APSIPA 2020

Session Index


Tuesday, December 8, 12:30 - 14:00
Tuesday, December 8, 15:30 - 17:00
Tuesday, December 8, 17:15 - 19:15
Wednesday, December 9, 12:30 - 14:00
Wednesday, December 9, 15:30 - 17:00
Wednesday, December 9, 17:15 - 19:15
Thursday, December 10, 12:30 - 14:00
Thursday, December 10, 15:30 - 17:15
Thursday, December 10, 17:30 - 19:30

Tuesday, December 8, 12:30 - 14:00 ∘ Room B
B-1-1 - Electrical Signals in Human

B-1-1.1: CLASSIFICATION OF SEIZURE EEGS BASED ON SHORT-TIME FOURIER TRANSFORM AND HIDDEN MARKOV MODEL

Du, Yuwei, Harbin Institute of Technology, China Jin, Jing, Harbin Institute of Technology, China Liu, Yan, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Science, China Wang, Qiang, Harbin Institute of Technology, China

B-1-1.2: A MULTI-SUBJECT TEMPORAL-SPATIAL HYPER-ALIGNMENT METHOD FOR EEG-BASED NEURAL ENTRAINMENT TO SPEECH

Zhou, Di, Japan advanced institute of science and technology, Japan Zhang, Gaoyan, Tianjin University, China Dang, Jianwu, Japan Advanced Institute of Science and Technology, Japan Wu, Shuang, Tianjin University, China Zhang, Zhuo, Tianjin University, China

B-1-1.3: DECODING AUDITORY FREQUENCIES AND DIRECTIONS BASED ON BRAIN FUNCTIONAL FEATURES

Wang, Mingxi, Tianjin University, China Zhang, Gaoyan, Tianjin University, China

B-1-1.4: A TEMPORAL ENVELOPE-BASED SPEECH RECONSTRUCTION APPROACH WITH EEG SIGNALS DURING SPEECH IMAGERY

Wu, Hongde, Southern University of Science and Technology, China Chen, Fei, Southern University of Science and Technology, China

B-1-1.5: FROM INTENDED TO SUBJECTIVE: A CONDITIONAL TENSOR FUSION NETWORK FOR RECOGNIZING SELF-REPORTED EMOTION USING PHYSIOLOGY

Yang, Hao-Chun, National Tsing Hua University, Taiwan Lee, Chi-Chun, National Tsing Hua University, Taiwan

B-1-1.6: GEOMETRIC FEATURES BASED MUSCLE FATIGUE ANALYSIS USING LOW FREQUENCY BAND IN SURFACE ELECTROMYOGRAPHIC SIGNALS

Krishnamani, Divya Bharathi, Indian Institute of Technology Madras, India P.A., Karthick, National Institute of Technology Tiruchirappalli, India Swaminathan, Ramakrishnan, Indian Institute of Technology Madras, India

Tuesday, December 8, 12:30 - 14:00 ∘ Room C
C-1-1 - Wireless Communications and Networking

C-1-1.2: CONSTRUCTION OF CYCLICALLY PERMUTABLE CODES FROM PRIME LENGTH CYCLIC CODES

Cho, Keng-Pei, National Chung Hsing University, Taiwan Lin, Chun-Long, National Chung Hsing University, Taiwan Chen, Houshou, National Chung Hsing University, Taiwan Yang, Ting-Ya, National Chung Hsing University, Taiwan

C-1-1.3: LOW-COMPLEXITY ROBUST BEAMFORMING WITH BLOCKAGE PREDICTION FOR MILLIMETER-WAVE COMMUNICATIONS

Okabe, Ryo, The University of Electro-Communications, Japan Iimori, Hiroki, Jacobs University Bremen, Germany Ishibashi, Koji, The University of Electro-Communications, Japan

C-1-1.4: AUTONOMOUS DECENTRALIZED TRANSMISSION TIMING CONTROL IN WIRELESS SENSOR NETWORK

Kaburaki, Aoto, The University of Electro-Communications, Japan Adachi, Koichi, The University of Electro-Communications, Japan Takyu, Osamu, Shinshu University, Japan Ohta, Mai, Fukuoka Univesity, Japan Fujii, Takeo, The University of Electro-Communications, Japan

C-1-1.5: PACKET AGGREGATION BASED ON ENCRYPTION-THEN-COMPRESSION FOR HIGHLY EFFICIENT MULTI-HOP TRANSMISSION

Yatsu, Ryota, The University of Electro-Communications, Japan Hara, Takanori, The University of Electro-Communications, Japan Ishibashi, Koji, The University of Electro-Communications, Japan Tsuchiya, Sota, Tokyo Gas Co., Ltd., Japan Endo, Hideki, Tokyo Gas Co., Ltd., Japan

