APSIPA ASC 2018

Session Index

Monday

09:00 - 12:30

T1: A 3-Hour Primer on Real World Autonomous Driving: Hands-on Introduction to Autoware

Room 308-A

T2: Sparse Signal Processing: Recent Advances and Applications

Room 309

T3: Voice Conversion: Challenges and Opportunities

Room 308-B

10:30 - 11:00

Coffee Break

13:30 - 17:00

T4: 360° Video for Immersive Media Communications

Room 308-A

T5: Fundamental Concepts in Machine Learning

Room 309

T6: Generative Adversarial Network and its Applications to Speech Signal and Natural Language Processing

Room 308-B

15:00 - 15:30

Coffee Break

18:00 - 20:00

Welcome Reception

Near Room 310

Tuesday

08:30 - 09:00

Opening Ceremony

09:00 - 10:00

José Moura - Cities Through the Mobility Looking Glass

Room 310

10:00 - 10:30

Coffee Break

10:30 - 12:10

TU-A1-2: Biometrics and Behavioral Analysis

Room 303-AB

TU-A1-3: Image/Video Compression

Room 305-AB

TU-A1-4: Signal Processing Systems

Room 306-B

TU-A1-5: Recent advances in estimation techniques of phase information

Room 307-A

TU-A1-6: Recent Advances in Data Analytics and Knowledge Discovery

Room 308-A

TU-A1-7: Wireless Communications and Networks

Room 308-B

TU-A1-8: Speech Recognition

Room 309

TU-A1-9: Ph.D. Forum I (Oral Presentations)

Room 306-A

Overview Session: Big Data

Room 310

12:10 - 13:30

Lunch

Friend Lab

Room 307-AB

WCN Technical Meeting

Room 308-A

SLA Technical Meeting

Room 306-B

SIPTM Technical Meeting

Room 309

13:30 - 14:30

Bin Yu - Three principles of data science: predictability, stability, and computability

Room 310

14:30 - 15:00

Coffee Break

15:00 - 17:00

TU-P1-1: Recent Advances in Online Learning, Stochastic Optimization, and Adaptive Signal Processing

Room 310

TU-P1-2: Privacy and Security for Mobile Internet and Cloud Computing in the Big Data Era

Room 303-AB

TU-P1-3: Recent topics in applications of learning methods to signal and image processing

Room 305-AB

TU-P1-4: Image/Video Interpretation and Understanding

Room 306-B

TU-P1-5: Advanced Signal Processing and Machine Learning for Audio and Speech Applications

Room 307-A

TU-P1-6: Signal Processing for Assistive Hearing Devices

Room 308-A

TU-P1-7: Spectrum Monitoring and Management in Wireless Sensor Networks

Room 308-B

TU-P1-8: Convergence of 5G with SDN/NFV/Cloud

Room 309

Ph.D. Forum II (Poster Presentations)

Room 306-A

18:00 - 20:00

Board of Governors Meeting

Room 302-A

Wednesday

08:00 - 09:40

WE-A1-2: Deep learning based brain information processing

Room 303-AB

WE-A1-3: Advanced Image Processing and Computer Vision Techniques (I)

Room 305-AB

WE-A1-4: Information hiding and Detection in Multimedia Big Data

Room 306-B

WE-A1-5: Recent advances of machine learning and signal processing in hypercomplex domain

Room 307-A

WE-A1-6: Minor- and Multi- lingual speech and language processing

Room 308-A

WE-A1-7: Hyperspectral and Multiview Image Processing

Room 308-B

WE-A1-8: Speech Synthesis

Room 309

WE-A1-P: Speech Processing

Room 306-A

Overview Session: APSIPA 10th Anniversary Magazine: The Era of Signal Processing and Information Technologies and Long Term Prospective I

Room 310

09:40 - 10:00

Coffee Break

10:00 - 11:00

Hsiao-Wuen Hon - Brief History of Intelligence

Room 310

11:10 - 12:50

WE-A2-2: Biomedical Signal Processing and Systems

Room 303-AB

WE-A2-3: Advanced Image Processing and Computer Vision Techniques (II)

Room 305-AB

WE-A2-4: Machine Learning for Information Processing and Forensics

Room 306-B

WE-A2-5: Optimization, Control, and Data Analytics for Cyber-Physical Systems

Room 307-A

WE-A2-6: Subjective perception and neural processing of speech in complex environments (I)

Room 308-A

WE-A2-7: Spectrum modeling and recognition for wireless communication

Room 308-B

WE-A2-8: Voice Conversation/Dialog

Room 309

WE-A2-P: Signal and Information Processing: Theory and Methods

Room 306-A

Overview Session: APSIPA 10th Anniversary Magazine: The Era of Signal Processing and Information Technologies and Long Term Prospective II

Room 310

12:50 - 14:00

Lunch

MSF Technical Meeting

Friend Lab

Room 307-AB

SPS Technical Meeting

Room 308-A

BioSiPS Technical Meeting

Room 308-B

IVM Technical Meeting

Room 309

14:00 - 15:30

Presidential Forum

Room 310

15:30 - 16:00

APSIPA General Assembly

Room 310

16:00 - 16:20

Coffee Break

16:20 - 18:00

WE-P1-2: Emerging Technologies for Healthcare

Room 303-AB

WE-P1-3: Recent Advances in High Performance Processing for Multi-dimensional Signals

Room 305-AB

WE-P1-4: Advances in Multimedia Security

Room 306-B

WE-P1-5: Distributed Optimization in Data Science

Room 307-A

WE-P1-6: Subjective perception and neural processing of speech in complex environments (II)

Room 308-A

WE-P1-7: Machine Learning for Signal and Information Processing

Room 308-B

WE-P1-8: Sound Processing

Room 309

Overview Session: APSIPA 10th Anniversary Magazine: The Era of Signal Processing and Information Technologies and Long Term Prospective III

Room 310

19:00 - 22:00

Conference Banquet

Ballroom B

Thursday

08:00 - 09:40

TH-A1-1: Replay Attack Anti-Spoofing Measures for ASV Systems

Room 310

TH-A1-2: Image/Video Synthesis and Rendering

Room 303-AB

TH-A1-3: Intelligent & Highly Efficient Image & Video Processing Systems

Room 305-AB

TH-A1-4: Recent Advances in Data Hiding and Encryption Technology

Room 306-B

TH-A1-5: Graph Signal Processing: Theory and Applications

Room 307-A

TH-A1-6: Security and Privacy in Information Fusion and Real time Decision Making

Room 308-A

TH-A1-7: Signal Processing for Advancing Cyber-Physical Systems

Room 308-B

TH-A1-8: Speech Enhancement

Room 309

TH-A1-P: Speech and Sound Processing

Room 306-A

09:40 - 10:00

Coffee Break

10:00 - 11:00

Shinji Watanabe - End-to-End Speech Processing: From Pipeline to Integrated Architecture

Room 310

11:10 - 12:50

TH-A2-1: Recent Trends on Active Control of Sound

Room 310

TH-A2-2: Advances in Cognitive Information Processing: Methods for conducting behavioral experiments in realistic environment and their applications

Room 303-AB

TH-A2-3: Advanced Topics on Signal Analysis and Compression for Monitoring Systems

Room 305-AB

TH-A2-4: Tensor modeling for signal processing and machine learning problems

Room 306-B

TH-A2-5: Recent topics in theory and application of digital filters

Room 307-A

TH-A2-6: Efficient Computing and Estimation in Deep Learning with Applications

Room 308-A

TH-A2-7: Large-Scale Stochastic Signal Processing for Wireless Systems

Room 308-B

TH-A2-8: Speech/Language Recognition

Room 309

TH-A2-P: Image, Video and Multimedia

Room 306-A

12:50 - 14:00

Lunch

Friend Lab

Room 307-AB

Conference Board Meeting

Room 308-A

Technical Board Meeting

Room 308-B

Editorial Board Meeting

Room 309

DL Meeting

Room 306-B

14:00 - 15:40

TH-P1-1: Speaker diarization and recognition in adverse acoustic environments

Room 310

TH-P1-2: Recent advantage on light field technologies

Room 303-AB

TH-P1-3: Audio/Visual Human Attribute Recognition and Modeling for Future Immersive Applications.

Room 305-AB

TH-P1-4: Digital Forensics and Data Hiding

Room 306-B

TH-P1-5: Recent advances of anomaly detection and estimation for network systems

Room 307-A

TH-P1-6: Deep Learning-based Detection and Recognition for Perception Applications

Room 308-A

TH-P1-7: Audio and Speech Content Analysis

Room 308-B

TH-P1-8: Sound/Speech Processing

Room 309

15:50 - 16:20

Closing Ceremony

Room 310

16:30 - 20:00

10 Year Celebration: Dinner Cruise

Dinner Cruise

TU-A1-2: Biometrics and Behavioral Analysis

Location: Room 303-AB
Time: Tuesday, November 13, 10:30 - 12:10

Session Chairs: Koichi Ito, Tohoku University and Tetsushi Ohki, Shizuoka University

TU-A1-2.1: A GENERALIZATION OF THE THEORY OF BIOMETRIC SYSTEM ENTROPY
Kenta Takahashi, Hitachi, Ltd., Japan; Takao Murakami, National Institute of Advanced Industrial Science and Technology, Japan

TU-A1-2.2: AGE AND GENDER PREDICTION FROM FACE IMAGES USING CONVOLUTIONAL NEURAL NETWORK
Koichi Ito, Hiroya Kawai, Takehisa Okano, Takafumi Aoki, Tohoku University, Japan

TU-A1-2.3: BIOMETRIC BIT STRING GENERATION FOR SMART-PHONES USING VOICE DATA
Aki Harada, Yasushi Yamazaki, The University of Kitakyushu, Japan; Tetsushi Ohki, Shizuoka University, Japan

TU-A1-2.4: SELF ADVERSARIAL TRAINING FOR HUMAN POSE ESTIMATION
Chia-Jung Chou, Aeolus Robotics, Taiwan; Jui-Ting Chien, Hwann-Tzong Chen, National Tsing Hua University, Taiwan

TU-A1-3: Image/Video Compression

Location: Room 305-AB
Time: Tuesday, November 13, 10:30 - 12:10

Session Chairs: Yongfei Zhang, Beihang University and Ming-Ting Sun, University of Washington

TU-A1-3.1: TEXTURE AND POSITION BASED MULTIPLE TRANSFORM FOR INTER-PREDICTED RESIDUE CODING
Liqiang Wang, Benben Niu, Tsinghua University, China; Yongbing Lin, Quanhe Yu, Jianhua Zheng, HiSilicon Technologies Co., Ltd, China; Yun He, Tsinghua University, China

TU-A1-3.2: A RATE CONTROL ALGORITHM FOR HEVC CONSIDERING VISUAL SALIENCY
Henglu Wei, Wei Zhou, Rui Bai, Zhemin Duan, Northwestern Polytechnical University, China

TU-A1-3.3: ADAPTIVE QUAD-TREE COMPLEXITY CONTROL FOR HEVC
Kun Duan, Pengyu Liu, Kebin Jia, Zeqi Feng, Zhonghua Sun, Beijing University of Technology, China

TU-A1-3.4: FAST MOTION ESTIMATION IN HEVC INTER CODING: AN OVERVIEW OF RECENT ADVANCES
Yongfei Zhang, Chao Zhang, Rui Fan, Beihang University, China

TU-A1-3.5: CONTENT-ADAPTIVE IMAGE COMPRESSED SENSING USING DEEP LEARNING
Liqun Zhong, Shuai Wan, Leyi Xie, Shun Zhang, Northwestern Polytechnical University, China

TU-A1-4: Signal Processing Systems

Location: Room 306-B
Time: Tuesday, November 13, 10:30 - 12:10

Session Chairs: Jiun-In Guo , National Chiao Tung University and Gwo Giun Lee, National Cheng Kung University

TU-A1-4.1: PARALLEL TIMING SYNCHRONIZATION ALGORITHM AND ITS IMPLEMENTATION IN HIGH SPEED WIRELESS COMMUNICATION SYSTEMS
Xin Hao, Qiuyu Wu, Zhaohui Wang, Jin Fan, Ying Wang, Changxing Lin, China Academy of Engineering Physics, China

TU-A1-4.2: STUDY ON HDR/WCG SERVICE MODEL FOR UHD SERVICE
Juhan Bae, Jeongyeon Lim, SK Telecom, Korea (South); So Ki Jung, SK Broadband, Korea (South)

TU-A1-4.3: TOWARD A HIGH PERFORMANCE PIANO PRACTICE SUPPORT SYSTEM FOR BEGINNERS
Shota Asahi, Satoshi Tamura, Gifu University, Japan; Yuko Sugiyama, Chubu Gakuin College, Japan; Satoru Hayamizu, Gifu University, Japan

TU-A1-4.4: AN ACCELERATED SAR BACK PROJECTION ALGORITHM USING INTEGER ARITHMETIC
Don Lahiru Nirmal Hettiarachchi, Eric Balster, University of Dayton, United States

TU-A1-4.5: HARMONY AND VOICING INTERPOLATION FOR AUTOMATIC MUSIC COMPOSITION ASSISTANCE
Christoph M. Wilk, Shigeki Sagayama, Meiji University, Japan

TU-A1-5: Recent advances in estimation techniques of phase information

Location: Room 307-A
Time: Tuesday, November 13, 10:30 - 12:10

Session Chairs: Isao Yamada, Tokyo Institute of Technology and Daichi Kitahara, Ritsumeikan University

TU-A1-5.1: SINGULARITY-SPREADING PHASE UNWRAPPING: ITS BASIC IDEA AND THE INFLUENCE OF TIME AND SPACE DISCRETENESS ON THE DYNAMICS
Akira Hirose, The University of Tokyo, Japan

TU-A1-5.2: ADVANCES OF MULTIBASELINE PHASE UNWRAPPING TECHNIQUE IN INSAR SIGNAL PROCESSING
Hanwen Yu, University of Houston, United States; Yang Lan, Mengdao Xing, Xidian University, China

TU-A1-5.3: DEEP LEARNING BASED PERIOD ORDER DETECTION IN FRINGE PROJECTION PROFILOMETRY
H Budianto, Yuk-Hee Chan, P.K. Daniel Lun, The Hong Kong Polytechnic University, China

TU-A1-5.4: PHASE RETRIEVAL — A DECONVOLUTION PERSPECTIVE
Abhilash Sainathan, Chandra Sekhar Seelamantula, Indian Institute of Science, India

TU-A1-5.5: A BRANCH CUT ALGORITHM FOR 180-DEGREE AMBIGUITY RESOLUTION IN 2D VECTOR FIELDS AND ITS APPLICATION TO SINGLE-FRAME FRINGE PROJECTION PROFILOMETRY
Daichi Kitahara, Ritsumeikan University, Japan; Isao Yamada, Tokyo Institute of Technology, Japan

TU-A1-6: Recent Advances in Data Analytics and Knowledge Discovery

Location: Room 308-A
Time: Tuesday, November 13, 10:30 - 12:10

Session Chairs: Marie Katsurai, Doshisha University and Koichiro Yoshino, Nara Institute of Science and Technology

TU-A1-6.1: ACCELERATION OF GAUSSIAN FILTER WITH SHORT WINDOW LENGTH USING DCT-1
Takahiro Yano, Kenjiro Sugimoto, Waseda University, Japan; Yoshimitsu Kuroki, National Institute of Technology, Kurume College, Japan; Sei-ichiro Kamata, Waseda University, Japan

TU-A1-6.2: ESTIMATING CHILDREN'S CHARACTERISTICS BY OBSERVING THEIR CLASSROOM ACTIVITIES
Masahiro Shiomi, Tsuyoshi Komatsubara, ATR, Japan; Thomas Kaczmarek, Takayuki Kanda, Kyoto University, Japan; Hiroshi Ishiguro, Osaka University, Japan

TU-A1-6.3: DECEPTION DETECTION AND ANALYSIS IN SPOKEN DIALOGUES BASED ON FASTTEXT
Naoki Hosomi, Sakriani Sakti, Koichiro Yoshino, Satoshi Nakamura, Nara Institute of Science and Technology, Japan

TU-A1-6.4: JOURNAL NAME EXTRACTION FROM JAPANESE SCIENTIFIC NEWS ARTICLES
Masato Kikuchi, Mitsuo Yoshida, Kyoji Umemura, Toyohashi University of Technology, Japan

TU-A1-6.5: MEASURING RESEARCHER RELATEDNESS WITH CHANGES IN THEIR RESEARCH INTERESTS
Hiroyuki Nishizawa, Marie Katsurai, Doshisha University, Japan; Ikki Ohmukai, Hideaki Takeda, National Institute of Informatics, Japan

TU-A1-7: Wireless Communications and Networks

Location: Room 308-B
Time: Tuesday, November 13, 10:30 - 12:10

Session Chairs: Shinsuke Ibi, Osaka University and Kazunori Hayashi, Kyoto University

TU-A1-7.1: MULTIPLE DIFFERENTIAL DETECTION WITH CHANNEL PREDICTION EMPLOYING SOFT-OUTPUT PER-SURVIVOR PROCESSING
Kazuki Shimomura, Hiroshi Kubo, Ritsumeikan University, Japan

TU-A1-7.3: OPTIMIZATION OF QUANTIZATION LEVELS FOR QUANTIZE-AND-FORWARD RELAYING WITH QAM SIGNALING
Xinyue Ling, Shinsuke Ibi, Osaka University, Japan; Kenji Miyamoto, NTT Access Network Service Systems Laboratories, Japan; Seiichi Sampei, Osaka University, Japan; Jun Terada, Akihiro Otaka, NTT Access Network Service Systems Laboratories, Japan

