检索结果-内蒙古大学图书馆

IEEE China Summit & International Conference on Signal and Information processing (ChinaSIP)

作者： Jianglin Wang Michael T. Johnson Speech and Signal Processing Laboratory Department of Electrical and Computer Engineering Marquette University Milwaukee USA

This paper introduces the use of two new features for speaker identification, Residual Phase Cepstrum Coefficients (RPCC) and Glottal Flow Cepstrum Coefficients (GLFCC), to capture speaker-specific characteristics from their vocal excitation patterns. Results on a cross-lingual speaker identification task taken from the NIST 2004 SRE demonstrate that these RPCC and GLFCC features are significantly more accurate than traditional mel-frequency cepstral coefficients (MFCC). In particular, these two new features give better results with smaller amounts of training data, due to lower model complexity.

关键词： Speech Mel frequency cepstral coefficient Accuracy Speaker recognition Feature extraction Adaptation models Filtering

来源：评论

学校读者我要写书评

暂无评论

Localization of multiple simultaneous speakers by combining the information from different subbands

Localization of multiple simultaneous speakers by combining ...

引用

Iranian Conference on electrical engineering (ICEE)

作者： Ali Dehghan Firoozabadi Hamid Reza Abutalebi Speech Processing Research Laboratory(SPRL) Electrical and Computer Engineering Department Yazd University Yazd Iran

Time Difference Of Arrival (TDOA)-based algorithms are the main methods for speech source localization. A category of these methods are based on Generalized Cross Correlation (GCC). These methods estimate the source location based on the calculated TDOA between microphones signals. The accuracy of these methods decreases as the amount of noise and reverberation increases. In this paper, we propose the utilization of subband processing for the localization of two simultaneous speech sources. While the conventional methods consider the whole signal spectrum identically in the localization procedure, the proposed method takes advantage of the differences in the frequency bands of the mixed speech for the localization of multiple speakers. Actually, the proposed method computes the GCC in the different frequency bands and then, combines the information from the subbands in a so-called smart manner. We have discussed several approaches for the combination of subband. The performance evaluations in different environmental conditions demonstrate the superiority of the proposed method compared to the fullband GCC method. The proposed method considerably increases the accuracy of simultaneous speaker localization.

关键词： Microphones Histograms Estimation Speech Direction-of-arrival estimation Noise measurement Accuracy

来源：评论

学校读者我要写书评

暂无评论

Relationship exploration among PPI, ATGP and VCA via theoretical analysis

Relationship exploration among PPI, ATGP and VCA via theoret...

引用

作者： Chang, Chein-I. Wen, Chia-Hsien Wu, Chao-Cheng Department of Computer Science and Electrical Engineering Remote Sensing Signal and Image Processing Laboratory University of Maryland 1000 Hilltop Circle Baltimore MD 21250 United States Department of Computer Science and Information Engineering Providence University Taichung Taiwan Department of Computer Science and Information Management Providence University 200 Taiwan Boulevard Shalu Dist. Taichung City 43301 Taiwan Department of Electrical Engineering National Taipei University of Technology 1 Zhongxiao E. Rd. Taipei 106 Taiwan

The principle of orthogonality using orthogonal projection (OP) is the key concept to develop mean squared error estimation theory in signal processing and communications. It has also found its way in a wide variety of applications in hyperspectral imaging. This paper explores close relationships among three OP-based algorithms, pixel purity index (PPI), vertex component analysis (VCA) in endmember extraction, automatic target generation process (ATGP) in mixed pixel classification and target detection, etc. and further shows that they indeed can be interpreted one way or another. Specifically, VCA and ATGP are essentially the same algorithm in the sense that they both extract targets via maximal OP from a nested sequence of successive orthogonal subspace projection spaces. Copyright © 2013 Inderscience Enterprises Ltd. Copyright © 2013 Inderscience Enterprises Ltd.