C-1-1.6: 24 GHZ FLEXIBLE LCP ANTENNA ARRAY FOR RADAR-BASED NONCONTACT VITAL SIGN MONITORING

Kathuria, Nitin, Auckland University of Technology, New Zealand Seet, Boon-Chong, Auckland University of Technology, New Zealand

Tuesday, December 8, 12:30 - 14:00 ∘ Room D
D-1-1 - Image/Video Recognition

D-1-1.1: CLOUD RECOGNITION BASED ON LIGHTWEIGHT NEURAL NETWORK

Zhang, Liang, Beijing University of Technology, China Jia, Kebin, Beijing University of Technology, China Liu, Pengyu, Beijing University of Technology, China Fang, Chunyao, Beijing University of Technology, China

D-1-1.2: MICRO-EXPRESSION RECOGNITION BASED ON MULTIPLE AGGREGATION NETWORKS

She, Wenxiang, Anhui University, China Lv, Zhao, Anhui University, China Tao, Jianhua, Institute of Automation, Chinese Academy of Sciences, China Liu, Bin, Institute of Automation, Chinese Academy of Sciences, China Niu, Mingyue, Institute of Automation, Chinese Academy of Sciences, China

D-1-1.3: ATTENTIVELY-COUPLED LONG SHORT-TERM MEMORY FOR AUDIO-VISUAL EMOTION RECOGNITION

Hsu, Jia-Hao, National Cheng Kung University, Taiwan Wu, Chung-Hsien, National Cheng Kung University, Taiwan

D-1-1.4: UNSUPERVISED DOMAIN ADVERSARIAL TRAINING IN ANGULAR SPACE FOR FACIAL EXPRESSION RECOGNITION

Takashima, Akihiko, NTT Corporation, Japan Makishima, Naoki, NTT Corporation, Japan Ihori, Mana, NTT Corporation, Japan Tanaka, Tomohiro, NTT Corporation, Japan Orihashi, Shota, NTT Corporation, Japan Masumura, Ryo, NTT Corporation, Japan

D-1-1.5: 3D SKELETAL MOVEMENT ENHANCED EMOTION RECOGNITION NETWORK

Shi, Jiaqi, Osaka University, Japan Liu, Chaoran, Advanced Telecommunications Research Institute International, Japan Ishi, Carlos Toshinori, Advanced Telecommunications Research Institute International, Japan Ishiguro, Hiroshi, Osaka University, Japan

Tuesday, December 8, 12:30 - 14:00 ∘ Room E
E-1-1 - Active Noise Control

E-1-1.1: STUDY ON FEEDFORWARD ACTIVE NOISE CONTROL SYSTEM WITH OPTICAL LASER MICROPHONE TO DETECT REFERENCE SIGNAL WITH SHORT DELAY

Iwai, Kenta, Ritsumeikan University, Japan Nishiura, Takanobu, Ritsumeikan University, Japan

E-1-1.2: FEEDFORWARD ACTIVE NOISE CONTROL WITH COHERENCE-ADJUSTING FILTER FOR IMPROVING NOISE REDUCTION PERFORMANCE UNDER LOW-COHERENCE CONDITION

Iwai, Kenta, Ritsumeikan University, Japan Nishiura, Takanobu, Ritsumeikan University, Japan

E-1-1.3: EFFECT OF CROSS-CHANNEL CONTROL FILTERS IN MULTI-CHANNEL FEEDBACK ACTIVE NOISE CONTROL

Shi, Chuang, University of Electronic Science and Technology of China, China Jia, Zhuoying, University of Electronic Science and Technology of China, China Xie, Rong, University of Electronic Science and Technology of China, China Li, Huiyong, University of Electronic Science and Technology of China, China

E-1-1.4: SIMULTANEOUS VARIABLE PERTURBATION METHOD FOR THE ACTIVE NOISE CONTROL SYSTEM WITH A WIRELESS ERROR MICROPHONE

Shi, Chuang, University of Electronic Science and Technology of China, China Yuan, Zhongxing, University of Electronic Science and Technology of China, China Xie, Rong, University of Electronic Science and Technology of China, China Li, Huiyong, University of Electronic Science and Technology of China, China

E-1-1.5: ACTIVE NOISE CONTROL OVER MULTIPLE ZONES: ADAPTIVE ALGORITHM IN TIME DOMAIN

Tang, Xiaoli, The Australian National University, Australia Zhang, Jihui, The Australian National University, Australia Abhayapala, Thushara, The Australian National University, Australia