TU-A1-7.4: A SIGNAL SEPARATION METHOD FOR PHYSICAL WIRELESS PARAMETER CONVERSION SENSOR NETWORKS USING K-SHORTEST PATH
Shuhei Yamasaki, Minato Oriuchi, Osamu Takyu, Keiichiro Shirai, Shinshu University, Japan; Takeo Fujii, The University of Electro-Communications, Japan; Mai Ohta, Fukuoka University, Japan; Fumihito Sasamori, Shiro Handa, Shinshu University, Japan

TU-A1-7.5: EXPERIMENTAL EVALUATION OF INTERFERENCE ROBUSTNESS FOR FREQUENCY SPECTRUM SHARING IN WLAN SYSTEMS
Hironori Godo, Osamu Takyu, Shinshu University, Japan; Koichi Adachi, The University of Electro-Communications, Japan; Mai Ohta, Fukuoka University, Japan; Takeo Fujii, The University of Electro-Communications, Japan; Fumihito Sasamori, Shiro Handa, Shinshu University, Japan

TU-A1-8: Speech Recognition

Location: Room 309
Time: Tuesday, November 13, 10:30 - 12:10

Session Chairs: Jun Du, University of Science and Technology of China and Nam Soo Kim, Seoul National University

TU-A1-8.1: STOCHASTIC DNN-HMM TRAINING FOR ROBUST ASR
Kang Hyun Lee, Woo Hyun Kang, Hyeonseung Lee, Nam Soo Kim, Seoul National University, Korea (South)

TU-A1-8.2: ONLINE SPEAKER ADAPTATION FOR LVCSR BASED ON ATTENTION MECHANISM
Jia Pan, University of Science and Technology of China, China; Diyuan Liu, Genshun Wan, iFlytek, China; Jun Du, University of Science and Technology of China, China; Qingfeng Liu, iFlytek, China; Zhongfu Ye, University of Science and Technology of China, China

TU-A1-8.3: LOW-FREQUENCY CHARACTER CLUSTERING FOR END-TO-END ASR SYSTEM
Hitoshi Ito, Aiko Hagiwara, Manon Ichiki, Takeshi Kobayakawa, Takeshi Mishima, Shoei Sato, NHK (Japan Broadcasting Corp.), Japan; Akio Kobayashi, Tsukuba University of Technology, Japan

TU-A1-8.4: MULTICHANNEL NMF WITH REDUCED COMPUTATIONAL COMPLEXITY FOR SPEECH RECOGNITION
Taiki Izumi, Takanobu Uramoto, Shingo Uenohara, Ken'ichi Furuya, Oita University, Japan; Ryo Aihara, Toshiyuki Hanazawa, Yohei Okato, Mitsubishi Electric Corporation, Japan

TU-A1-8.5: NEURAL SPEECH-TO-TEXT LANGUAGE MODELS FOR RESCORING HYPOTHESES OF DNN-HMM HYBRID AUTOMATIC SPEECH RECOGNITION SYSTEMS
Tomohiro Tanaka, Ryo Masumura, Takafumi Moriya, Yushi Aono, NTT Corporation, Japan

TU-A1-9: Ph.D. Forum I (Oral Presentations)

Location: Room 306-A
Time: Tuesday, November 13, 10:30 - 12:10
Session Chairs: Li-Wei Kang, Jiajia Chen, Yuichi Tanaka, and June Zhang

TU-A1-9.1: FREQUENCY-INVARIANT BEAMFORMING WITH MICROPHONE ARRAYS FOR HUMAN-MACHINE SPEECH INTERFACE AND VOICE COMMUNICATION
Gongping Huang, Jingdong Chen, Northwestern Polytechnical University, China; Jacob Benesty, University of Quebec, Canada

TU-A1-9.2: A NEW ACCURATE AND FAST HOMOGRAPHY COMPUTATION ALGORITHM FOR SPORTS AND TRAFFIC VIDEO ANALYSIS
Shumin Liu, Singapore University of Technology and Design, Singapore; Jia Jia Chen, Nanjing University of Aeronautics and Astronautics, China

TU-A1-9.3: DECISION-MAKING AND GAME THEORY IN DISTRIBUTED ESTIMATION
Kewei Chen, Yih-Fang Huang, University of Notre Dame, United States

TU-A1-9.4: TOWARDS SMART VIDEO REPRESENTATION: JOINT CODING OF VIDEO TEXTURE AND VISUAL FEATURES
Xiang Zhang, Wen Gao, Siwei Ma, Peking University, China

TU-A1-9.5: DYNAMIC GRAPH INFERENCE FROM OBSERVED DATA AND ITS APPLICATIONS
Koki Yamada, Yuichi Tanaka, Tokyo University of Agriculture and Technology, Japan

TU-A1-9.6: A RESEARCH SUMMARY OF RETINAL VESSEL SEGMENTATION
Di Li, Susanto Rahardja, Northwestern Polytechnical University, China

TU-A1-9.7: INDOOR SOUND SOURCE LOCALIZATION WITH PROBABILISTIC NEURAL NETWORK
Yingxiang Sun, Chau Yuen, Singapore University of Technology and Design, Singapore; Jia Jia Chen, Nanjing University of Aeronautics and Astronautics, China

TU-A1-9.8: LIMITED DATA VOICE CONVERSION FROM SPARSE REPRESENTATION TO GANS AND WAVENET
Berrak Sisman, Haizhou Li, National University of Singapore, Singapore

TU-A1-9.9: VISIBILITY ENHANCEMENT VIA LIGHT ADAPTIVE TONE MAPPING
Jiangyan Han, Susanto Rahardja, Northwestern Polytechnical University, China

TU-A1-9.10: AN OPTIMAL RESOURCE ALLOCATION FOR SECURING D2D COMMUNICATION
Oleksii Rudenko, Susanto Rahardja, Northwestern Polytechnical University, China

TU-A1-9.11: RESEARCH SUMMARY: A NEW PARADIGM OF COMMON SUBEXPRESSION ELIMINATION BY UNIFICATION OF ADDITION AND SUBTRACTION
Jiatao Ding, INSEAD, Singapore; Jia Jia Chen, Nanjing University of Aeronautics and Astronautics, China; Chip-Hong Chang, Nanyang Technological University, Singapore

TU-A1-9.12: RESEARCH SUMMARY: AREA- AND POWER-EFFICIENT NEARLY-LINEAR PHASE RESPONSE IIR FILTER BY ITERATIVE CONVEX OPTIMIZATION
Gelei Deng, SUTD, Singapore; Jia Jia Chen, Nanjing University of Aeronautics and Astronautics, China; Chip-Hong Chang, Nanyang Technological University, Slovenia

TU-A1-9.13: VEHICLE DETECTION AND CLASSIFICATION BASED ON DEEP NEURAL NETWORK FOR INTELLIGENT TRANSPORTATION APPLICATIONS
Chia-Chi Tsai, Jiun-In Guo, National Chiao Tung University, Taiwan

TU-A1-9.14: HYPERSPECTRAL IMAGE RESTORATION AND PANSHARPENING
Saori Takeyama, Shunsuke Ono, Itsuo Kumazawa, Tokyo Institute of Technology, Japan

TU-A1-9.15: DIFFUSION STRATEGIES BASED ON CONSENSUS PROPAGATION
Ayano Nakai-Kasai, Kyoto University, Japan; Kazunori Hayashi, Osaka City University, Japan

TU-A1-9.16: ACTION RECOGNITION USING SPHERICAL CAMERA
Sandy Ardianto, Hsueh-Ming Hang, National Chiao Tung University, Taiwan

TU-A1-9.17: REAL OR FAKE IMAGES: ATTACKING AND REINFORCING THE MACHINE LEARNING SYSTEMS
Huy Nguyen, The Graduate University for Advanced Studies, Japan; Isao Echizen, Junichi Yamagishi, National Institute of Informatics, Japan

TU-A1-9.18: CALIBRATION REDUCTION BY EFFICIENT TRANSFORMATION OF INDIVIDUAL TEMPLATES FOR SSVEP BRAIN--COMPUTER INTERFACES
Kaori Suefusa, Toshihisa Tanaka, Tokyo University of Agriculture and Technology, Japan

TU-A1-9.19: A COMPREHENSIVE FRAMEWORK FOR AUTOMATIC SINGING VOICE EVALUATION
Chitralekha Gupta, Haizhou Li, Ye Wang, National University of Singapore, Singapore

TU-A1-9.20: TENSOR DENOISING USING BAYESIAN CP FACTORIZATION AND ITS APPLICATIONS TO COMPUTER VISION
Lihua Gui, Jianting Cao, Saitama Institute of Technology, Japan

TU-A1-9.21: CONVEX COMBINED ADAPTIVE FILTERING ALGORITHM FOR ACOUSTIC ECHO CANCELLATION IN HOSTILE ENVIRONMENTS
Jin Li-You, National Taiwan University, Taiwan; Ying-Ren Chien, National Ilan University, Taiwan; Yu Tsao, Academia Sinica, Taiwan

TU-A1-9.22: BAYESIAN MULTICHANNEL SPEECH ENHANCEMENT WITH A DEEP SPEECH PRIOR
Kouhei Sekiguchi, Kyoto University, Japan; Yoshiaki Bando, National Institute of Advanced Industrial Science and Technology, Japan; Kazuyoshi Yoshii, Tatsuya Kawahara, Kyoto University, Japan

TU-A1-9.23: HOW CONSUMER EMPATHY ASSIST POWER GRID IN DEMAND RESPONSE
Mojtaba Abolfazli, June Zhang, University of Hawaii at Manoa, United States

TU-A1-9.24: MONOCULAR VISION BASED 3D SCENE RECONSTRUCTION AND HUMAN ACTION RECOGNITION
Bo Li, Mingyi He, Northwestern Polytechnical University, China

TU-P1-1: Recent Advances in Online Learning, Stochastic Optimization, and Adaptive Signal Processing

Location: Room 310
Time: Tuesday, November 13, 15:00 - 17:00

Session Chairs: Masahiro Yukawa, Keio University and Isao Yamada, Tokyo Institute of Technology

TU-P1-1.1: DIFFUSION AFFINE PROJECTION ALGORITHM FOR MULTITASK NETWORKS
Vinay Chakravarthi Gogineni, Mrityunjoy Chakraborty, Indian Institute of Technology Kharagpur, India

TU-P1-1.2: A FIXED-POINT ANALYSIS OF REGULARIZED DUAL AVERAGING UNDER STATIC SCENARIOS
Masahiro Yukawa, Keio University, Japan; Isao Yamada, Tokyo Institute of Technology, Japan

TU-P1-1.3: A NESTED L_1-PENALIZED ADAPTIVE NORMALIZED QUASI-NEWTON ALGORITHM FOR SPARSITY-AWARE GENERALIZED EIGEN-SUBSPACE EXTRACTION
Kengo Uchida, Isao Yamada, Tokyo Institute of Technology, Japan

TU-P1-1.4: NONLINEAR ONLINE LEARNING - A KERNEL SMF APPROACH
Kewei Chen, University of Notre Dame, United States; Stefan Werner, Norwegian University of Science and Technology, Norway; Anthony Kuh, University of Hawaii, United States; Yih-Fang Huang, University of Notre Dame, United States

TU-P1-1.5: CONVEX COMBINATION OF DIFFUSION STRATEGIES OVER DISTRIBUTED NETWORKS
Danqi Jin, Jie Chen, Jingdong Chen, Northwestern Polytechnical University, China

TU-P1-1.6: ONLINE UNSUPERVISED KERNEL AFFINE PROJECTION ALGORITHMS
Muhammad Sharif Uddin, Anthony Kuh, University of Hawaii, United States

TU-P1-2: Privacy and Security for Mobile Internet and Cloud Computing in the Big Data Era

Location: Room 303-AB
Time: Tuesday, November 13, 15:00 - 17:00

Session Chairs: Teng Li, Xidian University and Xiaoyan Zhu, Xidian University

TU-P1-2.1: RESEARCH ON DOCKER ROLE ACCESS CONTROL MECHANISM BASED ON DRBAC
Dapeng Lang, Haochen Jiang, Wei Ding, Yu Bai, Harbin Engineering University, China

TU-P1-2.2: LOG-BASED ANOMALIES DETECTION OF MANETS ROUTING WITH REASONING AND VERIFICATION
Teng Li, Jianfeng Ma, Qingqi Pei, Yulong Shen, Cong Sun, Xidian University, China

TU-P1-2.3: PROTECTION OF BIG DATA PRIVACY ON MULTIPLE CLOUD PROVIDERS BY ASYMMETRIC SECURITY SCHEME
Parinya Suwansrikham, Kun She, University of Electronic Science and Technology of China, China

TU-P1-2.4: PRIVACY PROTECTION METHOD BASED ON ACCESS CONTROL
Xin Qiao, Lixiaoyang Wang, Bo Qin, Hong Chen, Suyun Zhao, Renmin University of China, China

TU-P1-2.5: A PRIVACY-PRESERVING ATTRIBUTE-BASED AUTHENTICATION SCHEME FOR CLOUD COMPUTING
Chanying Huang, Songjie Wei, Kedong Yan, Gongxuan Zhang, Anmin Fu, Nanjing University of Science and Technology, China

TU-P1-2.6: TSFR: TIME-AWARE SEMANTIC-BASED FRIEND RECOMMENDATION IN LBSNS
Xiaoyan Zhu, Linjie Zhang, Yizhe Huang, Baoming Bai, Jianfeng Ma, Xidian University, China

TU-P1-3: Recent topics in applications of learning methods to signal and image processing

Location: Room 305-AB
Time: Tuesday, November 13, 15:00 - 17:00

Session Chairs: Kiyoshi Nishikawa, Tokyo Metropolitan University and Guan Gui, Nanjing University of Post and Telecommunications

TU-P1-3.1: DISTANT SOUND SUPPRESSION USING SPECTRAL PHASE VARIANCE FOR TWO CHANNEL BLIND SOURCE SEPARATION
Kazuhiro Murakami, Osaka University, Japan; Arata Kawamura, Kyoto Sangyo University, Japan; Youichi Fujisaka, Nobuhiko Hiruma, Rion Co., Ltd, Japan; Youji Iiguni, Osaka University, Japan

TU-P1-3.2: EFFECTIVE SOUND SOURCE SEPARATION USING SINGLE VOICE ACTIVITY SEGMENTS FOR BINAURAL SOUND
Wataru Noguchi, Osaka University, Japan; Arata Kawamura, Kyoto Sangyo University, Japan; Youji Iiguni, Osaka University, Japan

TU-P1-3.3: RETINEX FOREGROUND SEGMENTATION FOR LOW LIGHT ENVIRONMENTS
Yuuki Tanaka, Yoshihiro Yamashita, Kiyoshi Nishikawa, Toru Yamaguchi, Takao Nishitani, Tokyo Metropolitan University, Japan

TU-P1-3.4: A DIVERSIfiCATION STRATEGY FOR CSD COEFfiCIENT FIR FILTER DESIGN USING GA
Naoki Nakajima, Kenji Suyama, Tokyo Denki University, Japan

TU-P1-3.5: ADMM-NET FOR ROBUST COMPRESSIVE SENSING IMAGE RECONSTRUCTION IN THE PRESENCE OF SYMMETRIC \ALPHA-STABLE NOISE
Yunyi Li, Liya Huang, Yue Yin, Yu Wang, Guan Gui, Nanjing University of Posts and Telecommunications, China

TU-P1-3.6: IMPROVED DICTIONARY LEARNING SCHEME WITH CROSS-LABEL FOR SCENE CLASSIFICATION
Tian Zhou, Liya Huang, Sujuan Yang, Yu Zhao, Guan Gui, Nanjing University of Posts and Telecommunications, China

TU-P1-4: Image/Video Interpretation and Understanding

Location: Room 306-B
Time: Tuesday, November 13, 15:00 - 17:00

Session Chairs: Mingxing Xu , Tsinghua University and Wei Zhou, Northwestern Polytechnical University

TU-P1-4.1: TRAFFIC LANE DETECTION USING FULLY CONVOLUTIONAL NEURAL NETWORK
Jinju Zang, Wei Zhou, Guanwen Zhang, Zhemin Duan, Northwestern Polytechnical University, China

TU-P1-4.2: VISUAL SALIENCY DETECTION ALGORITHM IN COMPRESSED HEVC DOMAIN
Rui Bai, Wei Zhou, Guanwen Zhang, Henglu Wei, Northwestern Polytechnical University, China

TU-P1-4.3: 3D INDOOR SCENE CLASSIFICATION USING TRI-PROJECTION VOXEL SPLATTING
Kazuma Hamada, Masaki Aono, Toyohashi University of Technology, Japan

TU-P1-4.4: IMAGE RECOGNITION BASED ON CONVOLUTIONAL NEURAL NETWORKS USING FEATURES GENERATED FROM SEPARABLE LATTICE HIDDEN MARKOV MODELS
Takayuki Kasugai, Yoshinari Tsuzuki, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda, Nagoya Institute of Technology, Japan

TU-P1-4.5: MMANN: MULTIMODAL MULTILEVEL ATTENTION NEURAL NETWORK FOR HORROR CLIP DETECTION
Xingliang Cheng, Xiaotong Zhang, Mingxing Xu, Thomas Fang Zheng, Tsinghua University, China

TU-P1-4.6: MEASURING INFANT'S LENGTH WITH AN IMAGE
Maolong Tang, Ming-Ting Sun, University of Washington, United States; Leonardo Seda, Universidade de São Paulo, Brazil; James Swanson, University of California, Irvine, United States; Zhengyou Zhang, Tencent, China

