Singapore /August 4-6

Keynote Speakers

2017 2nd International Conference on Signal and Image Processing (ICSIP 2017)



Keynote Speaker I


Fellow of IEEE ,Dean, Prof. M J T Smith, Purdue University, USA

Speech Title: Voice Conversion and Modification


Abstract: Digital speech technology continues to have an increasing presence in society, impacting hundreds of millions of people. Common examples include text-to-speech systems, GPS devices, cell phones, automated response systems, and many more.  This talk presents some high performance approaches to speech modification and voice conversation that expand application functionality by enabling speaker identity to be modified. In particular, a voice conversion algorithm based on a Gaussian Mixture Model (GMM) is employed. Instead of employing the Expectation Maximization (EM) algorithm to determine the parameters of the GMM, we us a neural network, which helps improve the accuracy of the estimation and in turn reduces distortion in the converted speech. Flexibility to control pitch, cadence, and time scale are achieved using a sinusoidal model for synthesis.


Bio: Mark J. T. Smith received his B.S. degree from the Massachusetts Institute of Technology and his M.S. and Ph.D. degrees from the Georgia Institute of Technology, all in electrical engineering. He joined the electrical engineering faculty at Georgia Tech in 1984 and later served as the executive assistant to the president of the institute from 1997-2001. In January 2003, he joined the faculty at Purdue University as head of the School of Electrical and Computer Engineering. Presently, he serves as Dean of the Graduate School and holds the Michael & Katherine Birck endowed professorship.

Dr. Smith is a fellow of the IEEE and a former IEEE Distinguished Lecturer in Signal Processing.  He has authored many papers in the areas of speech and image processing, filter banks, and wavelets and is the co-author of two introductory books titled, Introduction to Digital Signal Processing and Digital Filtering. He is also co-editor of the book, Wavelets and Subband Transforms: Design and Applications, and the co-author of the textbook, A Study Guide for Digital Image Processing.

In addition to professional service, teaching, and research, Dr. Smith's past includes athletic training and competition in the sport of fencing. He was National Champion of the United States in 1981 and 1983 and a two-time member of the U.S. Olympic Team in 1980 and 1984.



Keynote Speaker II



Prof. Maode Ma, Nanyang Technological University, Singapore


Speech Title: Network Selection and Resource Allocation for Multicast Service in HetNets


Abstract: In a heterogeneous wireless system, the member stations of a multicast stream may be distributed in different wireless networks within the system. Meanwhile, each member station may have multiple network interfaces available simultaneously. Therefore, the selection of networks for serving the stream and the allocation of radio resources in the selected networks play significant roles in improving the utilization of system resource, especially for the stream with a large group size. In this talk, a novel joint network selection and resource allocation scheme is introduced aiming to minimize the overall resources consumed by the multicast stream in the heterogeneous wireless system. The fundamental idea is to gather the member stations locating in the same network region and to transmit the stream with possibly high modulation and coding rates. The problem is formulated as a binary integer programming problem, and then a computationally efficient Lagrangian-based heuristic algorithm is derived to solve the problem, where the architecture of interworking system is taken into account. Simulation results show that the proposed scheme will cost the minimum system bandwidth compared to other reference schemes.


Bio: Dr. Maode Ma received his Ph.D. degree in computer science from Hong Kong University of Science and Technology in 1999. Now, Dr. Ma is an Associate Professor in the School of Electrical and Electronic Engineering at Nanyang Technological University in Singapore. He has extensive research interests including wireless networking and network security. He has led and/or participated in 18 research projects funded by government, industry, military and universities in various countries. He has been a general chair, technical symposium chair, tutorial chair, publication chair, publicity chair and session chair for more than 70 international conferences. He has been a member of the technical program committees for more than 180 international conferences. Dr. Ma has about 300 international academic publications including more than 130 journal papers and over 160 conference papers. He currently serves as the Editor-in-Chief of International Journal of Computer and Communication Engineering and International Journal of Electronic Transport. He also serves as a Senior Editor for IEEE Communications Surveys and Tutorials, and an Associate Editor for International Journal of Network and Computer Applications, International Journal of Security and Communication Networks, International Journal of Wireless Communications and Mobile Computing and International Journal of Communication Systems. He had been an Associate Editor for IEEE Communications Letters from 2003 to 2011. Dr. Ma is the Fellow of IET and a senior member of IEEE Communication Society and IEEE Education Society. He is the Chair of the IEEE Education Society, Singapore Chapter. He is serving as an IEEE Communication Society Distinguished Lecturer from 2013 to 2016.