关键词： Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

A single channel-single trial P300 detection algorithm

A single channel-single trial P300 detection algorithm

引用

Iranian Conference on electrical engineering (ICEE)

作者： Neda Haghighatpanah Rasoul Amirfattahi Vahid Abootalebi Behzad Nazari Digital signal processing research Laboratory department of Electrical & Computer Engineering Isfahan University of technology Isfahan Iran Electrical & Computer Engineering Department Yazd University Yazd Iran

A Brain computer Interface (BCI) system allows the users to communicate with their surroundings without using any muscle activity. Many of these systems are based on the analysis of Event Related Potentials (ERPs) such as P300. P300 speller is one of the common BCI systems which attract a lot of attention; however, there are still a lot of flaws in these systems which should be considered. Since ERPs such as P300 signals have a very low Signal to Noise Ratio (SNR), single trial analysis of these signals is difficult and in many papers, denoising methods such as synchronous averaging were proposed to reduce random noise; however, it reduces the communication rate greatly. Another major problem in many BCI applications is the numerous number of channels needed to record EEG signals in order to have a reliable system. In this paper, a new method is presented to detect P300 signals through single channel data analysis and also it reaches an average accuracy of 65% in single trial P300 detection.

关键词： Electroencephalography Feature extraction Algorithm design and analysis Wavelet transforms Standards Detection algorithms Accuracy

来源：评论

学校读者我要写书评

暂无评论

Sonifying HTML tables for audio-spatially enhanced non-visual navigation

Sonifying HTML tables for audio-spatially enhanced non-visua...

引用

IEEE Southeastcon

作者： Jonathan Cofino Armando Barreto Fatemeh Abyarjoo Francisco R. Ortega Digital Signal Processing Laboratory Department of Electrical and Computer Engineering Florida International University Miami FL USA

ISBN: (纸本)9781479900527

Computing is now ubiquitous. Accessing the Internet is increasingly common from mobile devices through cellular networks. The Internet is now used for shopping, communicating, and for finding employment and housing. More information is readily available than at any time in human history; however, this information is often inaccessible to people with blindness or low-vision. In order to increase access to information for these individuals, information must be presentable in non-visual formats. Presently, screen readers are able to verbalize on-screen text using text-to-speech (TTS) synthesis; however, this vocalization is inadequate for browsing the Internet. Modern operating systems have generally relied on a graphical display and a mouse for interfacing. For individuals with vision loss, we propose to create and test an auditory interface that incorporates an auditory-spatial orientation with a standard keyboard for input. If information can be structured as a two-dimensional table, each link can be semantically grouped as a cell in a row within the auditory table. This provides a consistent structure for non-visual auditory navigation. After testing the auditory display prototype with 13 participants, it was shown that stereo panning was an effective technique for audiospatially orienting non-visual navigation through a five-row, six-column HTML table as compared to a centered, stationary synthesized voice. Rather than be left out of ubiquitous computing, blind and low-vision individuals may benefit from increased efficiency and accuracy in non-visual navigation. This finding may also stimulate interest in non-visual computing while performing other tasks, such as walking, eating, or driving.

关键词： Navigation Testing Speech Browsers HTML Internet Arrays

来源：评论

学校读者我要写书评

暂无评论

On variation of infinite horizon performance of model predictive control with varying receding horizon

On variation of infinite horizon performance of model predic...

引用

3rd IFAC Conference on Intelligent Control and Automation Science, ICONS 2013

作者： Cai, Xin Li, Shaoyuan Li, Ning Li, Kang Department of Automation Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai 200240 China School of Electronics Electrical Engineering and Computer Science Queen's University Belfast Belfast BT7 1NN United Kingdom

ISBN: (纸本)9783902823458

This paper investigates variation of infinite horizon (IH) performance of Model Predictive Control (MPC) without constraints as the optimization horizon changes. By exploring properties of the Difference Riccati Equations (DRE), an upper bound and a lower bound of the ratio between variation of IH performance of MPC and finite horizon (FH) optimal cost are obtained. The result shows the dynamic behavior of IH performance of closed-loop MPC systems as the optimization horizon varies. Copyright © 2013 IFAC.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Predictive analysis of two tone stream segregation via extended Kalman filter

Predictive analysis of two tone stream segregation via exten...