TU-P1-5: Advanced Signal Processing and Machine Learning for Audio and Speech Applications

Location: Room 307-A
Time: Tuesday, November 13, 15:00 - 17:00

Session Chairs: Shoji Makino, University of Tsukuba and Hiroshi Saruwatari, University of Tokyo

TU-P1-5.1: GENERATIVE APPROACH USING THE NOISE GENERATION MODELS FOR DNN-BASED SPEECH SYNTHESIS TRAINED FROM NOISY SPEECH
Masakazu Une, National Institute of Technology Tokuyama College, Japan; Yuki Saito, Shinnosuke Takamichi, The University of Tokyo, Japan; Daichi Kitamura, National Institute of Technology, Kagawa College, Japan; Ryoichi Miyazaki, National Institute of Technology Tokuyama College, Japan; Hiroshi Saruwatari, The University of Tokyo, Japan

TU-P1-5.2: DATA AUGMENTATION WITH MOMENT-MATCHING NETWORKS FOR I-VECTOR BASED SPEAKER VERIFICATION
Sayaka Shiota, Tokyo Metropolitan University, Japan; Shinnosuke Takamichi, The University of Tokyo, Japan; Tomoko Matsui, The Institue of Statistical and Mathematics, Japan

TU-P1-5.3: PERFORMANCE BASED COST FUNCTIONS FOR END-TO-END SPEECH SEPARATION
Shrikant Venkataramani, Ryley Higa, Paris Smaragdis, University of Illinois at Urbana-Champaign, United States

TU-P1-5.4: STACKED AUTOENCODER BASED HRTF SYNTHESIS FROM SPARSE DATA
Sunil Bharitkar, Timothy Mauer, Teresa Wells, David Berfanger, HP Inc., United States

TU-P1-5.5: ONLINE LSTM-BASED ITERATIVE MASK ESTIMATION FOR MULTI-CHANNEL SPEECH ENHANCEMENT AND ASR
Yanhui Tu, Jun Du, Nan Zhou, University of Science and Technology of China, China; Chin-Hui Lee, Georgia Institute of Technology, United States

TU-P1-5.6: MICROPHONE POSITION REALIGNMENT BY EXTRAPOLATION OF VIRTUAL MICROPHONE
Ryoga Jinzai, Kouei Yamaoka, Mitsuo Matsumoto, Takeshi Yamada, Shoji Makino, University of Tsukuba, Japan

TU-P1-6: Signal Processing for Assistive Hearing Devices

Location: Room 308-A
Time: Tuesday, November 13, 15:00 - 17:00

Session Chairs: Chin-Tuan Tan, University of Texas at Dallas and Alan Kan, University of Wisconsin-Madison

TU-P1-6.1: DEEP DENOISING AUTOENCODER BASED POST FILTERING FOR SPEECH ENHANCEMENT
Ryandhimas Edo Zezario, Academia Sinica, Taiwan; Jen-Wei Huang, National Cheng Kung University, Taiwan; Xugang Lu, National Institute of Information and Communications Technology, Japan; Yu Tsao, Hsin-Te Hwang, Hsin-Min Wang, Academia Sinica, Taiwan

TU-P1-6.2: WAVELET SCATTERING TRANSFORM FOR VARIABILITY REDUCTION IN CORTICAL POTENTIALS EVOKED BY PITCH MATCHED ELECTRO-ACOUSTIC STIMULATION IN UNILATERAL COCHLEAR IMPLANT PATIENTS
Mehrdad Heydarzadeh, Sara Akbarzadeh, Chin-Tuan Tan, The University of Texas at Dallas, United States

TU-P1-6.3: A SYSTEMATIC ASSESSMENT OF A COCHLEAR IMPLANT PROCESSOR'S ABILITY TO ENCODE INTERAURAL TIME DIFFERENCES
Alan Kan, Z. Ellen Peng, Keng Moua, Ruth Litovsky, University of Wisconsin-Madison, United States

TU-P1-6.4: IMPLICATION OF SPEECH LEVEL CONTROL IN NOISE TO SOUND QUALITY JUDGEMENT
Sara Akbarzadeh, Sungmin Lee, Satnam Singh, Chin-tuan Tan, University of Texas at Dallas, United States

TU-P1-6.5: A SPEECH PROCESSING STRATEGY BASED ON SINUSOIDAL SPEECH MODEL FOR COCHLEAR IMPLANT USERS
Sungmin Lee, Sara Akbarzadeh, Satnam Singh, Chin-tuan Tan, University of Texas at Dallas, United States

TU-P1-6.6: DOMINANT MELODY ENHANCEMENT IN COCHLEAR IMPLANTS
Drew Cappotto, City University of Hong Kong, China; Wenye Xuan, Qinglin Meng, South China University of Technology, China; Chaogang Zhang, KuGou Inc., China; Jan Schnupp, City University of Hong Kong, China

TU-P1-7: Spectrum Monitoring and Management in Wireless Sensor Networks

Location: Room 308-B
Time: Tuesday, November 13, 15:00 - 17:00

Session Chairs: Song Li, China University of Mining and Technology and Danyang Wang, Xidian University

TU-P1-7.1: RESEARCH ON PEDESTRIAN IMAGE RETRIEVAL BASED ON DEEP CONVOLUTION NEURAL NETWORK
Fan Jing, Kunming University of Science and Technology, China; Qu Jinshuai, Chen Mingmu, Yunnan Minzu University, China

TU-P1-7.2: RESOURCE MANAGEMENT FOR NON-ORTHOGONAL MULTIPLE ACCESS BASED MACHINE TYPE COMMUNICATIONS
Song Li, Qingming Wang, Yanjing Sun, Xin Cui, China University of Mining and Technology, China

TU-P1-7.3: MATCHING-BASED RESOURCE ALLOCATION AND DISTRIBUTED POWER CONTROL USING MEAN FIELD GAME IN THE NOMA-BASED UAV NETWORKS
Zihe Zhang, Lixin Li, Xiaomin Liu, Wei Liang, Northwestern Polytechnical University, China; Zhu Han, University of Houston, United States

TU-P1-7.4: ON THE PERFORMANCE OF COGNITIVE CLOUD RADIO ACCESS NETWORKS IN THE PRESENCE OF HARDWARE IMPAIRMENT
Haiyan Huang, Lanzhou Jiaotong University, China; Yangchao Huang, Air Force Engineering University, China; Zhongdong Wu, Xinying Li, Xuejun Zhang, Lanzhou Jiaotong University, China

TU-P1-7.5: A RSS-BASED PASSIVE LOCATING ALGORITHM FOR UNKNOWN SIGNAL SOURCES
Yuxian Bao, Fei Gao, Hongzhen Shi, Guofang Dong, Yunnan Minzu University, China

TU-P1-7.6: COOPERATIVE HYBRID VLC-RF SYSTEMS FOR WSNS
Chao Zhang, Jia Ye, Southwest University, China; Jia Shi, Xidian University, China; Gaofeng Pan, Southwest University, China; Zan Li, Xidian University, China; Zhiguo Ding, The University of Manchester, United Kingdom

TU-P1-8: Convergence of 5G with SDN/NFV/Cloud

Location: Room 309
Time: Tuesday, November 13, 15:00 - 17:00

Session Chairs: Wen-Ping Lai, Yuan Ze University and Po-Chiang Lin, Yuan Ze University

TU-P1-8.1: A FEASIBLE 5G CLOUD-RAN ARCHITECTURE WITH NETWORK SLICING FUNCTIONALITY
Chung-Nan Lee, Ming-Feng Lee, Jian-Min Wu, Wei-Chieh Chang, National Sun Yat-sen University, Taiwan

TU-P1-8.2: USER LOCATION RECOMMENDATION COMBINED WITH MLWDF PACKET SCHEDULING IN LTE DOWNLINK COMMUNICATION
Chiapin Wang, Kuan-Fan Shih, Chi-Ming Li, National Taiwan Normal University, Taiwan

TU-P1-8.3: PERFORMANCE PROFILING OF CLOUD RADIO ACCESS NETWORKS USING OPENAIRINTERFACE
Po-Chiang Lin, Sheng-Lun Huang, Yuan Ze University, Taiwan

TU-P1-8.4: A SKETCH-BASED NETWORK TRAFFIC ANALYSIS IMPLEMENTATION ON COMMODITY OPENFLOW SWITCHES
Zong-Cheng Liou, Chung-Hsiang Cheng, Theophilus Wellem, Ku-Yeh Shih, Yu-Kuen Lai, Chung Yuan Christian University, Taiwan

TU-P1-8.5: UPLINK RESOURCE ALLOCATION FOR NARROWBAND INTERNET OF THINGS (NB-IOT) CELLULAR NETWORKS
Ya-Ju Yu, Jhih-Kai Wang, National University of Kaohsiung, Taiwan

TU-P1-8.6: CONTAINERIZED DESIGN AND REALIZATION OF NETWORK FUNCTIONS VIRTUALIZATION FOR A LIGHT-WEIGHT EVOLVED PACKET CORE USING OPENAIRINTERFACE
Wen-Ping Lai, Yong-Hsiang Wang, Kuan-Chun Chiu, Yuan Ze University, Taiwan

WE-A1-2: Deep learning based brain information processing

Location: Room 303-AB
Time: Wednesday, November 14, 08:00 - 09:40

Session Chairs: Sung-Phil Kim, Ulsan National Institute of Science and Technology and Sung Chan Jun, Gwangju Institute of Science and Technology

WE-A1-2.1: DECODING UPPER LIMB KINEMATIC PARAMETERS FROM MOTOR CORTICAL ACTIVITY USING A DEEP LEARNING ALGORITHM
Jisung Park, Sung-Phil Kim, Ulsan National Institute of Science and Technology, Korea (South)

WE-A1-2.2: INDIVIDUAL DIFFERENCES AND IMPACTS OF PSYCHOPATHOLOGICAL SYMPTOMS IN OBSERVATIONAL REWARD LEARNING
Dongil Chung, HyungSeok Won, Yoo Joo Jeong, Dasom Park, HeeYoung Seon, Ulsan National Institute of Science and Technology, Korea (South)

WE-A1-2.3: EEG HYPERSCANNING FOR EIGHT OR MORE PERSONS - FEASIBILITY STUDY FOR EMOTION RECOGNITION USING DEEP LEARNING TECHNIQUE
Sunghan Lee, Sangjun Han, Sung Chan Jun, Gwangju Institute of Science and Technology, Korea (South)

WE-A1-2.4: EPILEPTIC FOCUS LOCALIZATION BASED ON IEEG BY USING POSITIVE UNLABELED (PU) LEARNING
Xuyang Zhao, Saitama Institute of Technology, Japan; Toshihisa Tanaka, Tokyo University of Agriculture and Technology, Japan; Wanzeng Kong, Hangzhou Dianzi University, China; Qibin Zhao, RIKEN Center for Advanced Intelligence Project (AIP), Japan; Jianting Cao, Saitama Institute of Technology, Japan; Hidenori Sugano, Juntendo University Faculty of Medicine, Japan; Noboru Yoshida, Juntendo University Nerima Hospital, Japan

WE-A1-3: Advanced Image Processing and Computer Vision Techniques (I)

Location: Room 305-AB
Time: Wednesday, November 14, 08:00 - 09:40

Session Chairs: Jae-Young Sim, Ulsan National Institute of Science and Technology and Chul Lee, Pukyong National University

WE-A1-3.1: VIDEO SALIENCY DETECTION USING ADAPTIVE FEATURE COMBINATION AND LOCALIZED SALIENCY COMPUTATION
Eunpil Park, Byeong-Ju Han, Seungjoon Yang, Jae-Young Sim, UNIST, Korea (South)

WE-A1-3.2: CONVOLUTION NEURAL NETWORK BASED VIDEO CODING TECHNIQUE USING REFERENCE VIDEO SYNTHESIS
Jung Kyung Lee, Nayoung Kim, Ewha Womans University, Korea (South); Seunghyun Cho, Realistic AV Research Group, Electronics and Telecommunications Research Institute, Korea (South); Je-Won Kang, Ewha Womans University, Korea (South)

WE-A1-3.3: CHANGE DETECTION IN HIGH RESOLUTION SATELLITE IMAGES USING AN ENSEMBLE OF CONVOLUTIONAL NEURAL NETWORKS
Kyungsun Lim, Dongkwon Jin, Chang-Su Kim, Korea University, Korea (South)

WE-A1-3.4: BLOCK-MATCHING CONVOLUTIONAL NEURAL NETWORK (BMCNN): IMPROVING CNN-BASED DENOISING BY BLOCK-MATCHED INPUTS
Byeongyong Ahn, Samsung Electronics, Korea (South); Yoonsik Kim, Gu Yong Park, Nam Ik Cho, INMC, Seoul National University, Korea (South)

WE-A1-4: Information hiding and Detection in Multimedia Big Data

Location: Room 306-B
Time: Wednesday, November 14, 08:00 - 09:40

Session Chairs: Yanzhen Ren, Wuhan University and Xiangui Kang, Sun Yat-sen University

WE-A1-4.1: STEGANOGRAPHY WITH CONVINCING NORMAL IMAGE FROM A JOINT GENERATIVE ADVERSARIAL FRAMEWORK
Hanqi Zi, Qiong Zhang, Jianhua Yang, Xiangui Kang, Sun Yat-sen University, China

WE-A1-4.2: DEEP LEARNING WITH FEATURE REUSE FOR JPEG IMAGE STEGANALYSIS
Jianhua Yang, Xiangui Kang, Sun Yat-sen University, China; Edward K. Wong, New York University, China; Yun-Qing Shi, New Jersey Institute of Technology, China

WE-A1-4.3: SILK STEGANOGRAPHY SCHEME BASED ON THE DISTRIBUTION OF LSF PARAMETER
Yanzhen Ren, Weiman Zheng, Lina Wang, Wuhan University, China

WE-A1-4.4: STEGANALYSIS OF ADAPTIVE JPEG STEGANOGRAPHY BASED ON RESDET
Xiaosa Huang, Shilin Wang, Tanfeng Sun, Gongshen Liu, Xiang Lin, Shanghai Jiao Tong University, China

WE-A1-4.5: SPEAKER IDENTITY TRACING USING FINGERPRINT DATA HIDING AGAINST TELECOMMUNICATIONS FRAUD
Hongxia Wang, Sichuan University, China; Jing Sang, Southwest Jiaotong University, China

WE-A1-5: Recent advances of machine learning and signal processing in hypercomplex domain

Location: Room 307-A
Time: Wednesday, November 14, 08:00 - 09:40

Session Chairs: Isao Yamada , Tokyo Institute of Technology and Akira Hirose, University of Tokyo

WE-A1-5.1: REMARKS ON CONTROL OF ROBOT MANIPULATOR USING QUATERNION NEURAL NETWORK
Kazuhiko Takahashi, Doshisha University, Japan

WE-A1-5.2: COMPLEX-VALUED AND QUATERNION NEURAL NETWORKS TO DEAL WITH COMPLEX AMPLITUDE AND POLARIZATION: THEIR STRENGTH IN ELECTRONICS
Akira Hirose, The University of Tokyo, Japan

WE-A1-5.3: QUATERNION KERNEL NORMALIZED MINIMUM ERROR ENTROPY ADAPTIVE ALGORITHMS
Carlo Safarian, Tokunbo Ogunfunmi, Santa Clara University, United States

WE-A1-5.4: HYPERCOMPLEX PRINCIPAL COMPONENT PURSUIT VIA CONVEX OPTIMIZATION
Takehiko Mizoguchi, Isao Yamada, Tokyo Institute of Technology, Japan

WE-A1-6: Minor- and Multi- lingual speech and language processing

Location: Room 308-A
Time: Wednesday, November 14, 08:00 - 09:40

Session Chairs: Dong Wang, Tsinghua University and Guanyu Li, Northwest Minzu University

WE-A1-6.1: MULTILINGUAL STEMMING AND TERM EXTRACTION FOR UYGHUR, KAZAK AND KIRGHIZ
Mijit Ablimit, Sardar Parhat, Askar Hamdulla, Xinjiang University, China; Thomas Fang Zheng, Tsinghua University, China

WE-A1-6.2: MAP AND RELABEL: TOWARDS ALMOST-ZERO RESOURCE SPEECH RECOGNITION
Ying Shi, Zhiyuan Tang, Lantian Li, Zheling Zhang, Dong Wang, Tsinghua University, China

WE-A1-6.3: AP18-OLR CHALLENGE: THREE TASKS AND THEIR BASELINES
Zhiyuan Tang, Dong Wang, Tsinghua University, China; Qing Chen, Speechocean, China

WE-A1-6.4: TIBETAN ACOUSTIC MODEL RESEARCH BASED ON TDNN
Jinghao Yan, Hongzhi Yu, Guanyu Li, Northwest Minzu University, China

WE-A1-6.5: TDNN-BASED MULTILINGUAL MIX-SYNTHESIS WITH LANGUAGE DISCRIMINATIVE TRAINING
Gulijiamali Maimaitiaili, Xinjiang Normal University, China; Zhiyong Zhang, Aisikaer Rouzi, Tsinghua University, China

WE-A1-7: Hyperspectral and Multiview Image Processing

Location: Room 308-B
Time: Wednesday, November 14, 08:00 - 09:40

Session Chairs: Mingyi He, Northwestern Polytechnical University and Qian Du, Mississippi State University

WE-A1-7.1: CNN-BASED LARGE SCALE LANDSAT IMAGE CLASSIFICATION
Xuemei Zhao, Key Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, China; Lianru Gao, Zhengchao Chen, Bing Zhang, Key LaboraKey Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earthtory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, China; Wenzhi Liao, Department Telecommunications and Information Processing, Belgium

