperspectral image classification

Kernel-based Linear Spectral Mixture Analysis for hyperspect...

引用

Workshop on Hyperspectral Image and Signal processing: Evolution in Remote Sensing, WHISPERS

作者： Keng-Hao Liu Englin Wong Chein-I Chang Remote Sensing Signal and Image Processing Laboratory the Department of Computer Science and Electrical Engineering Department University of Maryland Baltimore MD USA Department of Electrical Engineering National Chung Hsing University Taichung Taiwan

Linear spectral mixture analysis (LSMA) has been widely used in remote sensing community. Recently, kernel-based approaches have received considerable interest in hyperspectral image analysis where nonlinear kernels are used to resolve the issue of nonlinear separability in classification. This paper extends the LSMA to kernel-based LSMA where three least squares-based LSMA techniques, least squares orthogonal subspace projection (LSOSP), non-negativity constrained least squares (NCLS) and fully constrained least squares (FCLS) are extended to their kernel counterparts, KLSOSP, KNCLS and KFCLS.

关键词： Image analysis Spectral analysis Hyperspectral imaging Image classification Least squares methods Hyperspectral sensors Kernel Subspace constraints Remote sensing Image resolution

来源：评论

学校读者我要写书评

暂无评论

Component analysis-based unsupervised linear spectral mixture analysis for hyperspectral imagery

Component analysis-based unsupervised linear spectral mixtur...

引用

Workshop on Hyperspectral Image and Signal processing: Evolution in Remote Sensing, WHISPERS

作者： Xiaoli Jiao Yingzi Du Chein-I Chang Remote Sensing Signal and Image Processing Laboratory Department of Computer Science & Electrical Engineering University of Maryland Baltimore MD USA Department of Electrical and Computer Engineering Purdue School of Engineering and Technology Indiana University-Purdue University Indianapolis Indianapolis IN USA Department of Electrical Engineering National Chung Hsing University Taichung Taiwan

One of the most challenging issues in unsupervised linear spectral mixture analysis (LSMA) is how to obtain unknown knowledge of target signatures referred to as virtual endmembers (VEs) directly from the data to be processed. This issue has never arisen in supervised LSMA where the VEs are either assumed to be known a priori or can be provided by visual inspection. With the recent advent of hyperspectral sensor technology many unknown and subtle signal sources can be uncovered and revealed without prior knowledge. This paper addresses this issue and develops a component analysis-based unsupervised LSMA where the desired VEs can be extracted by component analysis-based transforms directly from the data to be processed without appealing for prior knowledge. In order to substantiate the utility of the proposed approach extensive experiments are conducted for demonstration.

关键词： Image analysis Spectral analysis Hyperspectral imaging Independent component analysis Personal communication networks Inspection Statistics Signal analysis Hyperspectral sensors Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Multimodal speaker localization from omnidirectional videos

Multimodal speaker localization from omnidirectional videos

引用

European Signal processing Conference (EUSIPCO)

作者： Pascal Reuse Mihai Gurban Ivar Austvoll Jean-Philippe Thiran Ecole Polytechnique Federale de Lausanne Lausanne Signal Processing Laboratory 5 Switzerland Department of Electrical and Computer Engineering University of Stavanger Stavanger Norway

The use of omnidirectional cameras for videoconferencing promises to simplify the hardware setup necessary for large groups of participants. We investigate the use of a multimodal speaker detection algorithm on audio-visual sequences captured with such a camera, in particular, an algorithm that uses the audio energy together with the optical flow. We analyze several types of optical flow methods to determine the one which is appropriate to the omnidirectional context.

关键词： Optical filters Image motion analysis computer vision Optical imaging Optical distortion Cameras Integrated optics

来源：评论

学校读者我要写书评

暂无评论

Dimensionality reduction of SIFT using PCA for object categorization

Dimensionality reduction of SIFT using PCA for object catego...

引用

IEEE International Symposium on Intelligent Signal processing and Communication Systems (ISPACS)

作者： Nattachai Watcharapinchai Supavadee Aramvith Supakorn Siddhichai Sanparith Marukatat Digital Signal Processing Research Laboratory Department of Electrical Engineering Chulalongkom University Bangkok Thailand National Electronics and Computer Technology Center Pathumthani Thailand

The problem of automatic object categorization is investigated under the proposed bag of feature object categorization framework. The framework consists of feature detection and representation which uses the scale invariant feature transform (SIFT) as local feature and bag of feature model to represent the image. Learning process utilizes k-NN (k-nearest neighbour). In this paper, we propose the dimensionality reduction of SIFT using principal component analysis (PCA) on each object category to reduce computational complexity and memory requirement during training process. Experimental results show that our proposed technique can reduce the dimension of SIFT up to around 80% with the same average precision compared to baseline technique without our proposed method.