E-1-1.6: IMPLEMENTATION OF FEEDFORWARD ACTIVE NOISE CONTROL TECHNIQUES FOR HEADPHONES

Huang, Chong-Rui, Chung Yuan Christian University, Taiwan Chang, Cheng-Yuan, Chung Yuan Christian University, Taiwan Kuo, Sen M., Chung Yuan Christian University, Taiwan

Tuesday, December 8, 12:30 - 14:00 ∘ Room F
F-1-1 - Emotion, Dialect, and Age Recognition

F-1-1.1: DIALECT-AWARE MODELING FOR END-TO-END JAPANESE DIALECT SPEECH RECOGNITION

Imaizumi, Ryo, Tokyo Metropolitan University, Japan Masumura, Ryo, Nippon Telegraph and Telephone Corporation, Japan Shiota, Sayaka, Tokyo Metropolitan University, Japan Kiya, Hitoshi, Tokyo Metropolitan University, Japan

F-1-1.2: ACOUSTIC AND TEXTUAL DATA AUGMENTATION FOR CODE-SWITCHING SPEECH RECOGNITION IN UNDER-RESOURCED LANGUAGE

Hsieh, I-Ting, National Cheng Kung University, Taiwan Wu, Chung-Hsien, National Cheng Kung University, Taiwan Wang, Chun-Huang, National Cheng Kung University, Taiwan

F-1-1.3: SPEAKER-INVARIANT PSYCHOLOGICAL STRESS DETECTION USING ATTENTION-BASED NETWORK

Shin, Hyeon-Kyeong, Yonsei University, Korea (South) Han, Hyewon, Yonsei University, Korea (South) Byun, Kyunggeun, Yonsei University, Korea (South) Kang, Hong-Goo, Yonsei University, Korea (South)

F-1-1.4: SENSING WITH CONTEXTS: CRYING REASON CLASSIFICATION FOR INFANT CARE CENTER WITH ENVIRONMENTAL FUSION

Chang, Chun-Min, National Tsing Hua University, Taiwan Chen, Huan-Yu, National Tsing Hua University, Taiwan Chen, Hsiang-Chun, National Tsing Hua University, Taiwan Lee, Chi-Chun, National Tsing Hua University, Taiwan

F-1-1.5: SPEAKER AGE ESTIMATION USING AGE-DEPENDENT INSENSITIVE LOSS

Kitagishi, Yuki, NTT, Japan Kamiyama, Hosana, NTT, Japan Ando, Atsushi, NTT, Japan Tawara, Naohiro, NTT, Japan Mori, Takeshi, NTT, Japan Kobashikawa, Satoshi, NTT, Japan

F-1-1.6: DEEP MULTILAYER PERCEPTRONS FOR DIMENSIONAL SPEECH EMOTION RECOGNITION

Atmaja, Bagus Tris, JAIST, Japan Akagi, Masato, Japan Advanced Institute of Science and Technology, Japan

Tuesday, December 8, 15:30 - 17:00 ∘ Room B
B-1-2 - Adaptive and Intelligent Signal Processing

B-1-2.1: LEARNING GRAPHS WITH MULTIPLE TEMPORAL RESOLUTIONS

Yamada, Koki, Tokyo University of Agriculture and Technology, Japan Tanaka, Yuichi, Tokyo University of Agriculture and Technology, Japan

B-1-2.2: A PARALLEL ADAPTIVE FILTERING ALGORITHM BASED ON THE MEAN-SQUARE DEVIATION ANALYSIS FOR LARGE-SCALE DATA

Jung, Sang Mok, Agency for Defense Development, Korea (South)

B-1-2.3: CLASS ATTENTION NETWORK FOR SEMANTIC SEGMENTATION OF REMOTE SENSING IMAGES

Rao, Zhibo, Northwestern Polytechnical University, China He, Mingyi, Northwestern Polytechnical University, China Dai, Yuchao, Northwestern Polytechnical University, China

B-1-2.4: ESTIMATING DRONE MOTOR RELATED ACOUSTIC TRANSFER FUNCTION: A PRELIMINARY INVESTIGATION

Manamperi, Wageesha, Australian National University, Australia Abhayapala, Thushara, Australian National University, Australia Zhang, Jihui, Australian National University, Australia Samarasinghe, Prasanga, Australian National University, Australia

B-1-2.5: AN EVOLUTIONARY GAME THEORETICAL FRAMEWORK FOR DECISION FUSION IN THE PRESENCE OF BYZANTINES

Lin, Yiqing, Tsinghua University, China Hu, Hong, Tsinghua University, China Zhao, H.Vicky, Tsinghua University, China Chen, Yan, University of Science and Technology of China, China