WE-A1-7.2: PARALLEL MULTI-VIEW LOW-RANK AND SPARSE SUBSPACE CLUSTERING FOR UNSUPERVISED HYPERSPECTRAL IMAGE CLASSIFICATION
Long Tian, Qian Du, Mississippi State University, United States

WE-A1-7.3: COCOA BEAN QUALITY ASSESSMENT USING CLOSED RANGE HYPERSPECTRAL IMAGES
Oswaldo Bayona, Daniel Ochoa, Ronald Criollo, Juan Cevallos-Cevallos, Escuela Superior Politécnica del Litoral, Ecuador; Wenzhi Liao, Ghent University, Belgium

WE-A1-7.4: KERNEL EXTREME LEARNING MACHINE JOINT SPATIAL-SPECTRAL INFORMATION FOR HYPERSPECTRAL IMAGE CLASSIFICATION
Xumin Yu, Yan Feng, Northwestern Polytechnical University, China; Zhongliang Wang, Tongling University, China; Yanlong Gao, Northwestern Polytechnical University, China

WE-A1-8: Speech Synthesis

Location: Room 309
Time: Wednesday, November 14, 08:00 - 09:40

Session Chairs: Junichi Yamagishi, National Institute of Informatics, Japan and Keiichi Tokuda, Nagoya Institute of Technology

WE-A1-8.1: A DNN-BASED EMOTIONAL SPEECH SYNTHESIS BY SPEAKER ADAPTATION
Hongwu Yang, Northwest Normal University, Engineering Research Center of Gansu Province for Intelligent Information Technology and Application, National and Provincial Joint Engineering Laboratory of Learning Analysis Technology in Online Education, China; Weizhao Zhang, Northwest Normal University, Engineering Research Center of Gansu Province for Intelligent Information Technology and Application, China; Pengpeng Zhi, Northwest Normal University, China

WE-A1-8.2: SPEAKER ADAPTATION FOR SPEECH SYNTHESIS BASED ON DEEP NEURAL NETWORKS USING HIDDEN SEMI-MARKOV MODEL STRUCTURES
Kento Nakao, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda, Nagoya Institute of Technology, Japan

WE-A1-8.3: SPEECH SYNTHESIS USING WAVENET VOCODER BASED ON PERIODIC/APERIODIC DECOMPOSITION
Takato Fujimoto, Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda, Nagoya Institute of Technology, Japan

WE-A1-8.4: UNSUPERVISED SPEAKER ADAPTATION FOR DNN-BASED SPEECH SYNTHESIS USING INPUT CODES
Shinji Takaki, National Institute of Informatics, Japan; Yoshikazu Nishimura, Alt Inc., Japan; Junichi Yamagishi, National Institute of Informatics, Japan

WE-A1-8.5: PROSODY-AWARE SUBWORD EMBEDDING CONSIDERING JAPANESE INTONATION SYSTEMS AND ITS APPLICATION TO DNN-BASED MULTI-DIALECT SPEECH SYNTHESIS
Takanori Akiyama, Shinnosuke Takamichi, Hiroshi Saruwatari, The University of Tokyo, Japan

WE-A1-P: Speech Processing

Location: Room 306-A
Time: Wednesday, November 14, 08:00 - 09:40

Session Chairs: Chia-Ping Chen, National Sun Yat-Sen University and Hemant A. Patil, Dhirubhai Ambani Institute of Information and Communication Technology

WE-A1-P.1: FEATURE-BASED LEARNING HIDDEN UNIT CONTRIBUTIONS FOR DOMAIN ADAPTATION OF RNN-LMS
Michael Hentschel, Nara Institute of Science and Technology, Japan; Marc Delcroix, Atsunori Ogawa, Tomohiro Nakatani, NTT Communication Science Laboratories, Japan

WE-A1-P.2: COMPOSITE WAVELET MODEL FOR STABILITY-ORIENTED SPEECH SYNTHESIS FROM CEPSTRAL FEATURES
Junya Koguchi, Shigeki Sagayama, Meiji University, Japan

WE-A1-P.4: A DNN-BASED MANDARIN-TIBETAN CROSS-LINGUAL SPEECH SYNTHESIS
Weitong Guo, Hongwu Yang, Zhenye Gan, Northwest Normal University, China

WE-A1-P.5: COMPENSATING UTTERANCE INFORMATION IN FIXED PHRASE SPEAKER VERIFICATION
Rohan Kumar Das, Maulik Madhavi, Haizhou Li, National University of Singapore, Singapore

WE-A1-P.6: SPEECH INTELLIGIBILITY ENHANCEMENT IN NOISY ENVIRONMENTS VIA VOICE CONVERSION WITH GLIMPSE PROPORTION MEASURE
Taiho Takeuchi, Yosuke Tatekura, Shizuoka University, Japan

WE-A1-P.7: CUSTOMIZATION OF AN EXAMPLE-BASED DIALOG SYSTEM WITH USER DATA AND DISTRIBUTED WORD REPRESENTATIONS
Eichi Seto, Ryota Nishimura, Norihide Kitaoka, Tokushima University, Japan

WE-A1-P.8: APPLYING COMPLEX-VALUED NEURAL NETWORKS TO ACOUSTIC MODELING FOR SPEECH RECOGNITION
Daichi Hayakawa, Takashi Masuko, Hiroshi Fujimura, Toshiba Corporation, Japan

WE-A1-P.9: DIALOGUE BEHAVIOR CONTROL MODEL FOR EXPRESSING A CHARACTER OF HUMANOID ROBOTS
Kenta Yamamoto, Koji Inoue, Shizuka Nakamura, Katsuya Takanashi, Tatsuya Kawahara, Kyoto University, Japan

WE-A1-P.10: BOTTLENECK FEATURE-MEDIATED DNN-BASED FEATURE MAPPING FOR THROAT MICROPHONE SPEECH RECOGNITION
Takahito Suzuki, Shizuoka University, Japan; Jun Ogata, National Institute of Advanced Industrial Science and Technology, Japan; Takashi Tsunakawa, Masafumi Nishida, Masafumi Nishimura, Shizuoka University, Japan

WE-A1-P.11: DISCRIMINATIVE FEATURE EXTRACTION BASED ON SEQUENTIAL VARIATIONAL AUTOENCODER FOR SPEAKER RECOGNITION
Takenori Yoshimura, Natsumi Koike, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda, Nagoya Institute of Technology, Japan

WE-A1-P.12: ACOUSTIC MODEL ADAPTATION FOR EMOTIONAL SPEECH RECOGNITION USING TWITTER-BASED EMOTIONAL SPEECH CORPUS
Tetsuo Kosaka, Yoshitaka Aizawa, Masaharu Kato, Yamagata University, Japan; Takashi Nose, Tohoku University, Japan

WE-A1-P.13: USER’S INTENTION UNDERSTANDING IN QUESTION-ANSWERING SYSTEM USING ATTENTION-BASED LSTM
Yuki Matsuyoshi, Tetsuya Takiguchi, Yasuo Ariki, Kobe University, Japan

WE-A1-P.14: VV-COUPLET: AN OPEN SOURCE CHINESE COUPLET GENERATION SYSTEM
Jiyuan Zhang, Zheling Zhang, Shiyue Zhang, Dong Wang, Center for Speech and Language Technologies, Research Institute of Information Technology, China

WE-A1-P.15: HYBRID TEXT-TO-SPEECH FOR ARTICULATION DISORDERS WITH A SMALL AMOUNT OF NON-PARALLEL DATA
Ryuka Nanzaka, Tetsuya Takiguchi, Kobe University, Japan

WE-A1-P.16: SPEAKER VERIFICATION BASED ON DEEP NEURAL NETWORK FOR TEXT-CONSTRAINED SHORT COMMANDS
Heesu Kim, Euntae Choi, Kiyoung Choi, Seoul National University, Korea (South)

WE-A1-P.17: ATTENTION BASED FULLY CONVOLUTIONAL NETWORK FOR SPEECH EMOTION RECOGNITION
Yuanyuan Zhang, Jun Du, Zi-Rui Wang, Jianshu Zhang, Yanhui Tu, University of Science and Technology of China, China

WE-A1-P.18: NOVEL INTER MIXTURE WEIGHTED GMM POSTERIORGRAM FOR DNN AND GAN-BASED VOICE CONVERSION
Nirmesh Shah, Sreeraj R, Neil Shah, Hemant Patil, Dhirubhai Ambani Institute of Information and Communication Technology, India

WE-A1-P.19: A PREDICTION MODEL FOR END-OF-UTTERANCE BASED ON PROSODIC FEATURES AND PHRASE-DEPENDENCY IN SPONTANEOUS JAPANESE
Yuichi Ishimoto, National Institute for Japanese Language and Linguistics, Japan; Takehiro Teraoka, Takushoku University, Japan; Mika Enomoto, Tokyo University of Technology, Japan

WE-A2-2: Biomedical Signal Processing and Systems

Location: Room 303-AB
Time: Wednesday, November 14, 11:10 - 12:50

Session Chairs: Sung Chan Jun, Gwangju Institute of Science and Technology and Z. Jane Wang, University of British Columbia

WE-A2-2.1: CLASSIFICATION OF SHUNT MURMURS FOR DIAGNOSIS OF ARTERIOVENOUS FISTULA STENOSIS
Daisuke Higashi, Keisuke Nishijima, Ken'ichi Furuya, Oita University, Japan; Keiko Tanaka, Satoko Shin, Oita University of Nursing and Health sciences, Japan

WE-A2-2.2: UNRESTRAINED DIASTOLIC BLOOD PRESSURE ESTIMATION METHOD USING HEARTBEAT DURING SLEEP
Tomomasa Yamasaki, Hikaru Iwasaki, Takashi Kaburagi, Yosuke Kurihara, Aoyama Gakuin University, Japan

WE-A2-2.3: SUPPORT FOR A CLINICAL DIAGNOSIS OF MILD COGNITIVE IMPAIRMENT USING PHOTOPLETHYSMOGRAPHY AND GAIT SENSORS
Migyeong Gwak, Majid Sarrafzadeh, Ellen Woo, University of California, Los Angeles, United States

WE-A2-2.4: EEG DIPOLE SOURCE LOCALIZATION IN HEMISPHERICAL HARMONICS DOMAIN
Amita Giri, Lalan Kumar, Tapan Gandhi, Indian Institute of Technology Delhi, India

WE-A2-2.5: AUTOMATIC DETECTION OF TRANSLUCENCY USING A DEEP LEARNING METHOD FROM PATCHES OF CLINICAL BASAL CELL CARCINOMA IMAGES
He Huang, Pegah Kharazmi, David McLean, Harvey Lui, Jane Wang, University of British Columbia, Canada; Tim Lee, BC Cancer Agency, Canada

WE-A2-3: Advanced Image Processing and Computer Vision Techniques (II)

Location: Room 305-AB
Time: Wednesday, November 14, 11:10 - 12:50

Session Chairs: Jae-Young Sim, Ulsan National Institute of Science and Technology and Chang-Su Kim, Korea University

WE-A2-3.1: SKIPPED-HIERARCHICAL FEATURE PYRAMID NETWORKS FOR NUCLEI INSTANCE SEGMENTATION
Hyekyoung Hwang, Toan Duc Bui, Sang-il Ahn, Jitae Shin, Sungkyunkwan University, Korea (South)

WE-A2-3.2: PEDESTRIAN DETECTION BASED ON DEEP FUSION NETWORK USING FEATURE CORRELATION
Yongwoo Lee, Toan Duc Bui, Jitae Shin, Sungkyunkwan University, Korea (South)

WE-A2-3.3: OPTIMIZED TONE MAPPING OF HDR IMAGES VIA HVS MODEL-BASED 2D HISTOGRAM EQUALIZATION
Nam Hoang Nguyen, Tu Van Vo, Pukyong National University, Korea (South); Younghoon Jeong, Youngsu Moon, Samsung Electronics, Korea (South); Chul Lee, Pukyong National University, Korea (South)

WE-A2-3.4: VIDEO GENERATION AND SYNTHESIS NETWORK FOR LONG-TERM VIDEO INTERPOLATION
Nayoung Kim, Jung Kyung Lee, Chae Hwa Yoo, Seunghyun Cho, Je-Won Kang, Ewha Womans University, Korea (South)

WE-A2-4: Machine Learning for Information Processing and Forensics

Location: Room 306-B
Time: Wednesday, November 14, 11:10 - 12:50

Session Chairs: Xiangui Kang, Sun Yat-sen University and Shunquan Tan, Shenzhen University

WE-A2-4.1: RELOCATED I-FRAMES DETECTION IN H.264 DOUBLE COMPRESSED VIDEOS BASED ON GENETIC-CNN
Qiang Xu, Xinghao Jiang, Tanfeng Sun, Peisong He, Shilin Wang, Shanghai Jiao Tong University, China; Bin Li, Shenzhen Key Laboratory of Media Security, China

WE-A2-4.2: DETECTION OF DOUBLE JPEG COMPRESSION WITH THE SAME QUANTIZATION MATRIX BASED ON CONVOLUTIONAL NEURAL NETWORKS
Peng Peng, Tanfeng Sun, Xinghao Jiang, Ke Xu, Shanghai Jiao Tong University, China; Bin Li, Shenzhen Key Laboratory of Media Security, China; Yun-Qing Shi, New Jersey Institute of Technology, United States

WE-A2-4.3: CAN FORENSIC DETECTORS IDENTIFY GAN GENERATED IMAGES?
Haodong Li, Han Chen, Bin Li, Shunquan Tan, Shenzhen University, China

WE-A2-4.4: DOUBLE JPEG COMPRESSION DETECTION BY EXPLORING THE CORRELATIONS IN DCT DOMAIN
Pengpeng Yang, Rongrong Ni, Yao Zhao, Beijing Jiaotong University, China

WE-A2-4.5: FAKE COLORIZED IMAGE DETECTION WITH CHANNEL-WISE CONVOLUTION BASED DEEP-LEARNING FRAMEWORK
Long Zhuo, Shunquan Tan, Jishen Zeng, Bin Li, Shenzhen University, China

WE-A2-5: Optimization, Control, and Data Analytics for Cyber-Physical Systems

Location: Room 307-A
Time: Wednesday, November 14, 11:10 - 12:50

Session Chair: Yu Zhang, UCSC

WE-A2-5.1: OPTIMAL CONTROL FOR ELECTRICITY STORAGE AGAINST THREE-TIER TOU PRICING
Chenye Wu, Yang Yu, Tsinghua University, China

WE-A2-5.2: OPTIMAL ROTATIONAL LOAD SHEDDING VIA BILINEAR INTEGER PROGRAMMING
Atif Maqsood, Yu Zhang, Keith Corzine, University of California, Santa Cruz, United States

WE-A2-5.3: ELECTRICITY DEMAND RESPONSE UNDER REAL-TIME PRICING: A MULTI-ARMED BANDIT GAME
Zibo Zhao, Andrew L. Liu, Purdue University, United States; Yihsu Chen, University of California, Santa Cruz, United States

WE-A2-6: Subjective perception and neural processing of speech in complex environments (I)

Location: Room 308-A
Time: Wednesday, November 14, 11:10 - 12:50

Session Chairs: Nengheng Zheng, Shenzhen University and Qinglin Meng, South China University of Technology

WE-A2-6.1: EFFECT OF HUMAN SPEAKER'S HEAD ROTATION ON SPEECH TRANSMISSION INDEX IN VEHICLE SOUND ENVIRONMENT
Le Yu, Guangzheng Yu, Qinglin Meng, South China University of Technology, China

WE-A2-6.2: EFFECTS OF VOCODER PROCESSING ON SPEECH PERCEPTION IN REVERBERANT CLASSROOMS
Qinglin Meng, Guangzheng Yu, South China University of Technology, China; Yangyang Wan, Shenzhen University, China; Fanhui Kong, Xianren Wang, Sun Yat-sen University, China; Nengheng Zheng, Shenzhen University, China

WE-A2-6.3: NOISE SUPPRESSION WITH APPARENT GAIN THRESHOLD FOR COCHLEAR IMPLANTS: A VOCODER SIMULATED VERIFICATION
Nengheng Zheng, Xiaowei Shao, Baihan Zeng, Shenzhen University, China; Qinglin Meng, South China University of Technology, China

WE-A2-6.4: SPEECH ENHANCEMENT ALGORITHM BASED ON REASSIGNED SPECTROGRAM AND AUDITORY MASKING
Jie Wang, Chengcheng Yang, Manlu Huang, Linhuang Yan, Guangzhou University, China; Jinqiu Sang, Chinese Academy of Sciences, China

WE-A2-7: Spectrum modeling and recognition for wireless communication

Location: Room 308-B
Time: Wednesday, November 14, 11:10 - 12:50

Session Chair: Osamu Takyu, Shinshu University

WE-A2-7.1: ORTHOGONAL RESOURCE ALLOCATION USING SVM FOR CSMA/CA
Naoki Aihara, Koichi Adachi, The University of Electro-Communications, Japan

WE-A2-7.2: DATA SEPARATION TECHNIQUE USING SPATIAL CORRELATION OF SENSING RESULTS FOR PHYSICAL WIRELESS PARAMETER CONVERSION SENSOR NETWORKS
Naoya Amano, Osamu Takyu, Keiichiro Shirai, Fumihito Sasamori, Shiro Handa, Shinshu University, Japan

WE-A2-7.3: A STUDY ON RADIO SIGNAL IDENTIFICATION METHOD FOR SPECTRUM SHARING
Haruki Fujita, Mai Ohta, Fukuoka University, Japan