引用

Annual Conference on Information Sciences and Systems (CISS)

作者： Debmalya Chakrabarty Mounya Elhilali Department of Electrical and Computer Engineering Laboratory of Computational Audio Perception Center for Speech and Language Processing Johns Hopkins University MD USA

Hearing engages in a seemingly effortless way, complex processes that allow our brains to parse the acoustic environment around us into perceptual sound objects, in a phenomenon called streaming or stream segregation. In this paper, we explore the hypothesis that the auditory system relies on the regularity inherent to each stream to segregate it from other competing streams in the scene. Tracking these regularities is achieved via a recursive prediction that tracks the evolution of each stream, using a Kalman filtering approach. The proposed approach combines spectral analysis operating at the level of the auditory periphery with a temporal analysis using Kalman tracking. To incorporate nonlinear relationships in the signal patterns, we employ an extended Kalman filter. This scheme is tested on sinusoidal patterns, or the two tone paradigm. The combined spectral and temporal analysis developed here is able to predict perceptual results of stream segregation by human listeners in a two tone paradigm.

关键词： Indexes Kalman filters Frequency response

来源：评论

学校读者我要写书评

暂无评论

Iron ore green pellet diameter measurement by using of image processing techniques

Iron ore green pellet diameter measurement by using of image...

引用

Iranian Conference on electrical engineering (ICEE)

作者： Mahdi Heydari Rassoul Amirfattahi Behzad Nazari Alireza Bastani Digital Signal processing Research Laboratory Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan Iran Department of Mechanical Engineering Isfahan University of Technology Isfahan Iran

Automatic Quality control is a vital process in many manufacturing process such as steel industry. Pellet size monitoring and control is a critical process which is done in steel making to improve quality of products. According to the technical reports, pellet size should be fall in the range of 9-16 mm in diameter. Larger or smaller pellets could degrade the final products and impose extra overheads to industry. In this paper, a new method is proposed for measuring the pellet size using practical Image processing algorithms. In this method, active contour with Chen-Vese method is used to eliminate the images backgrounds and achieving a distinguishable plot of the objects. After detecting distinct elements existing in the image, the number of pellets in each object is determined and each object is classified as singular, double, triple or more pellets using an SVM classifier. Finally, morphological methods are used to estimate the real size of pellets and the pellets size histogram is presented. This practical method was applied in Mobarakeh Steel Complex, where the method was tested on about 1000 prototypes. Results showed that we have 95.1% of accuracy for detection of one pellet elements and in classification by SVM 95.6% of elements were classified correctly.

关键词： Support vector machines Image edge detection Iron Active contours Finite impulse response filters Steel Accuracy