B-1-2.6: A MATCH PURSUIT BASED METHOD ADAPTED TO OVERCOMPLETE DICTIONARY FOR COMPRESSIVE SPECTRAL IMAGING

Zhu, Jianchen, Tongji University, China Zhao, Shengjie, Tongji University, China Zhang, Rongqing, Tongji University, China

Tuesday, December 8, 15:30 - 17:00 ∘ Room C
C-1-2 - Advanced Signal Processing and Data Analysis for Environmental Recognition in Wireless Communication

C-1-2.1: COMPENSATION METHOD OF RECEIVED SIGNAL POWER OBSERVED BY SMARTPHONE FOR CROWDSENSED SPECTRUM DATABASE

Matsushima, Taiki, The University of Electro-Communications, Japan Fujii, Takeo, The University of Electro-Communications, Japan

C-1-2.2: 3D CONVOLUTIONAL NEURAL NETWORK-AIDED INDOOR POSITIONING BASED ON FINGERPRINTS OF BLE RSSI

Tasaki, Kodai, Osaka University, Japan Takahashi, Takumi, Osaka University, Japan Ibi, Shinsuke, Doshisha University, Japan Sampei, Seiichi, Osaka University, Japan

C-1-2.3: AN OVERLOADED IOT SIGNAL DETECTION METHOD USING NON-CONVEX SPARSE REGULARIZERS

Hayashi, Kazunori, Kyoto University, Japan Nakai-Kasai, Ayano, Kyoto University, Japan Hirayama, Atsuya, Osaka City University, Japan Honda, Hiroki, Osaka City University, Japan Sasaki, Tetsuya, Osaka City University, Japan Yasukawa, Hideki, Osaka City University, Japan Hayakawa, Ryo, Osaka University, Japan

C-1-2.4: SPECIFICATION OF LINK QUALITY DEGRADATION IN WLAN BASED ON MCS AND RETRANSMISSION FLAG

Senda, Hirotaka, Shinshu University, Japan Kamio, Akinori, Shinshu University, Japan Takyu, Osamu, Shinshu University, Japan Ohta, Mai, Fukuoka University, Japan Fujii, Takeo, The University of Electro-Communications, Japan

Tuesday, December 8, 15:30 - 17:00 ∘ Room D
D-1-2 - Machine Learning Techniques for Image & Video

D-1-2.1: LOCAL BACKLIGHT DIMMING FOR LIQUID CRYSTAL DISPLAYS VIA CONVOLUTIONAL NEURAL NETWORK

JO, JUNHO, Seoul National University, Korea (South) SOH, JAE WOONG, Seoul National University, Korea (South) PARK, JAE SUNG, Samsung Electronics, Ltd., Korea (South) CHO, NAM IK, Seoul National University, Korea (South)

D-1-2.2: HALLUCINATING SCENES

Hsieh, Ting-I, National Tsing Hua University, Taiwan Chen, Hwann-Tzong, National Tsing Hua University, Taiwan Cheng, Chia-Ming, MediaTek Inc., Taiwan Huang, Yan-Hao, Industrial Technology Research Institute, Taiwan

D-1-2.3: VISUAL SENTIMENT ANALYSIS FOR FEW-SHOT IMAGE CLASSIFICATION BASED ON METRIC LEARNING

Asakawa, Tetsuya, Toyohashi University of Technology, Japan Aono, Masai, Toyohashi University of Technology, Japan

D-1-2.4: LEARNING DENSE CORRESPONDENCES VIA LOCAL AND NON-LOCAL FEATURE FUSION

Chin, Wen-Chi, National Tsing Hua University, Taiwan Jhang, Zih-Jian, Industrial Technology Research Institute, Taiwan Huang, Yan-Hao, Industrial Technology Research Institute, Taiwan Ito, Koichi, Tohoku University, Japan Chen, Hwann-Tzong, National Tsing Hua University, Taiwan

D-1-2.5: BLIND TONE-MAPPED IMAGE QUALITY ASSESSMENT AND ENHANCEMENT VIA DISENTANGLED REPRESENTATION LEARNING

Wang, Lei, University of Electronic Science and Technology of China, China Wu, Qingbo, University of Electronic Science and Technology of China, China Ngan, King Ngi, University of Electronic Science and Technology of China, China Li, Hongliang, University of Electronic Science and Technology of China, China Meng, Fanman, University of Electronic Science and Technology of China, China Xu, Linfeng, University of Electronic Science and Technology of China, China