WE-A2-7.4: A STUDY ON IMPULSE RESPONSE MODEL OF REFLECTED PATH FOR THZ BAND
Kazuhiro Tsujimura, Kenta Umebayashi, Tokyo University of Agriculture and Technology, Japan; Joonas Kokkoniemi, Janne Lehtomaki, University of Oulu, Finland

WE-A2-7.5: ENVIRONMENTAL AWARE HIERARCHICAL AD HOC NETWORK WITH MULTIPLE FREQUENCY BANDS USING WEIGHTED LAPLACIAN MATRIX
Toshiyuki Shizuoka, Takeo Fujii, The University of Electro-Communications, Japan

WE-A2-8: Voice Conversation/Dialog

Location: Room 309
Time: Wednesday, November 14, 11:10 - 12:50

Session Chairs: Norihide Kitaoka, Tokushima University and Yu Tsao, Academia Sinica

WE-A2-8.1: EFFECT OF MUTUAL SELF-DISCLOSURE IN SPOKEN DIALOG SYSTEM ON USER IMPRESSION
Shunsuke Tada, Yuya Chiba, Takashi Nose, Akinori Ito, Tohoku University, Japan

WE-A2-8.2: ONLINE CALL SCENE SEGMENTATION OF CONTACT CENTER DIALOGUES BASED ON ROLE AWARE HIERARCHICAL LSTM-RNNS
Ryo Masumura, Setsuo Yamada, Tomohiro Tanaka, Atsushi Ando, Hosana Kamiyama, Yushi Aono, NTT Corporation, Japan

WE-A2-8.3: A REVISIT TO FEATURE HANDLING FOR HIGH-QUALITY VOICE CONVERSION BASED ON GAUSSIAN MIXTURE MODEL
Hitoshi Suda, Gaku Kotani, Shinnosuke Takamichi, Daisuke Saito, The University of Tokyo, Japan

WE-A2-8.4: ERROR REDUCTION NETWORK FOR DBLSTM-BASED VOICE CONVERSION
Mingyang Zhang, Southeast University, China; Berrak Sisman, Sai Sirisha Rallabandi, Haizhou Li, National University of Singapore, Singapore; Li Zhao, Southeast University, China

WE-A2-8.5: MANY-TO-MANY VOICE CONVERSION BASED ON BOTTLENECK FEATURES WITH VARIATIONAL AUTOENCODER FOR NON-PARALLEL TRAINING DATA
Yanping Li, Nanjing University of Posts and Telecommunications, China; Kong Aik Lee, NEC Corporation, Japan; Yougen Yuan, Northwestern Polytechnical University, China; Haizhou Li, National University of Singapore, Singapore; Zhen Yang, Nanjing University of Posts and Telecommunications, China

WE-A2-P: Signal and Information Processing: Theory and Methods

Location: Room 306-A
Time: Wednesday, November 14, 11:10 - 12:50

Session Chairs: Takeo Fujii , The University of Electro-Communications and Kosin Chamnongthai, King Mongkut's Univeraity of Technology Thonburi

WE-A2-P.1: IDENTIFICATION AND RESTORATION OF LZ77 COMPRESSED DATA USING A MACHINE LEARNING APPROACH
Beom Kwon, Myongsik Gong, Jungwoo Huh, Sanghoon Lee, Yonsei University, Korea (South)

WE-A2-P.2: A FRACTIONAL INTEGRATOR BASED NOVEL DETECTOR FOR WEAK SIGNAL DETECTION WITH WATERMARK APPLICATION
Sumit Kumar, Rajib Jha, Indian Institute of Technology Patna, India

WE-A2-P.3: FEATURE PYRAMID DEEP MATCHING AND LOCALIZATION NETWORK FOR IMAGE FORENSICS
Kui Ye, Jing Dong, Wei Wang, Bo Peng, Tieniu Tan, Institute of Automation, Chinese Academy of Sciences, China

WE-A2-P.4: A DEEP LEARNING APPROACH TO THE ACOUSTIC CONDITION MONITORING OF A SINTERING PLANT
Shahab Pasha, ARC Research Hub for Australian Steel Manufacturing, Australia; Christian Ritz, David Stirling, University of Wollongong, Australia; Paul Zulli, ARC Research Hub for Australian Steel Manufacturing, Australia; David Pinson, Sheng Chew, BlueScope Steel, Australia

WE-A2-P.5: PREDICTION METHOD OF INFECTION SPREADING WITH CNN FOR SELF-EVOLVING BOTNETS
Keita Kishioka, Koki Hongyo, Kansai University, Japan; Tomotaka Kimura, Doshisha University, Japan; Takanori Kudo, Setsunan University, Japan; Yoshiaki Inoue, Osaka University, Japan; Kouji Hirata, Kansai University, Japan

WE-A2-P.6: RACORN-K: RISK-AVERSION PATTERN MATCHING-BASED PORTFOLIO SELECTION
Yang Wang, Dong Wang, Thomas Fang Zheng, Tsinghua University, China

WE-A2-P.7: STATISTICAL-MECHANICAL ANALYSIS OF THE SECOND-ORDER ADAPTIVE VOLTERRA FILTER
Kimiko Motonaka, Kansai University, Japan; Takashi Katsube, KYOCERA Communication Systems Co., Ltd., Japan; Yoshinobu Kajikawa, Seiji Miyoshi, Kansai University, Japan

WE-A2-P.8: DISTRIBUTED OPTIMIZATION OF QUADRATIC COSTS WITH A GROUP-SPARSITY REGULARIZATION VIA PDMM
Kangwei Hu, Danqi Jin, Wen Zhang, Jie Chen, Northwestern Polytechnical University, China

WE-A2-P.10: NONLINEAR BEAMFORMING VIA CONVEX OPTIMIZATION FOR PHASED ARRAY WEATHER RADAR
Daichi Kitahara, Maya Nakahara, Akira Hirabayashi, Ritsumeikan University, Japan; Eiichi Yoshikawa, Japan Aerospace Exploration Agency, Japan; Hiroshi Kikuchi, Tomoo Ushio, Tokyo Metropolitan University, Japan

WE-A2-P.11: MULTICARRIER ENABLED BASEBAND SUBSAMPLING MIMO SYSTEM (MBS-MIMO)
Franz G. Aletsee, Reinhard Stolle, Augsburg University of Applied Sciences, Germany

WE-A2-P.12: ENSEMBLE DEEP LEARNING BASED COOPERATIVE SPECTRUM SENSING WITH STACKING FUSION CENTER
Hang Liu, The University of Electro-Communications, Japan; Xu Zhu, Toshiba Corporation, Japan; Takeo Fujii, The University of Electro-Communications, Japan

WE-A2-P.13: A STUDY ON INDOOR DIMMING METHOD UTILIZING OUTSIDE LIGHT FOR POWER SAVING
Kengo Sasaki, Eiji Okamoto, Nagoya Institute of Technology, Japan

WE-A2-P.14: A CAPSULE BASED APPROACH FOR POLYPHONIC SOUND EVENT DETECTION
Yaming Liu, Jian Tang, Yan Song, Lirong Dai, University of Science and Technology of China, China

WE-A2-P.15: FULLY DATA-DRIVEN OPTIMIZATION OF GAUSSIAN PARAMETERS FOR KERNEL CLASSIFIER
Kosuke Fukumori, Toshihisa Tanaka, Tokyo University of Agriculture and Technology, Japan

WE-P1-2: Emerging Technologies for Healthcare

Location: Room 303-AB
Time: Wednesday, November 14, 16:20 - 18:00

Session Chairs: Beth Jelfs, RMIT University and Ling Li, University of Kent

WE-P1-2.1: RESTORATION OF DRY ELECTRODE EEG USING DEEP CONVOLUTIONAL NEURAL NETWORK
Yuki Kojoma, Yoshikazu Washizawa, The University of Electro-Communications, Japan

WE-P1-2.2: GRAPHICAL USER INTERFACE FOR MEDICAL DEEP LEARNING - APPLICATION TO MAGNETIC RESONANCE IMAGING
Sebastian Milde, Annika Liebgott, Ziwei Wu, Wenyi Feng, Jiahuan Yang, Lukas Mauch, University of Stuttgart, Germany; Petros Martirosian, Fabian Bamberg, Konstantin Nikolaou, Sergios Gatidis, Fritz Schick, University of Tuebingen, Germany; Bin Yang, Thomas Küstner, University of Stuttgart, Germany

WE-P1-2.3: MUSCLE CONNECTIVITY ANALYSIS FOR HAND GESTURE RECOGNITION VIA SEMG
Yuzhou Lin, Philippe De Wilde, Ramaswamy Palaniappan, Ling Li, The University Of Kent, United Kingdom

WE-P1-2.4: ESTIMATING MUSCLE FIBRE CONDUCTION VELOCITY IN THE PRESENCE OF ARRAY MISALIGNMENT
Christopher Gilliam, Beth Jelfs, RMIT University, Australia

WE-P1-2.5: ANALYSIS OF VNS EFFECT ON EEG CONNECTIVITY WITH GRANGER CAUSALITY AND GRAPH THEORY
Tsuyoshi Uchida, Koichi Fujiwara, Kyoto University, Japan; Takao Inoue, Yuichi Maruta, Yamaguchi University, Japan; Manabu Kano, Kyoto University, Japan; Michiyasu Suzuki, Yamaguchi University, Japan

WE-P1-3: Recent Advances in High Performance Processing for Multi-dimensional Signals

Location: Room 305-AB
Time: Wednesday, November 14, 16:20 - 18:00

Session Chair: Masahiro Okuda, University of Kitakyushu

WE-P1-3.1: AN IMAGE SEGMENTATION METHOD BASED ON LUMINANCE DISTRIBUTION AND ITS APPLICATION TO IMAGE ENHANCEMENT
Yuma Kinoshita, Hitoshi Kiya, Tokyo Metropolitan University, Japan

WE-P1-3.2: MOCAP SIGNAL INTERPOLATION USING LOW-RANK MATRIX RECOVERY
Ryuji Imamura, Masahiro Okuda, The University of Kitakyushu, Japan

WE-P1-3.3: EFFICIENT COMPUTATIONAL SCHEDULING OF BOX AND GAUSSIAN FIR FILTERING FOR CPU MICROARCHITECTURE
Norishige Fukushima, Yoshihiro Maeda, Yuki Kawasaki, Masahiro Nakamura, Tomoaki Tsumura, Nagoya Institute of Technology, Japan; Kenjiro Sugimoto, Sei-Ichiro Kamata, Waseda University, Japan

WE-P1-3.4: HYPERSPECTRAL PANSHARPENING USING NOISY PANCHROMATIC IMAGE
Saori Takeyama, Shunsuke Ono, Itsuo Kumazawa, Tokyo Institute of Technology, Japan

WE-P1-3.5: SAFETY-LEVEL ESTIMATION OF AERIAL IMAGES BASED ON CONVOLUTIONAL NEURAL NETWORK FOR EMERGENCY LANDING OF UNMANNED AERIAL VEHICLE
Isana Funahashi, Yo Umeki, Nagaoka University of Technology, Japan; Taichi Yoshida, University of Electro-Communications, Japan; Masahiro Iwahashi, Nagaoka University of Technology, Japan

WE-P1-4: Advances in Multimedia Security

Location: Room 306-B
Time: Wednesday, November 14, 16:20 - 18:00

Session Chairs: KokSheik Wong, Monash University and Xiangui Kang, Sun Yat-sen University

WE-P1-4.1: DETECTING TECHNOLOGY OF NETWORK STORAGE COVERT CHANNEL BASED ON OPTICS ALGORITHM
Linkai Huang, Linna Zhou, University of International Relations, China; Yunbiao Guo, Beijing Institue of Electronics Technology and Application, China

WE-P1-4.2: PRIVACY-PRESERVING SVM COMPUTING IN THE ENCRYPTED DOMAIN
Takahiro Maekawa, Ayana Kawamura, Yuma Kinoshita, Hitoshi Kiya, Tokyo Metropolitan University, Japan

WE-P1-4.3: A ROBUST SECRET SHARING QR CODE VIA TEXTURE PATTERN DESIGN
Xin Zhang, Jia Duan, Jiantao Zhou, University of Macau, China

WE-P1-4.4: A GENERALIZED APPROACH FOR CANCELLABLE TEMPLATE AND ITS REALIZATION FOR MINUTIA CYLINDER-CODE
Xingbo Dong, Zhe Jin, KokSheik Wong, Monash University Malaysia, Malaysia

WE-P1-5: Distributed Optimization in Data Science

Location: Room 307-A
Time: Wednesday, November 14, 16:20 - 18:00

Session Chair: Qing Ling, Sun Yat-Sen University

WE-P1-5.1: WECHAT TOXIC ARTICLE DETECTION: A DATA-DRIVEN MACHINE LEARNING APPROACH
Yunpeng Weng, Muhong Wu, Xu Chen, Qiong Wu, Sun Yat-sen University, China; Lingnan He, Guangdong Key Laboratory for Big Data Analysis and Simulation of Public Opinion, China; Liang Chen, Tencent Holdings Limited, China

WE-P1-5.2: MULTIPLE TRANSFER NET BASED REGION ENSEMBLE NETWORK FOR DEEP HAND POSE ESTIMATION
Haoqian Wang, Da Li, Xingzheng Wang, Key Laboratory of Broadband Network & Multimedia, Graduate School at Shenzhen, Tsinghua University, China

WE-P1-5.3: ENERGY EFFICIENT MOBILE EDGE COMPUTING USING JOINT BENDERS DECOMPOSITION AND DISTRIBUTED DINKELBACH ALGORITHM
Ye Yu, Xiangyuan Bu, Kai Yang, Beijing Institute of Technology, United States; Zhu Han, University of Houston, United States

WE-P1-5.4: ENERGY EFFICIENCY COMPETITION FOR VISIBLE LIGHT COMMUNICATION UNDER ILLUMINATION CONSTRAINT
Xiao Tang, Pinyi Ren, Xi'an Jiaotong University, China; Zhu Han, University of Houston, United States

WE-P1-6: Subjective perception and neural processing of speech in complex environments (II)

Location: Room 308-A
Time: Wednesday, November 14, 16:20 - 18:00

Session Chairs: Nengheng Zheng, Shenzhen University and Qinglin Meng, South China University of Technology

WE-P1-6.1: SPEECH ENHANCEMENT ALGORITHM OF BINARY MASK ESTIMATION BASED ON A PRIORI SNR CONSTRAINTS
Jie Wang, Chengcheng Yang, Linhuang Yan, Manlu Huang, Guangzhou University, China; Jinqiu Sang, Chinese Academy of Sciences, China

WE-P1-6.2: EFFECTS OF TEMPORAL MODULATION CODING CHARACTERISTICS IN THE AUDITORY MIDBRAIN ON SPEECH RECOGNITION
Tiaohao Li, Mengna Sun, Yanji Jiang, Liaoning Technical University, China

WE-P1-6.3: A WOLA-BASED REAL-TIME NOISE REDUCTION ALGORITHM TO IMPROVE SPEECH PERCEPTION WITH COCHLEAR IMPLANTS
Kaibao Nie, University of Washington, United States; Tzu-Lin Ong, Xinzhao Liu, Hanqing Wen, Listent America Corp, United States; Feifan Lai, University of Washington, Bothell, United States; Wei Fan, Changjian Xu, Xindong Liu, Zengjun Sun, Shanghai Listent Medical Tech Co., Ltd, China

WE-P1-7: Machine Learning for Signal and Information Processing

Location: Room 308-B
Time: Wednesday, November 14, 16:20 - 18:00

Session Chairs: Yoshikazu Washizawa, The University of Electro-Communications and Toshihisa Tanaka , Tokyo University of Agriculture and Technolgy

WE-P1-7.1: DISCRIMINATIVE SPARSE REPRESENTATION LEARNING USING MULTICLASS HINGE LOSS
Ryota Kamiya, Yoshikazu Washizawa, The University of Electro-Communications, Japan

WE-P1-7.2: BAYESIAN INDEPENDENT COMPONENT ANALYSIS UNDER HIERARCHICAL MODEL ON INDEPENDENT COMPONENTS
Kai Asaba, Shota Saito, Shunsuke Horii, Toshiyasu Matsushima, Waseda University, Japan

WE-P1-7.3: A CONVERGENCE AND ASYMPTOTIC ANALYSIS OF NONLINEAR SEPARATION MODEL
Lu Wang, Tomoaki Ohtsuki, Keio University, Japan

WE-P1-7.4: VARIATIONAL BAYESIAN COMPRESSED SENSING FOR SPARSE AND LOCALLY CONSTANT SIGNALS
Shunsuke Horii, Waseda University, Japan

WE-P1-7.5: DOUBLY SPARSE BAYESIAN KERNEL LOGISTIC REGRESSION
Atsushi Kojima, Toshihisa Tanaka, Tokyo University of Agriculture and Technology, Japan

WE-P1-8: Sound Processing

Location: Room 309
Time: Wednesday, November 14, 16:20 - 18:00

Session Chairs: Woon-Seng Gan, Nanyang Technological University and Kei Hashimoto, Nagoya Institute of Technology

WE-P1-8.1: SEQUENTIAL GENERATION OF SINGING F0 CONTOURS FROM MUSICAL NOTE SEQUENCES BASED ON WAVENET
Yusuke Wada, Ryo Nishikimi, Eita Nakamura, Kyoto University, Japan; Katsutoshi Itoyama, Tokyo Institute of Technology, Japan; Kazuyoshi Yoshii, Kyoto University, Japan