来源：评论

学校读者我要写书评

暂无评论

Erratum to: Methods for evaluating medical tests and biomarkers

引用

Diagnostic and prognostic research 2017年第1期1卷 11页

作者： Gowri Gopalakrishna Miranda Langendam Rob Scholten Patrick Bossuyt Mariska Leeflang Anna Noel-Storr James Thomas Iain Marshall Byron Wallace Penny Whiting Clare Davenport Gowri GopalaKrishna Isabel de Salis Sue Mallett Robert Wolff Richard Riley Marie Westwood Jos Kleinen Gary Collins Hans Reitsma Karel Moons Antonia Zapf Annika Hoyer Katharina Kramer Oliver Kuss J Ensor J J Deeks E C Martin R D Riley Gerta Rücker Susanne Steinhauser Martin Schumacher Joie Ensor Kym Snell Brian Willis Thomas Debray Jon Deeks Lavinia Ferrante di Ruffano Sian Taylor-Phillips Chris Hyde Stuart A Taylor Gauraang Batnagar Lavinia Ferrante Di Ruffano Farah Seedat Aileen Clarke Sarah Byron Frances Nixon Rebecca Albrow Thomas Walker Carla Deakin Zhivko Zhelev Harriet Hunt Yaling Yang Lucy Abel James Buchanan Thomas Fanshawe Bethany Shinkins Laure Wynants Jan Verbakel Sabine Van Huffel Dirk Timmerman Ben Van Calster Aeliko Zwinderman Jason Oke Jack O'Sullivan Rafael Perera Brian Nicholson Hannah L Bromley Tracy E Roberts Adele Francis Denniis Petrie G Bruce Mann Kinga Malottki Holly Smith Lucinda Billingham Alice Sitch Oke Gerke Mie Holm-Vilstrup Eivind Antonsen Segtnan Ulrich Halekoh Poul Flemming Høilund-Carlsen Bernard G Francq Jac Dinnes Julie Parkes Walter Gregory Jenny Hewison Doug Altman William Rosenberg Peter Selby Julien Asselineau Paul Perez Aïssatou Paye Emilie Bessede Cécile Proust-Lima Christiana Naaktgeboren Joris de Groot Anne Rutjes Johannes Reitsma Emmanuel Ogundimu Jonathan Cook Yannick Le Manach Yvonne Vergouwe Romin Pajouheshnia Rolf Groenwold Karen Moons Linda Peelen Daan Nieboer Bavo De Cock Micael J Pencina Ewout W Steyerberg Jennifer Cooper Nick Parsons Chris Stinton Steve Smith Andy Dickens Rachel Jordan Alexandra Enocson David Fitzmaurice Peymane Adab Charles Boachie Gaj Vidmar Karoline Freeman Martin Connock Rachel Court Carl Moons Jessica Harris Andrew Mumford Zoe Plummer Kurtis Lee Barnaby Reeves Chris Rogers Veerle Verheyden Gianni D Angelini Gavin J Murphy Jeremy Huddy Melody Ni Katherine Good Graham Cooke 1Department of Clinical Epidemiology Biostatistics & Bioinformatics Academic Medical Center University of Amsterdam Amsterdam The Netherlands. 2Cochrane Netherlands Julius Center for Health Sciences and Primary Care University Medical Center Utrecht Utrecht Netherlands. 234Department of Clinical Epidemiology Biostatistics & Bioinformatics Academic Medical Center University of Amsterdam Amsterdam The Netherlands. 49Department of Clinical Epidemiology Biostatistics & Bioinformatics Academic Medical Center University of Amsterdam Amsterdam The Netherlands. 3Cochrane Dementia and Cognitive Improvement Group University of Oxford Oxford UK. 4EPPI-Centre Department of Social Science University College London London UK. 5Division of Health and Social Care Research King's College London London UK. 6College of Computer and Information Science Northeastern University Boston USA. 13University Hospitals Bristol NHS Foundation Trust School of Social and Community Medicine Bristol UK. 275Institute of Applied Health Research University of Birmingham Birmingham UK. 9Department of Clinical Epidemiology Biostatistics & Bioinformatics Academic Medical Center University of Amsterdam Amsterdam The Netherlands. 10School of Social and Community Medicine University of Bristol Bristol UK. 179Institute of Applied Health Research University of Birmingham Birmingham UK. 12Kleijnen Systematic Reviews Ltd York UK. 25Research Institute for Primary Care and Health Sciences Keele University Keele UK. 188Centre for Statistics in Medicine Nuffield Department of Orthopaedics Rheumatology and Musculoskeletal Sciences University of Oxford Oxford UK. 191Julius Center for Health Sciences and Primary Care University Medical Center Utrecht 3584 CG Utrecht Netherlands. 237Julius Center for Health Sciences and Primary Care University Medical Center Utrecht 3584 CG Utrecht Netherlands. 18Department of Medical Statistics University Medical Center Göttingen Göttingen Germany. 19Institute for B

[This corrects the article DOI: 10.1186/s41512-016-0001-y.].

关键词：

来源：评论

学校读者我要写书评

暂无评论

An open-source development and simulation platform for smart wheelchairs

An open-source development and simulation platform for smart...

引用

6th International Conference on Intelligent Robotics and Applications, ICIRA 2013

作者： Liao, Wenlong Chen, Weidong Wei, Zhixuan Zhang, Wenxi Wang, Jingchuan Li, Kang Department of Automation and Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiao Tong University Shanghai 200240 China Harbin 150001 China Electrical Engineering and Computer Science Queen's University Belfast Belfast BT9 5AH United Kingdom

ISBN: (纸本)9783642408519

Simulator for smart wheelchairs is of great significance for both driver training and algorithm design. A development and simulation platform for wheelchairs is presented in this paper. On this platform, simulations of kinematics, dynamics and sensors are integrated, and a virtual prototype of wheelchair and virtual world are modled also. The sensors include encoders, a laser range finder and a set of Kinect. This platform is implemented in Gazebo and ROS, and is completely open source and freely available. Experiments verifies that this platform can be used as a valid tool for driver training and algorithm design. © 2013 Springer-Verlag Berlin Heidelberg.

关键词： Virtual reality

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：