关键词： Principal component analysis computer vision Histograms Digital signal processing Computational complexity Video compression Testing Training data Vocabulary Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Achieving Close-Capacity Performance with Simple Concatenation Scheme on Multiple-Antenna Channels

Achieving Close-Capacity Performance with Simple Concatenati...

引用

GLOBECOM 2009 - 2009 IEEE Global Telecommunications Conference

作者： Nghi H. Tran Tho Le-Ngoc Tad Matsumoto Ha H. Nguyen Department of Electrical & Computer Engineering McGill University Montreal QUE Canada Information Theory and Signal Processing Laboratory School of Information Science Japan Advanced Institute of Science and Technology Japan Department of Electrical & Computer Engineering University of Saskatchewan Saskatoon SAS Canada

This paper proposes a simple yet capacity-approaching concatenation of a mixture of short memory length convolutional codes and simple rate-1 block code followed by either complex 1-dimensional (1-D) anti-Gray or Gray mapping over multiple antenna channels with quadrature phase-shift keying (QPSK). By interpreting rate-1 code together with 1-D mapping as a multi-D mapping employed over multiple transmit antennas, the error performance is analyzed in two regions, the error-floor and turbo pinch-off regions. In the former one, a tight union bound and design criterion on the asymptotic performance are first derived, which provide an useful tool to predict the error performance. Based on the design criterion, an optimal rate-1 code for each 1-D mapping is then constructed to achieve the best asymptotic performance. In the turbo pinch-off area, by using extrinsic information transfer (EXIT) chart, the most suitable mixed codes are selected for both symmetric and asymmetric antenna setups. It is demonstrated that the simple concatenation scheme can achieve near-capacity. Furthermore, its error performance is comparable to that obtained by using well-designed irregular low-density parity-check (LDPC) and repeat accumulate (RA) codes, and thereby, outperforms a scheme employing a parallel concatenated turbo code.

关键词： Parity check codes Convolutional codes Block codes Phase shift keying Quadrature phase shift keying Transmitting antennas Error analysis Performance analysis Concatenated codes Turbo codes

来源：评论

学校读者我要写书评

暂无评论

Brain tissue classification using independent vector analysis (IVA) for magnetic resonance image

Brain tissue classification using independent vector analysi...

引用

2009 9th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2009

作者： Chiou, Yaw-Jiunn Chen, Hsiang-Min Chai, Jyh Wen Chen, Clayton Chi-Chang Ouyang, Yen-Chieh Su, Wu-Chung Yang, Ching-Wen Lee, San-Kan Chang, Chein-I. Department of Electrical Engineering National Chung Hsing University Taichung Taiwan Department of Radiology College of Medicine China Medical University Taichung Taiwan School of Medicine National Yang-Ming University Taipei Taiwan Department of Radiology Taichung Veterans General Hospital Taichung Taiwan Department of Radiological Technology Central Taiwan University of Science and Technology Taichung 406 Taiwan Computer Center Taichung Veterans General Hospital Taichung 407 Taiwan Remote Sensing Signal and Image Processing Laboratory Department of Computer Science and Electrical Engineering University of Maryland Baltimore County Baltimore MD 21250 United States

ISBN: (纸本)9780769536569

The purpose of this study is to present a new method, independent vector analysis (IVA), by extending independent component analysis (ICA) of univariate source signals to multivariate source signals on Magnetic Resonance Imaging (MRI). IVA is utilized to relief the limitation of the conventional ICA approach. The proposed method can resolve the permutation problem during individual ICA runs for group brain MR images. The proposed IVA method in conjunction with support vector machine (SVM), we can effectively separate the different part of gray, white matter and cerebrospinal fluid (CSF) from brain soft tissues. In order to demonstrate the proposed IVA-SVM method, experiments are conducted for performance analysis and evaluation. Simulation results show that using IVA can greatly release from the problem cause from traditional ICA to the situation of analyzing inconsistent results of MR image. © 2009 IEEE.

关键词： Magnetic resonance imaging

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：