WE-P1-8.2: AUTOMATIC EVALUATION OF SINGING QUALITY WITHOUT A REFERENCE
Chitralekha Gupta, Haizhou Li, Ye Wang, National University of Singapore, Singapore

WE-P1-8.3: PROGRESSIVE NEURAL NETWORK-BASED KNOWLEDGE TRANSFER IN ACOUSTIC MODELS
Takafumi Moriya, Ryo Masumura, NTT Corporation, Japan; Taichi Asami, NTT DOCOMO, INC., Japan; Yusuke Shinohara, Marc Delcroix, Yoshikazu Yamaguchi, Yushi Aono, NTT Corporation, Japan

WE-P1-8.4: RECENT DEVELOPMENT OF THE DNN-BASED SINGING VOICE SYNTHESIS SYSTEM -- SINSY
Yukiya Hono, Shumma Murata, Kazuhiro Nakamura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda, Nagoya Institute of Technology, Japan

WE-P1-8.5: MUSICAL GENRE AND STYLE RECOGNITION USING DEEP NEURAL NETWORKS AND TRANSFER LEARNING
Deepanway Ghosal, Maheshkumar H. Kolekar, Indian Institute of Technology Patna, India

TH-A1-1: Replay Attack Anti-Spoofing Measures for ASV Systems

Location: Room 310
Time: Thursday, November 15, 08:00 - 09:40

Session Chairs: Hemant A. Patil, DA-IICT Gandhinagar and Haizhou Li, haizhou.li@nus.edu.sg

TH-A1-1.1: REPLAY SPOOF DETECTION USING POWER FUNCTION BASED FEATURES
Prasad Tapkir, Madhu Kamble, Hemant Patil, Dhirubhai Ambani Institute of Information and Communication Technology, India; Maulik Madhavi, National University of Singapore, Singapore

TH-A1-1.2: EXTENDED CONSTANT-Q CEPSTRAL COEFFICIENTS FOR DETECTION OF SPOOFING ATTACKS
Jichen Yang, Rohan Kumar Das, Haizhou Li, National University of Singapore, Singapore

TH-A1-1.3: INSTANTANEOUS PHASE AND EXCITATION SOURCE FEATURES FOR DETECTION OF REPLAY ATTACKS
Rohan Kumar Das, Haizhou Li, National University of Singapore, Singapore

TH-A1-1.4: USE OF CLAIMED SPEAKER MODELS FOR REPLAY DETECTION
Gajan Suthokumar, Kaavya Sriskandaraja, Vidhyasaharan Sethu, Chamith Wijenayake, Eliathamby Ambikairajah, The University of New South Wales, Australia; Haizhou Li, The National University of Singapore, Singapore

TH-A1-1.5: A SURVEY ON REPLAY ATTACK DETECTION FOR AUTOMATIC SPEAKER VERIFICATION (ASV) SYSTEM
Hemant Patil, Madhu Kamble, Dhirubhai Ambani Institute of Information and Communication Technology, India

TH-A1-2: Image/Video Synthesis and Rendering

Location: Room 303-AB
Time: Thursday, November 15, 08:00 - 09:40

Session Chairs: Wen-Nung Lie, National Chung Cheng University and Yao Zhao, Beijing Jiaotong University

TH-A1-2.1: JOINT BACK PROJECTION AND RESIDUAL NETWORKS FOR EFFICIENT IMAGE SUPER-RESOLUTION
Zhi-Song Liu, Wan-Chi Siu, Yui-Lam Chan, Hong Kong Polytechnic University, China

TH-A1-2.2: OPTICAL FLOW-GUIDED MULTI-SCALE DENSE NETWORK FOR FRAME INTERPOLATION
Ting Zhang, Huihui Bai, Feng Li, Yao Zhao, Beijing Jiaotong University, China

TH-A1-2.3: HIGH DYNAMIC RANGE IMAGE GENERATION BASED ON CONVOLUTIONAL WEIGHT OPTIMIZATION ROBUST TO MIXED NOISE REMOVAL
Ryo Matsuoka, Kagawa University, Japan; Shunsuke Ono, Tokyo Institute of Technology, Japan; Masahiro Okuda, The University of Kitakyushu, Japan

TH-A1-2.4: HIGHER-DIMENSION TENSOR COMPLETION VIA LOW-RANK TENSOR RING DECOMPOSITION
Longhao Yuan, Jianting Cao, Xuyang Zhao, Saitama Institute of Technology, Japan; Qiang Wu, Shandong University, China; Qibin Zhao, RIKEN Center for Advanced Intelligence Project (AIP), Japan

TH-A1-2.5: FOREGROUND DEPTH ESTIMATION FOR SEMI-AUTOMATIC 2D-TO-3D VIDEO CONVERSION
Wen-Nung Lie, Yi-Kai Chen, National Chung Cheng University, Taiwan; Jui-Chiu Chiang, Associate Proffessor/National Chung Cheng University, Taiwan

TH-A1-3: Intelligent & Highly Efficient Image & Video Processing Systems

Location: Room 305-AB
Time: Thursday, November 15, 08:00 - 09:40

Session Chair: Kosin Chamnongthai, KMUTT

TH-A1-3.1: IMAGE FUSION FOR SINGLE-SHOT HIGH DYNAMIC RANGE IMAGING WITH SPATIALLY VARYING EXPOSURES
Chihiro Go, Yuma Kinoshita, Sayaka Shiota, Hitoshi Kiya, Tokyo Metropolitan University, Japan

TH-A1-3.2: DEVELOPMENT OF REAL-TIME FHD LOSS-LESS VIDEO COMMUNICATION OVER AN 8×8 MIMO-OFDM SYSTEM
Yoshikazu Miyanaga, Hokkaido University, Japan; Junji Yamano, Masaki Miura, Tohru Gotoh, Raytron inc, Japan; Takashi Imagawa, Ritsumeikan University, Japan; Hiroshi Tsutsui, Hokkaido University, Japan

TH-A1-3.3: DIGITAL HALFTONE DATABASE (DHD): A COMPREHENSIVE ANALYSIS ON HALFTONE TYPES
Jing Ming Guo, Sankarasrinivasan Seshathiri, National Taiwan University of Science and Technology, Taiwan

TH-A1-3.4: SALIENCY DETECTION VIA BACKGROUND SEEDS BY OBJECT PROPOSALS
Muwei Jian, Shandong University of Finance and Economics, China; Runxia Zhao, Junyu Dong, Ocean University of China, China; Kin-Man Lam, The Hong Kong Polytechnic University, China

TH-A1-4: Recent Advances in Data Hiding and Encryption Technology

Location: Room 306-B
Time: Thursday, November 15, 08:00 - 09:40

Session Chairs: Simying Ong, University of Malaya and KokSheik Wong, Monash University

TH-A1-4.1: A BLOCK-PERMUTATION-BASED IMAGE ENCRYPTION ALLOWING HIERARCHICAL DECRYPTION
Yusuke Izawa, Shoko Imaizumi, Chiba University, Japan; Hitoshi Kiya, Tokyo Metropolitan University, Japan

TH-A1-4.2: A RAPID WATERMARKING STRATEGY FOR MULTI-TONE IMAGES
Jing Ming Guo, Sankarasrinivasan Seshathiri, National Taiwan University of Science and Technology, Taiwan

TH-A1-4.3: ENCRYPTION AND DATA INSERTION TECHNIQUE USING REGION DIVISION AND HISTOGRAM MANIPULATION
Ryoma Ito, Shinshu University, Japan; KokSheik Wong, Monash University Malaysia, Malaysia; Simying Ong, University of Malaya, Malaysia; Kiyoshi Tanaka, Shinshu University, Japan

TH-A1-4.4: A NOVEL COVERLESS INFORMATION HIDING TECHNIQUE USING PATTERN IMAGE SYNTHESIS
Weng Ken Lee, Taylor's University, Malaysia; Simying Ong, KokSheik Wong, University of Malaya, Malaysia; Kiyoshi Tanaka, Shinshu University, Japan

TH-A1-4.5: DATA HIDING IN MP4 VIDEO CONTAINER BASED ON SUBTITLE TRACK
ChuanSheng Chan, KokSheik Wong, Monash University Malaysia, Malaysia; Imdad Maungmuang, University of Malaya, Malaysia

TH-A1-5: Graph Signal Processing: Theory and Applications

Location: Room 307-A
Time: Thursday, November 15, 08:00 - 09:40

Session Chairs: Yuichi Tanaka, TUAT and Gene Cheung, NII

TH-A1-5.1: COLORIZATION ALGORITHM BASED ON IMAGE SEGMENTATION AND GRAPH SIGNAL PROCESSING
Mamoru Sugawara, Tokyo University of Science, Japan; Kazunori Uruma, Kogakuin University, Japan; Seiichiro Hangai, Tokyo University of Science, Japan

TH-A1-5.2: ALTERNATING BINARY CLASSIFIER AND GRAPH LEARNING FROM PARTIAL LABELS
Cheng Yang, Zhejiang University of Technology, China; Gene Cheung, National Institute of Informatics, Japan; Vladimir Stankovic, University of Strathclyde, United Kingdom

TH-A1-5.3: CASCADE AND LIFTING STRUCTURES IN THE SPECTRAL DOMAIN FOR BIPARTITE GRAPH FILTER BANKS
David Tay, Deakin University, Australia; Antonio Ortega, Aamir Anis, University of Southern California, United States

TH-A1-5.4: AUDIO SOURCE SEPARATION BASED ON NONNEGATIVE MATRIX FACTORIZATION WITH GRAPH HARMONIC STRUCTURE
Tomohiro Ichita, Seisuke Kyochi, The University of Kitakyushu, Japan; Keisuke Imoto, Ritsumeikan University, Japan

TH-A1-5.5: LOW-RANK SPARSE DECOMPOSITION OF GRAPH ADJACENCY MATRICES FOR EXTRACTING CLEAN CLUSTERS
Taiju Kanada, Masaki Onuki, Yuichi Tanaka, Tokyo University of Agriculture and Technology, Japan

TH-A1-6: Security and Privacy in Information Fusion and Real time Decision Making

Location: Room 308-A
Time: Thursday, November 15, 08:00 - 09:40

Session Chair: Yih-Fang Huang, University of Notre Dame

TH-A1-6.1: DECISION FUSION WITH UNBALANCED PRIORS UNDER SYNCHRONIZED BYZANTINE ATTACKS: A MESSAGE-PASSING APPROACH
Andrea Abrardo, Associate Professor, Italy; Mauro Barni, Full Professor, Italy; Kassem Kallas, Benedetta Tondi, University of Siena, Italy

TH-A1-6.2: ON THE ROLE OF INFORMATION SHARING IN THE SECURITY OF INTERCONNECTED SYSTEMS
Rajasekhar Anguluri, Vaibhav Katewa, Fabio Pasqualetti, University of California, Riverside, United States

TH-A1-6.3: ON SYBIL-PROOF OPTIMAL AUCTION DESIGN FOR CROWDSENSING
Swastik Brahma, Eunice Michael, Tennessee State University, United States

TH-A1-6.4: OPTIMAL DISTRIBUTION MAPPING FOR INFERENCE PRIVACY
Ruochi Zhang, Parv Venkitasubramaniam, Lehigh University, United States

TH-A1-7: Signal Processing for Advancing Cyber-Physical Systems

Location: Room 308-B
Time: Thursday, November 15, 08:00 - 09:40

Session Chairs: Yuhong Liu, Santa Clara University and Behnam Dezfouli, Santa Clara University

TH-A1-7.1: HIGH PERFORMANCE CLUSTER MONITORING SYSTEM
Xunfei Jiang, Tuguldur Baigalmaa, Lam Nguyen, Daiki Akiyoshi, Eli Ramthun, Niraj Parajuli, Charles Peck, Earlham College, United States

TH-A1-7.2: A ROOT-BASED DEFENSE MECHANISM AGAINST RPL BLACKHOLE ATTACKS IN INTERNET OF THINGS NETWORKS
Jun Jiang, Yuhong Liu, Behnam Dezfouli, Santa Clara University, United States

TH-A1-7.3: ANALYZING THE RESOURCE UTILIZATION OF AES ENCRYPTION ON IOT DEVICES
Pedro Sanchez Munoz, Nam Tran, Brandon Craig, Behnam Dezfouli, Yuhong Liu, Santa Clara University, United States

TH-A1-7.4: IMAGE RETRIEVAL USING CNN AND LOW-LEVEL FEATURE FUSION FOR CRIME SCENE INVESTIGATION IMAGE DATABASE
Ying Liu, Yanan Peng, Dan Hu, Daxiang Li, Keng-Pang Lim, Xi’an University of Posts and Telecommunications, China; Nam Ling, Santa Clara University, United States

TH-A1-7.5: ON THE PDF ESTIMATION FOR INFORMATION THEORETIC LEARNING FOR NEURAL NETWORKS
Tokunbo Ogunfunmi, Manas Deb, Santa Clara University, United States

TH-A1-8: Speech Enhancement

Location: Room 309
Time: Thursday, November 15, 08:00 - 09:40

Session Chairs: Tatsuya Kawahara, Kyoto University and Changchun Bao, Beijing University of Technology

TH-A1-8.1: SPEECH ENHANCEMENT WITH PHASE CORRECTION BASED ON MODIFIED DNN ARCHITECTURE
Rui Cheng, Changchun Bao, Yang Xiang, Beijing University of Technology, China

TH-A1-8.2: A NOVEL TRAINING STRATEGY USING DYNAMIC DATA GENERATION FOR DEEP NEURAL NETWORK BASED SPEECH ENHANCEMENT
Mao-Kui He, Jun Du, Zi-Rui Wang, Lei Sun, University of Science and Technology of China, China

TH-A1-8.3: BAYESIAN MULTICHANNEL SPEECH ENHANCEMENT WITH A DEEP SPEECH PRIOR
Kouhei Sekiguchi, RIKEN Center for Advanced Intelligence Project (AIP), Japan; Yoshiaki Bando, AIST, Japan; Kazuyoshi Yoshii, Tatsuya Kawahara, Kyoto University, Japan

TH-A1-8.4: SELF-PRODUCED SPEECH ENHANCEMENT AND SUPPRESSION METHOD USING AIR- AND BODY-CONDUCTIVE MICROPHONES
Moe Takada, Shogo Seki, Tomoki Toda, Nagoya University, Japan

TH-A1-8.5: TIME-FREQUENCY MASK-BASED SPEECH ENHANCEMENT USING CONVOLUTIONAL GENERATIVE ADVERSARIAL NETWORK
Neil Shah, Hemant Patil, Meet H. H. Soni, DA-IICT, Gandhinagar, India

TH-A1-P: Speech and Sound Processing

Location: Room 306-A
Time: Thursday, November 15, 08:00 - 09:40

Session Chairs: Takahiro Shinozaki, Tokyo Institute of Technology and Tai-Shih Chi , National Chiao Tung University

TH-A1-P.1: COMPOSING MUSIC WITH GRAMMAR ARGUMENTED NEURAL NETWORKS AND NOTE-LEVEL ENCODING
Zheng Sun, Jiaqi Liu, Zewang Zhang, Jingwen Chen, Sun Yat-sen University, China; Zhao Huo, China University of Political Science and Law, China; Ching Hua Lee, Institute of High Performance Computing, Singapore; Xiao Zhang, Sun Yat-sen University, China

TH-A1-P.2: NON-LINEAR HARMONIC GENERATION BASED BLIND BANDWIDTH EXTENSION CONSIDERING ALIASING ARTIFACTS
Haruna Miyamoto, Sayaka Shiota, Hitoshi Kiya, Tokyo Metropolitan University, Japan

TH-A1-P.3: EMOTION-CLUSTER CLASSIFICATION OF INFANT CRIES USING SPARSE REPRESENTATION
Takayuki Kurokawa, Tasuku Miura, Masaru Yamashita, Tomoya Sakai, Shoichi Matsunaga, Nagasaki University, Japan

TH-A1-P.4: ESTIMATION OF GLOTTAL SOURCE WAVEFORMS AND VOCAL TRACT SHAPE FOR SINGING VOICES WITH WIDE FREQUENCY RANGE
Kyoko Takahashi, Masato Akagi, Japan Advanced Institute of Science and Technology, Japan

TH-A1-P.5: A DIGITAL MODELING TECHNIQUE FOR DISTORTION EFFECT BASED ON A MACHINE LEARNING APPROACH
Yuto Matsunaga, Naofumi Aoki, Yoshinori Dobashi, Tsuyoshi Yamamoto, Hokkaido University, Japan

TH-A1-P.6: ANALYSIS OF SPEECH AND SINGING SIGNALS FOR TEMPORAL ALIGNMENT
Karthika Vijayan, Xiaoxue Gao, Haizhou Li, National University of Singapore, Singapore

TH-A1-P.7: BLINKIES: SOUND-TO-LIGHT CONVERSION SENSORS AND THEIR APPLICATION TO SPEECH ENHANCEMENT AND SOUND SOURCE LOCALIZATION
Robin Scheibler, Daiki Horiike, Nobutaka Ono, Tokyo Metropolitan University, Japan

TH-A1-P.8: PROBABILISTIC SEQUENTIAL PATTERNS FOR SINGING TRANSCRIPTION
Eita Nakamura, Ryo Nishikimi, Kyoto University, Japan; Simon Dixon, Queen Mary University of London, United Kingdom; Kazuyoshi Yoshii, Kyoto University, Japan

TH-A1-P.9: SINGING VOICE CONVERSION USING POSTED WAVEFORM DATA ON MUSIC SOCIAL MEDIA
Koki Senda, Yukiya Hono, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda, Nagoya Institute of Technology, Japan