Plenary Speaker I


Prof. Yasuhiro Matsuda, Kanagawa Institute of Technology, Japan


Emotional Recognition Systems in Tactual Communication

 Various positive emotions can be expressed between people familiar to each other by tactual communication. In this speech, we introduce emotional expressions in tactual communication and also explain their emotion recognition systems.
Finger Braille is one of the tactual communication methods utilized by deafblind individuals. We developed an emotion recognition system using piezoelectric accelerometers worn by non-disabled person. The emotion recognition system recognized four emotions (joy, sadness, anger and neutral) expressed by the deafblind person. The emotion recognition system calculated the means probabilities of four emotions by duration of dotting and amplitude of acceleration and recognized the expressed emotion.
We have been developing a tactual communication tool which conveys emotions during face-to-face oral conversation. Two users each hold one ball during an oral conversation. When one ball is gripped, air is pumped out of that ball and into the other. We developed an emotion recognition algorithm to recognize six emotions (surprise, joy, anger, sadness, disgust and fear). Using four parameters (number of grips, maximum air pressure change, release time of one-time grip and mean of release and grip time of multiple grips), the expressed emotion was estimated to one of the six emotions.


Bio: Prof. Yasuhiro Matsuda obtained his Ph.D. degree from the University of Tokyo in 2007. He joined the Department of Welfare Systems Engineering at Kanagawa Institute of Technology in 2000, and later joined the Department of Robotics and Mechatronics. Now, he is a professor and department chair of the Department of Clinical Engineering. Prof. Matsuda’s expertise is in the field of assistive technology for deaf and/or blind persons and measurement engineering. Currently, his main research interest is in the development of the communication support system using Finger Braille for deafblind person and tactual communication tool for elderly person.



Invited Speaker I


Assoc. Prof. Baohong Yuan, University of Texas at Arlington, United States


New generation ultrasound-switchable fluorescence imaging


Abstract: We developed a dual-modality imaging system by combining our recently developed ultrasound-switchable fluorescence (USF) imaging technology with the conventional ultrasound (US) B-mode imaging. This dual-modality system can simultaneously image tissue acoustic structure information and multi-color fluorophores in centimeter-deep tissue with comparable spatial resolutions. To conduct USF imaging on the same plane (i.e. x-z plane) as US imaging, we adopted two 900-crossed ultrasound transducers with an overlapped focal region, while the US transducer (the 3rd one) was positioned at the center of these two USF transducers. Thus, the axial resolution of USF is close to the lateral resolution, which allows a point-by-point USF scanning on the same plane as the US imaging. Both multi-color USF and ultrasound imaging of a tissue phantom were demonstrated.


Bio: Prof. Baohong Yuan obtained his Biomedical Engineering Ph.D. degree from University of Connecticut in 2006, and completed post-doctoral training in Columbia University in 2007. From 2010, he joined the bioengineering department at University of Texas at Arlington (UTA). Prof. Yuan’s expertise is in the field of biomedical imaging, specifically biomedical optical and ultrasonic imaging. Currently, his main research interest is in the development of ultrasound-switchable fluorescence technique for imaging deep-tissue micro-events with super-high resolution. He has published ~60 peer-reviewed journal papers, presented numerous conference or seminar invited talks, and received/applied four U.S. patents. As a principal investigator (PI), he has received ~$3 million funding support from Federal and State funding agencies, including NSF(CAREER award), NIH, CPRIT and NHARP during the past few years. In addition, a total of ~$3.2 million requested budget is pending. He is a senior member of SPIE and OSA, a member of BMES and WMIS. He serves and chairs in several conference committees, such as SPIE Biomedical Imaging and BMES Ultrasound Imaging. He is an editor, a guess editor or an editorial board member for many academic journals, such as Scientific Reports, Journal of Biomedical Optics, Technology in Cancer Research and Treatment. He is a reviewer for 28 scientific journals (such as Biomaterials, Scientific Reports, Plos One, Optics Letters, Applied Physics letters, et al) and several governmental funding agencies (NIH, NSF and AHA). His major awards include NSF CAREER award, Outstanding Early Career Award, Kaman Award for Excellence in Research, and Burns Faculty Fellow.


Invited Speaker II

Dr. Manoj Gupta, University of Rajasthan, India


Performance Evaluation of Hybrid Image Fusion Using DTCWT Technique



← Older Entires Newer Entires →

Keep In Touch


Submission Method

Conference Venue

NTU@one-north, Singapore
Address: 11 Slim Barracks Rise (off North Buona Vista Road),NTU@one-north campus, Executive Centre #09-09, Singapore 138664