TH-A1-P.10: WEAKLY LABELED LEARNING USING BLSTM-CTC FOR SOUND EVENT DETECTION
Taiki Matsuyoshi, University of Tsukuba, Japan; Tatsuya Komatsu, Reishi Kondo, NEC Corporation, Japan; Takeshi Yamada, Shoji Makino, University of Tsukuba, Japan

TH-A1-P.12: UNSUPERVISED SINGING VOICE SEPARATION USING GAMMATONE AUDITORY FILTERBANK AND CONSTRAINT ROBUST PRINCIPAL COMPONENT ANALYSIS
Feng Li, Masato Akagi, Japan Advanced Institute of Science and Technology, Japan

TH-A1-P.13: EXPLORING REDUNDANCY OF HRTFS FOR FAST TRAINING DNN-BASED HRTF PERSONALIZATION
Tzu-Yu Chen, Po-Wen Hsiao, Tai-Shih Chi, National Chiao Tung University, Taiwan

TH-A1-P.14: REWARD ONLY TRAINING OF ENCODER-DECODER DIGIT RECOGNITION SYSTEMS BASED ON POLICY GRADIENT METHODS
Yilong Peng, Hayato Shibata, Takahiro Shinozaki, Tokyo Institute of Technology, Japan

TH-A1-P.15: FACTORISED HIDDEN LAYER BASED DOMAIN ADAPTATION FOR RECURRENT NEURAL NETWORK LANGUAGE MODELS
Michael Hentschel, Nara Institute of Science and Technology, Japan; Marc Delcroix, Atsunori Ogawa, Tomoharu Iwata, Tomohiro Nakatani, NTT Communication Science Laboratories, Japan

TH-A1-P.16: NOVEL SPECTRAL ROOT CEPSTRAL FEATURES FOR REPLAY SPOOF DETECTION
Prasad Tapkir, Ankur Patil, Neil Shah, Hemant Patil, Dhirubhai Ambani Institute of Information and Communication Technology, India

TH-A1-P.17: SIGNIFICANCE OF TEAGER ENERGY OPERATOR PHASE FOR REPLAY SPOOF DETECTION
Prasad Tapkir, Hemant Patil, Dhirubhai Ambani Institute of Information and Communication Technology, India

TH-A1-P.18: MULTI-LABEL PLAYLIST CLASSIFICATION USING CONVOLUTIONAL NEURAL NETWORK
Guan-Hua Wang, Chia-Hao Chung, National Taiwan University, Taiwan; Yian Chen, KKBOX Inc., Taiwan; Homer Chen, National Taiwan University, Taiwan

TH-A2-1: Recent Trends on Active Control of Sound

Location: Room 310
Time: Thursday, November 15, 11:10 - 12:50

Session Chairs: Yoshinobu Kajikawa, Kansai University and Woon-Seng Gan, NTU

TH-A2-1.1: ACTIVE SPEECH OBSCURATION WITH SPEAKER-DEPENDENT HUMAN SPEECH-LIKE NOISE FOR SPEECH PRIVACY
Yoshitaka Ohshio, Haruka Adachi, Kenta Iwai, Takanobu Nishiura, Yoichi Yamashita, Ritsumeikan University, Japan

TH-A2-1.2: EFFECTIVENESS OF ACTIVE NOISE CONTROL SYSTEM FOR NONSTATIONARY NOISE IN CONSIDERATION OF PSYCHOACOUSTIC PROPERTIES
Rina Hasegawa, Hiroto Yamashita, Yoshinobu Kajikawa, Kansai University, Japan

TH-A2-1.3: DISTANCE CONTROL OF VIRTUAL SOUND SOURCE USING PARAMETRIC AND DYNAMIC LOUDSPEAKERS
Masato Nakayama, Osaka Sangyo University, Japan; Takanobu Nishiura, Ritsumeikan University, Japan

TH-A2-1.4: TRIMMED-MEAN FXLMS ALGORITHM FOR ANC IN IMPULSIVE NOISE
Dah-Chung Chang, Po-Wei Chiang, National Central University, Taiwan

TH-A2-1.5: ACTIVE NOISE CONTROL WITH VIRTUAL SENSING TECHNOLOGY FOR HEADREST
He-Siang Deng, Cheng-Yuan Chang, Sen Maw Kuo, Chung Yuan Christian University, Taiwan

TH-A2-2: Advances in Cognitive Information Processing: Methods for conducting behavioral experiments in realistic environment and their applications

Location: Room 303-AB
Time: Thursday, November 15, 11:10 - 12:50

Session Chairs: Toshihiko Matsuka, Chiba University and Hiroo Sekiya, Chiba University

TH-A2-2.1: GENERATIVE ADVERSARIAL NETWORKS FOR GENERATING RGB-D VIDEOS
Yuki Nakahira, Kazuhiko Kawamoto, Chiba University, Japan

TH-A2-2.2: EFFECT OF TEMPORAL LOBE EPILEPSY ON AUDITORY-MOTOR INTEGRATION FOR VOCAL PITCH REGULATION: EVIDENCE FROM BRAIN FUNCTIONAL NETWORK ANALYSIS
Tianqi Wang, Shenzhen Institute of Advanced Technology, China; Hanjun Liu, The First Affiliated Hospital, Sun Yat-sen University, China; Lan Wang, Shenzhen Institute of Advanced Technology, China; Manwa Lawrence Ng, The University of Hong Kong, China; Hua Li, The First Affiliated Hospital of Shenzhen University, China; Nan Yan, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China

TH-A2-2.3: XOR LEARNING BY SPIKING NEURAL NETWORK WITH INFRARED COMMUNICATIONS
Kazuki Matsumoto, Chiba University, Japan; Hiroyuki Torikai, Hosei University, Japan; Hiroo Sekiya, Chiba University, Japan

TH-A2-2.4: EFFECTS OF OBSERVERS' CHARACTERISTICS ON IMPRESSION FORMATION ON FACE
Kuangzhe Xu, Chiba University / ASCON, Japan; Toshihiko Matsuka, Chiba University, Japan

TH-A2-2.5: HOW DO PEOPLE CONSTRUCT MUTUAL BELIEFS IN TASK-ORIENTED DIALOGUES?
Yoshiko Kawabata, National Institute for Japanese Language and Linguistics, Japan; Toshihiko Matsuka, Chiba University, Japan

TH-A2-3: Advanced Topics on Signal Analysis and Compression for Monitoring Systems

Location: Room 305-AB
Time: Thursday, November 15, 11:10 - 12:50

Session Chairs: Supavadee Aramvith , Chulalongkorn University and Shogo Muramatsu , Niigata University

TH-A2-3.1: RIVER WATER QUALITY ESTIMATION BASED ON CONVOLUTIONAL NEURAL NETWORK
Takahiro Oga, Yo Umeki, Masahiro Iwahashi, Yoko Matsuda, Nagaoka University of Technology, Japan

TH-A2-3.2: SINGLE-IMAGE SUPER-RESOLUTION USING COMPLEX NONSEPARABLE OVERSAMPLED LAPPED TRANSFORMS
Satoshi Nagayama, Shogo Muramatsu, Hiroyoshi Yamada, Niigata University, Japan

TH-A2-3.3: GRAPH LEARNING & FAST TRANSFORM CODING OF 3D RIVER DATA
Weihang Liao, Gene Cheung, National Institute of Informatics, Japan; Shogo Muramatsu, Hiroyasu Yasuda, Kiyoshi Hayasaka, Niigata University, Japan

TH-A2-3.4: REAL-TIME MULTIPLE FACE RECOGNITION USING DEEP LEARNING ON EMBEDDED GPU SYSTEM
Savath Saypadith, Supavadee Aramvith, Chulalongkorn University, Thailand

TH-A2-4: Tensor modeling for signal processing and machine learning problems

Location: Room 306-B
Time: Thursday, November 15, 11:10 - 12:50

Session Chairs: Tatsuya Yokota, Nagoya Institute of Technology and Qibin Zhao, RIKEN

TH-A2-4.1: TENSOR COMPLETION WITH SHIFT-INVARIANT COSINE BASES
Tatsuya Yokota, Hidekata Hontani, Nagoya Institute of Technology, Japan

TH-A2-4.2: SIMULTANEOUS PET IMAGE RECONSTRUCTION AND FEATURE EXTRACTION METHOD USING NON-NEGATIVE, SMOOTH, AND SPARSE MATRIX FACTORIZATION
Kazuya Kawai, Hidekata Hontani, Tatsuya Yokota, Nagoya Institute of Technology, Japan; Muneyuki Sakata, Tokyo Metropolitan Institute of Gerontology, Japan; Yuichi Kimura, Kindai University, Japan

TH-A2-4.3: BLOCK TENSOR TRAIN DECOMPOSITION FOR MISSING VALUE IMPUTATION
Namgil Lee, Kangwon National University, Korea (South)

TH-A2-4.4: AN EFFECTIVE TENSOR COMPLETION METHOD BASED ON MULTI-LINEAR TENSOR RING DECOMPOSITION
Jinshi Yu, Guoxu Zhou, Guangdong University of Technology, China; Qibin Zhao, RIKEN Center for Advanced Intelligence Project (AIP), Japan. Guangdong University of Technology, China; Kan Xie, Guangdong University of Technology, China

TH-A2-4.5: ORTHOGONAL RANDOM PROJECTION BASED TENSOR COMPLETION FOR IMAGE RECOVERY
Yali Feng, Guoxu Zhou, Yuning Qiu, Weijun Sun, Guangdong University of technology, China

TH-A2-5: Recent topics in theory and application of digital filters

Location: Room 307-A
Time: Thursday, November 15, 11:10 - 12:50

Session Chairs: Shunsuke Yamaki, Tohoku University and Kenji Suyama, Tokyo Denki University

TH-A2-5.1: DSP IMPLEMENTATION OF ADAPTIVE NOTCH FILTERS WITH OVERFLOW AVOIDANCE IN FIXED-POINT ARITHMETIC
Satoru Ishibashi, Shunsuke Koshita, Masahide Abe, Masayuki Kawamata, Tohoku University, Japan

TH-A2-5.2: PERFORMANCE EVALUATION OF PHASE-ONLY CORRELATION FUNCTIONS FROM THE VIEWPOINT OF CORRELATION FILTERS
Shunsuke Yamaki, Masahide Abe, Masayuki Kawamata, Makoto Yoshizawa, Tohoku University, Japan

TH-A2-5.3: A DIVERSIFICATION STRATEGY FOR IIR FILTER DESIGN USING PSO
Yuya Takase, Kenji Suyama, Tokyo Denki University, Japan

TH-A2-5.4: DESIGN OF GRADIENT AND VARIABLE STEP-SIZE FOR FAST ADAPTIVE NOTCH FILTER
Yosuke Sugiura, Tetsuya Shimamura, Saitama University, Japan

TH-A2-5.5: A VARIABLE STRUCTURE FOR LINEAR PHASE MAXIMALLY FLAT FIR DIGITAL FILTERS
Takashi Yoshida, Tokyo Metropolitan College of Industrial Technology, Japan

TH-A2-6: Efficient Computing and Estimation in Deep Learning with Applications

Location: Room 308-A
Time: Thursday, November 15, 11:10 - 12:50

Session Chairs: Li-Wei Kang, National Yunlin University of Science and Technology, Wen-Huang Cheng, National Chiao Tung University and Pei-Yun Tsai, National Central University

TH-A2-6.1: ONE STAGE DETECTION NETWORK WITH AN AUXILIARY CLASSIFIER FOR REAL-TIME ROAD MARKS DETECTION
Guan-Ting Lin, National Chiao Tung University, Taiwan; Patrisia Sherryl Santoso, Che-Tsung Lin, Chia-Chi Tsai, Jiun-In Guo, Industrial Technology Research Institute, Taiwan

TH-A2-6.2: USING CNN FOR ELLIPSE ESTIMATION IN AN INFANT LENGTH MEASUREMENT APPLICATION
Maolong Tang, Ming-Ting Sun, University of Washington, United States

TH-A2-6.3: LEARNING PRIORS FOR ADVERSARIAL AUTOENCODERS
Hui-Po Wang, Wei-Jan Ko, Wen-Hsiao Peng, National Chiao Tung University, Taiwan

TH-A2-6.4: DEEP LEARNING FOR DETECTION OF FETAL ECG FROM MULTI-CHANNEL ABDOMINAL LEADS
Fang-Wen Lo, Pei-Yun Tsai, National Central University, Taiwan

TH-A2-6.5: A RECONFIGURABLE PROCESS ENGINE FOR FLEXIBLE CONVOLUTIONAL NEURAL NETWORK ACCELERATION
Xiaobai Chen, Shanlin Xiao, Zhiyi Yu, Sun Yat-sen University, China

TH-A2-7: Large-Scale Stochastic Signal Processing for Wireless Systems

Location: Room 308-B
Time: Thursday, November 15, 11:10 - 12:50

Session Chair: Koji Ishibashi, UEC

TH-A2-7.1: A SIMPLE MESSAGE PASSING DETECTOR BASED ON QR-DECOMPOSITION FOR MIMO SYSTEMS
Akihide David Shigyo, Koji Ishibashi, The University of Electro-Communications, Japan

TH-A2-7.2: ITERATIVE DECODING BASED ON CONCATENATED BELIEF PROPAGATION FOR CRC-AIDED POLAR CODES
Satoshi Tajima, Takumi Takahashi, Shinsuke Ibi, Seiichi Sampei, Osaka University, Japan

TH-A2-7.3: SUPERPOSED 16-QAM SIGNAL DETECTION USING GABP IN A MASSIVE MIMO SYSTEM
Taisei Watabe, Toshihiko Nishimura, Takeo Ohgane, Yasutaka Ogawa, Junichiro Hagiwara, Hokkaido University, Japan

TH-A2-7.4: UPLINK OVERLOADED MU-MIMO OFDM SIGNAL DETECTION METHODS USING CONVEX OPTIMIZATION
Kazunori Hayashi, Osaka City University, Japan; Ayano Nakai, Ryo Hayakawa, Kyoto University, Japan; Sangseok Ha, Osaka City University, Japan

TH-A2-8: Speech/Language Recognition

Location: Room 309
Time: Thursday, November 15, 11:10 - 12:50

Session Chairs: Eliathamby Ambikairajah, University of New South Wales and Masato Akagi, Japan Advanced Institute of Science and Technology

TH-A2-8.1: MAXIMAL INFORMATION COEFFICIENT AND PREDOMINANT CORRELATION-BASED FEATURE SELECTION TOWARD A THREE-LAYER MODEL FOR SPEECH EMOTION RECOGNITION
Xingfeng Li, Masato Akagi, Japan Advanced Institute of Science and Technology, Japan

TH-A2-8.2: RELEVANT PHONETIC-AWARE NEURAL ACOUSTIC MODELS USING NATIVE ENGLISH AND JAPANESE SPEECH FOR JAPANESE-ENGLISH AUTOMATIC SPEECH RECOGNITION
Ryo Masumura, NTT Corporation, Japan; Suguru Kabashima, The University of Tokyo, Japan; Takafumi Moriya, Satoshi Kobashikawa, Yoshikazu Yamaguchi, Yushi Aono, NTT Corporation, Japan

TH-A2-8.3: SECOND ORDER FACTORIZED MODEL ADAPTATION FOR SHORT DURATION LANGUAGE IDENTIFICATION
Sarith Fernando, Vidhyasaharan Sethu, Eliathamby Ambikairajah, University of New South Wales, Australia; Haizhou Li, National University of Singapore, Singapore

TH-A2-8.4: UNSUPERVISED PATTERN DISCOVERY FROM THEMATIC SPEECH ARCHIVES BASED ON MULTILINGUAL BOTTLENECK FEATURES
Man-Ling Sung, Siyuan Feng, Tan Lee, The Chinese University of Hong Kong, China

TH-A2-8.5: F-MEASURE BASED END-TO-END OPTIMIZATION OF NEURAL NETWORK KEYWORD DETECTORS
Tomohiro Tanaka, Takahiro Shinozaki, Tokyo Institute of Technology, Japan

TH-A2-P: Image, Video and Multimedia

Location: Room 306-A
Time: Thursday, November 15, 11:10 - 12:50

Session Chairs: Chung-Nan Lee, National Sun Yat-Sen University and Chen-Kuo Chiang, National Chung Cheng University

TH-A2-P.1: REAL-TIME BACKGROUND SUBTRACTION VIA L1 NORM TENSOR DECOMPOSITION
Taehyeon Kim, Yoonsik Choe, Yonsei University, Korea (South)

TH-A2-P.2: ROBUST IMAGE IDENTIFICATION FOR DOUBLE-COMPRESSED AND RESIZED JPEG IMAGES
Kenta Iida, Hitoshi Kiya, Tokyo Metropolitan University, Japan

TH-A2-P.3: OPTIMIZING THE PERFORMANCE OF HALFTONING-BASED BLOCK TRUNCATION CODING
Zi-Xin Xu, Chengdu University of Information Technology, China; Yuk-Hee Chan, P.K. Daniel Lun, The Hong Kong Polytechnic University, China

TH-A2-P.4: MODEL-BASED ENCODING PARAMETER OPTIMIZATION FOR 3D POINT CLOUD COMPRESSION
Qi Liu, Hui Yuan, Shandong University, China; Junhui Hou, City University of Hong Kong, China; Hao Liu, Shandong University, China; Raouf Hamzaoui, De Montfort University, United Kingdom

TH-A2-P.5: REFERENCE SAMPLES PADDING FOR INTRA-FRAME CODING OF OMNIDIRECTIONAL VIDEO
Ning Li, Shuai Wan, Northwestern Polytechnical University, China; Fuzheng Yang, State Key Laboratory of Integrated Services Networks, Xidian University, China

TH-A2-P.6: FULL COMPLEX HOLOGRAM REPRESENTATION METHOD USING DOE PHASE MASK
Kwan-Jung Oh, Keehoon Hong, ETRI, Korea (South); Seung-Yeol Lee, KNU, Korea (South); Jisun Park, JLab, Korea (South)

TH-A2-P.7: AUXILIARY STRUCTURE FOR CONVOLUTIONAL NEURAL NETWORK TRAINING
Cheng-Yeh Chen, Chen-Kuo Chiang, National Chung Cheng University, Taiwan

TH-A2-P.8: SUPERVISED SALIENCY MAPS FOR FIRST-PERSON VIDEOS BASED ON SPARSE CODING
Yujie Li, The National Institute of Advanced Industrial Science and Technology (AIST), Japan; Atsunori Kanemura, The National Institute of Advanced Industrial Science and Technology (AIST), Advanced Telecommunications Research Institute International (ATR), LeapMind Inc., Japan; Hideki Asoh, The National Institute of Advanced Industrial Science and Technology (AIST), Japan; Taiki Miyanishi, Motoaki Kawanabe, Advanced Telecommunications Research Institute International (ATR), Japan

TH-A2-P.9: FAST MONOCULAR VISION-BASED RAILWAY LOCALIZATION FOR SITUATIONS WITH VARYING SPEEDS
Chu-Tak Li, Wan-Chi Siu, Hong Kong Polytechnic University, China

TH-A2-P.10: ASSESSMENT OF VISION-BASED VEHICLE TRACKING FOR TRAFFIC MONITORING APPLICATIONS
Dale Joshua Del Carmen, Rhandley Cajote, University of the Philippines Diliman, Philippines

TH-A2-P.11: LAPPED CUBOID-BASED PERCEPTUAL ENCRYPTION FOR MOTION JPEG STANDARD
Kosuke Shimizu, Taizo Suzuki, Keisuke Kameyama, University of Tsukuba, Japan

TH-A2-P.12: SOUND RECOVERY USING VIBRATION MODES OF THE OBJECT IN A VIDEO
Yohei Fuse, Yusuke Yasumi, Tetsuya Takiguchi, Kobe University, Japan

TH-A2-P.13: A LUNG DISEASE CLASSIFICATION BASED ON FEATURE FUSION CONVOLUTIONAL NEURAL NETWORK WITH X-RAY IMAGE ENHANCEMENT
Yue Cheng, Jinchao Feng, Kebin Jia, Beijing University of Technology, China

TH-A2-P.14: IMPROVING POWER LINE DETECTION BASED ON PHASE DIFFERENCE IN RADAR IMAGE
Dianqi Li, University of Washington, United States; Haoming Chen, Google, Inc, United States; Darren S. Goshi, Honeywell Corporation, United States; Ming-Ting Sun, University of Washington, United States

TH-A2-P.15: IMPROVED VESSEL SEGMENTATION USING CURVELET TRANSFORM AND LINE OPERATORS
Renoh Johnson Chalakkal, Waleed H Soni, The University of Auckland, New Zealand

TH-A2-P.16: A DEEP LEARNING BASED FRAMEWORK FOR CONVERTING SIGN LANGUAGE TO EMOTIONAL SPEECH
Nan Song, Hongwu Yang, Pengpeng Zhi, Northwest Normal University, China

TH-A2-P.17: GPU-FRIENDLY APPROXIMATE BILATERAL FILTER FOR 3D VOLUME DATA
Koichi Yano, Kenjiro Sugimoto, Sei-ichiro Kamata, Waseda University, Japan

TH-P1-1: Speaker diarization and recognition in adverse acoustic environments

Location: Room 310
Time: Thursday, November 15, 14:00 - 15:40

Session Chairs: Xiao-Lei Zhang, Northwestern Polytechnical University and Wei-Qiang Zhang, Tsinghua University

TH-P1-1.1: AN INVESTIGATION OF SPEAKER CLUSTERING ALGORITHMS IN ADVERSE ACOUSTIC ENVIRONMENTS
Meng-Zhen Li, Xiao-Lei Zhang, Northwestern Polytechnical University, China

TH-P1-1.2: INVESTIGATION OF FRAME ALIGNMENTS FOR GMM-BASED DIGIT-PROMPTED SPEAKER VERIFICATION
Yi Liu, Liang He, Wei-Qiang Zhang, Jia Liu, Tsinghua University, China; Michael T. Johnson, University of Kentucky, United States

TH-P1-1.3: AN ANALYSIS OF SPEAKER DIARIZATION FUSION METHODS FOR THE FIRST DIHARD CHALLENGE
Bing Yin, Jun Du, Lei Sun, University of Science and Technology of China, China; Xueyang Zhang, Shan He, iFlytek Research, China; Zhenhua Ling, University of Science and Technology of China, China; Guoping Hu, iFlytek Research, China; Wu Guo, University of Science and Technology of China, China

TH-P1-1.4: DEEP SPEAKER EMBEDDINGS WITH CONVOLUTIONAL NEURAL NETWORK ON SUPERVECTOR FOR TEXT-INDEPENDENT SPEAKER RECOGNITION
Danwei Cai, Zexin Cai, Ming Li, Duke Kunshan University, China

TH-P1-1.5: INVESTIGATING TEXT-INDEPENDENT SPEAKER VERIFICATION FROM PRACTICALLY REALIZABLE SYSTEM PERSPECTIVE
Rohan Kumar Das, National University of Singapore, Singapore; S. R. Mahadeva Prasanna, Indian Institute of Technology Guwahati, India

TH-P1-2: Recent advantage on light field technologies

Location: Room 303-AB
Time: Thursday, November 15, 14:00 - 15:40

Session Chairs: Yukihiro Bandoh, NTT and Yo-Sung Ho, Gwangju Institute of Science and Technology

TH-P1-2.1: INTEGRAL 3D IMAGE CODING BY USING MULTIVIEW VIDEO COMPRESSION TECHNOLOGIES
Kazuhiro Hara, Miwa Katayama, Masahiro Kawakita, NHK (Japan Broadcasting Corp.), Japan; Toshiaki Fujii, Nagoya University, Japan; Tomoyuki Mishina, NHK (Japan Broadcasting Corp.), Japan

TH-P1-2.2: DEPTH ESTIMATION FROM LIGHT FIELD IMAGES VIA CONVOLUTIONAL RESIDUAL NETWORK
Ji-Hun Mun, Yo-Sung Ho, Gwangju Institute of Science and Technology, Korea (South)

TH-P1-2.3: EFFICIENT DEPTH ESTIMATION FOR LIGHT FIELD IMAGES
Wisarut Chantara, Ji-Hun Mun, Yo-Sung Ho, Gwangju Institute of Science and Technology, Korea (South)

TH-P1-2.4: DERIVING SYNTHETIC FILTER BANK FOR PERFECT RECONSTRUCTION OF LIGHT FIELD FROM ITS FOCAL STACK
Akira Kubota, Asami Ito, Chuo University, Japan; Kazuya Kodama, National Institute of Informatics, Japan

TH-P1-3: Audio/Visual Human Attribute Recognition and Modeling for Future Immersive Applications.

Location: Room 305-AB
Time: Thursday, November 15, 14:00 - 15:40

Session Chairs: Sanghoon Lee, Yonsei University and Engin Erzin, Ko¸c University

TH-P1-3.1: MULTIMODAL SPEECH DRIVEN FACIAL SHAPE ANIMATION USING DEEP NEURAL NETWORKS
Sasan Asadiabadi, Rizwan Sadiq, Engin Erzin, Koc university, Turkey

TH-P1-3.2: NO-REFERENCE VIDEO QUALITY ASSESSMENT BASED ON CONVOLUTIONAL NEURAL NETWORK AND HUMAN TEMPORAL BEHAVIOR
Sewoong Ahn, Sanghoon Lee, Yonsei University, Korea (South)

TH-P1-3.3: A SIMPLE METHOD ON GENERATING SYNTHETIC DATA FOR TRAINING REAL-TIME OBJECT DETECTION NETWORKS
Jungwoo Huh, Kyoungoh Lee, Inwoong Lee, Sanghoon Lee, Yonsei University, Korea (South)

TH-P1-3.4: 3D CNN BASED PARTIAL 3D SHAPE RETRIEVAL FOCUSING ON LOCAL FEATURES
Wataru Iwabuchi, Masaki Aono, Toyohashi University of Technology, Japan

TH-P1-3.5: DEPTH MAP ENHANCEMENT ON RGB-D VIDEO CAPTURED BY KINECT V2
Ke-Yu Lin, Hsueh-Ming Hang, National Chiao Tung University, Taiwan

TH-P1-4: Digital Forensics and Data Hiding

Location: Room 306-B
Time: Thursday, November 15, 14:00 - 15:40

Session Chairs: Keiichi Iwamura, Tokyo University of Science and Minoru Kuribayashi, Okayama University

TH-P1-4.1: IMPROVED SIFT FEATURE-BASED WATERMARKING METHOD FOR IHC VER. 5
Masato Hayashi, Masaki Kawamura, Yamaguchi University, Japan

TH-P1-4.2: DETECTABILITY OF THE IMAGE OPERATION ORDER: UPSAMPLING AND MEAN FILTERING
Jiana Li, Xin Liao, Rongbing Hu, Xuchong Liu, Hunan University, China

TH-P1-4.3: ESTIMATION OF COLLUSION ATTACK IN BIAS-BASED BINARY FINGERPRINTING CODE
Tatsuya Yasui, Minoru Kuribayashi, Nobuo Funabiki, Okayama University, Japan; Isao Echizen, National Institute of Informatics, Japan

TH-P1-4.4: CHATTING APPLICATION MONITORING ON ANDROID SYSTEM AND ITS DETECTION BASED ON THE CORRELATION TEST
Yafei Li, Jiageng Chen, Central China Normal University, China; Anthony TS Ho, University of Surrey, China

TH-P1-4.5: TACKLING ANDROID STEGO APPS IN THE WILD
Wenhao Chen, Li Lin, Iowa State University, United States; Min Wu, University of Maryland, College Parks, United States; Jennifer Newman, Iowa State University, United States

TH-P1-5: Recent advances of anomaly detection and estimation for network systems

Location: Room 307-A
Time: Thursday, November 15, 14:00 - 15:40

Session Chairs: Isao Yamada, Tokyo Institute of Technology and Masao Yamagishi, Tokyo Institute of Technology

TH-P1-5.1: ACCURATE OD TRAFFIC MATRIX ESTIMATION BASED ON RESAMPLING OF OBSERVED FLOW DATA
Simon Kase, iD Corporation, Japan; Masato Tsuru, Kyushu Institute of Technology, Japan; Masato Uchida, Waseda University, Japan

TH-P1-5.2: A DDOS ATTACK DETECTION BY GROUP-SPARSE PLUS LOW-RANK TEMPORALLY-SMOOTH DECOMPOSITION FOR EXTENDED OD FLOW MATRIX
Masao Yamagishi, Masaya Endo, Isao Yamada, Tokyo Institute of Technology, Japan

TH-P1-5.3: DETECTION AND BLOCKING OF ANOMALY DNS TRAFFIC BY ANALYZING ACHIEVED NS RECORD HISTORY
Hikaru Ichise, Hokkaido University /Tokyo Institute of Technology, Japan; Yong Jin, Global Scientific Information and Computing Center, Tokyo Institute of Technology, Japan; Katsuyoshi Iida, Yoshiaki Takai, Information Initiative Center, Hokkaido University, Japan

TH-P1-5.4: HIERARCHICAL TRAFFIC MATRICES: AXIOMATIC FOUNDATIONS TO PRACTICAL TRAFFIC MATRIX SYNTHESIS
Paul Tune, Matthew Roughan, University of Adelaide, Australia; Chris Wiren, Defence Science Technology Group, Australia

TH-P1-6: Deep Learning-based Detection and Recognition for Perception Applications

Location: Room 308-A
Time: Thursday, November 15, 14:00 - 15:40

Session Chairs: Li-Wei Kang, National Yunlin University of Science and Technology, Wen-Huang Cheng, National Chiao Tung University and Li Su, Academia Sinica

TH-P1-6.1: MULTI-VIEW AND MULTI-MODAL ACTION RECOGNITION WITH LEARNED FUSION
Sandy Ardianto, Hsueh-Ming Hang, National Chiao Tung University, Taiwan

TH-P1-6.2: VEHICLE DETECTION AND CLASSIFICATION BASED ON DEEP NEURAL NETWORK FOR INTELLIGENT TRANSPORTATION APPLICATIONS
Chia-Chi Tsai, Ching-Kan Tseng, National Chiao Tung University, Taiwan; Ho-Chia Tang, Institute for Information Industry, Taiwan; Jiun-In Guo, National Chiao Tung University, Taiwan

TH-P1-6.3: SINGLE IMAGE DEHAZING VIA DEEP LEARNING-BASED IMAGE RESTORATION
Chia-Hung Yeh, National Taiwan Normal University, Taiwan; Chih-Hsiang Huang, National Sun Yat-sen University, Taiwan; Li-Wei Kang, National Yunlin University of Science and Technology, Taiwan; Min-Hui Lin, National Sun Yat-sen University, Taiwan

TH-P1-6.4: SMOKING ACTION RECOGNITION BASED ON SPATIAL-TEMPORAL CONVOLUTIONAL NEURAL NETWORKS
Chien-Fang Chiu, Chien-Hao Kuo, Pao-Chi Chang, National Central University, Taiwan

TH-P1-6.5: DEEP LEARNING MODELS FOR MELODY PERCEPTION: AN INVESTIGATION ON SYMBOLIC MUSIC DATA
Wei-Tsung Lu, Li Su, Academia Sinica, Taiwan

TH-P1-7: Audio and Speech Content Analysis

Location: Room 308-B
Time: Thursday, November 15, 14:00 - 15:40

Session Chair: Shigeki Sagayama, Meiji University

TH-P1-7.1: MULTIRESOLUTIONAL HIERARCHICAL BAYESIAN NMF FOR DETAILED AUDIO ANALYSIS OF MUSIC PERFORMANCES
Takeshi Hori, Kazuyuki Nakamura, Shigeki Sagayama, Meiji University, Japan

TH-P1-7.2: SEMI-SUPERVISED NMF IN THE CHROMA DOMAIN APPLIED TO MUSIC HARMONY ESTIMATION
Takuya Takahashi, Takeshi Hori, Christoph M. Wilk, Shigeki Sagayama, Meiji University, Japan

TH-P1-7.3: THE MUSICAL SCHEMAGRAM: TIME-SCALE VISUALIZATION OF REPEATED PATTERNS IN MUSIC
Tsung-Ping Chen, Li Su, Academia Sinica, Taiwan

TH-P1-7.4: MAXIMUM A POSTERIORI ESTIMATION OF SPECTRAL GAIN WITH HARMONIC-STRUCTURE-BASED PHASE RECONSTRUCTION FOR PHASE-AWARE SPEECH ENHANCEMENT
Yukoh Wakabayashi, Nobutaka Ono, Tokyo Metropolitan University, Japan

TH-P1-7.5: AGGLOMERATIVE HIERARCHICAL CLUSTERING OF BASIS VECTOR FOR MONAURAL SOUND SOURCE SEPARATION BASED ON NMF
Kentaro Murai, Taiho Takeuchi, Yosuke Tatekura, Shizuoka University, Japan

TH-P1-8: Sound/Speech Processing

Location: Room 309
Time: Thursday, November 15, 14:00 - 15:40

Session Chairs: Christian Ritz, University of Wollongong and Thomas Fang Zheng, Tsinghua University

TH-P1-8.1: INVESTIGATING CO-PRIME MICROPHONE ARRAYS FOR SPEECH DIRECTION OF ARRIVAL ESTIMATION
Jiahong Zhao, Christian Ritz, University of Wollongong, Australia

TH-P1-8.2: ON THE COMPARATIVE EFFECT OF SNOWFALL, ACCUMULATION, AND DENSITY ON SPEECH INTELLIGIBILITY
Shuto Shibata, Kazuhiro Kondo, Yamagata University, Japan

TH-P1-8.3: ADVERSARIAL AUTOENCODER FOR REDUCING NONLINEAR DISTORTION
Naohiro Tawara, Tetsunori Kobayashi, Waseda University, Japan; Masaru Fujieda, Kazuhiro Katagiri, Takashi Yazu, OKI Electric Industry Co., Ltd., Japan; Tetsuji Ogawa, Waseda University, Japan

TH-P1-8.4: REVISITING SPECTRAL ENVELOPE RECOVERY FROM SPEECH SOUNDS GENERATED BY PERIODIC EXCITATION
Hideki Kawahara, Wakayama University, Japan; Masanori Morise, University of Yamanashi, Japan; Kanru Hua, University of Illinois at Urbana-Champaign, United States

TH-P1-8.5: INDEPENDENT LOW-RANK MATRIX ANALYSIS BASED ON TIME-VARIANT SUB-GAUSSIAN SOURCE MODEL
Shinichi Mogami, Norihiro Takamune, The University of Tokyo, Japan; Daichi Kitamura, National Institute of Technology, Kagawa College, Japan; Hiroshi Saruwatari, The University of Tokyo, Japan; Yu Takahashi, Kazunobu Kondo, Hiroaki Nakajima, Yamaha Corporation, Japan; Nobutaka Ono, Tokyo Metropolitan University, Japan