D-1-2.6: FIXATIONAL FEATURE-BASED GAZE PATTERN RECOGNITION USING LONG SHORT-TERM MEMORY

Yeamkuan, Suparat, King Mongkut’s University of Technology Thonburi, Thailand Chamnongthai, Kosin, King Mongkut’s University of Technology Thonburi, Thailand

Tuesday, December 8, 15:30 - 17:00 ∘ Room E
E-1-2 - Music Information Processing 1, Audio Scene Classification

E-1-2.1: A DEEP MUSIC GENRES CLASSIFICATION MODEL BASED ON CNN WITH SQUEEZE & EXCITATION BLOCK

Xu, Yijie, Donghua University, China Zhou, Wuneng, Donghua University, China

E-1-2.2: DEEP NEURAL NETWORK MODELING OF DISTORTION STOMP BOX USING SPECTRAL FEATURES

Yoshimoto, Kento, Ritsumeikan University, Japan Kuroda, Hiroki, Ritsumeikan University, Japan Kitahara, Daichi, Ritsumeikan University, Japan Hirabayashi, Akira, Ritsumeikan University, Japan

E-1-2.3: BEAT AND DOWNBEAT TRACKING OF SYMBOLIC MUSIC DATA USING DEEP RECURRENT NEURAL NETWORKS

Chuang, Yi-Chin, National Chung Hsing University, Taiwan Su, Li, Academia Sinica, Taiwan

E-1-2.4: SYMMETRY IN THE STRUCTURE OF MUSICAL NODES

Sunil Phatnani, Kirtana, Dhirubhai Ambani Institute of Information and Communication Technology, India Patil, Hemant A., Dhirubhai Ambani Institute of Information and Communication Technology, India

E-1-2.5: TATUM-LEVEL DRUM TRANSCRIPTION BASED ON A CONVOLUTIONAL RECURRENT NEURAL NETWORK WITH LANGUAGE MODEL-BASED REGULARIZED TRAINING

Ishizuka, Ryoto, Graduate School of Informatics, Kyoto University, Japan Nishikimi, Ryo, Graduate School of Informatics, Kyoto University, Japan Nakamura, Eita, Graduate School of Informatics, Kyoto University, Japan Yoshii, Kazuyoshi, Graduate School of Informatics, Kyoto University, Japan

E-1-2.6: DEEP SEMANTIC ENCODER-DECODER NETWORK FOR ACOUSTIC SCENE CLASSIFICATION WITH MULTIPLE DEVICES

Ma, Xinxin, Jiangsu Normal University, China Shao, Yunfei, Tsinghua University, China Ma, Yong, Jiangsu Normal University, China Zhang, Wei-Qiang, Tsinghua University, China

Tuesday, December 8, 15:30 - 17:00 ∘ Room F
F-1-2 - Natural Language and Spoken Dialogue

F-1-2.1: LANGUAGE MODEL ADAPTATION FOR EMOTIONAL SPEECH RECOGNITION USING TWEET DATA

Saeki, Kazuya, Yamagata University, Japan Kato, Masaharu, Yamagata University, Japan Kosaka, Tetsuo, Yamagata University, Japan

F-1-2.2: SIMULTANEOUS FAKE NEWS AND TOPIC CLASSIFICATION VIA AUXILIARY TASK LEARNING

Cheung, Tsun-hin, The Hong Kong Polytechnic Universtity, Hong Kong (SAR of China) Lam, Kin-man, The Hong Kong Polytechnic Universtity, Hong Kong (SAR of China)

F-1-2.3: OPENNLU: OPEN-SOURCE WEB-INTERFACE NLU TOOLKIT FOR DEVELOPMENT OF CONVERSATIONAL AGENT

Ong, Yi Fan, National University of Singapore, Singapore Madhavi, Maulik, National University of Singapore, Singapore Chan, Ken, ST Engineering Land Systems Ltd, Singapore, Singapore

F-1-2.4: SPOKEN MULTIPLE-CHOICE QUESTION ANSWERING USING MULTI-TURN AUDIO-EXTRACTER BERT

Luo, Shang-Bao, National Taiwan University of Science and Technology, Taiwan Kuo, Chia-Chih, National Taiwan University of Science and Technology, Taiwan Chen, Kuan-Yu, National Taiwan University of Science and Technology, Taiwan

F-1-2.5: "YOUR BEHAVIOR MAKES ME THINK IT IS A LIE": RECOGNIZING PERCEIVED DECEPTION USING MULTIMODAL DATA IN DIALOG GAMES

Chou, Huang-Cheng, National Tsing Hua University, Taiwan Lee, Chi-Chun, National Tsing Hua University, Taiwan

F-1-2.6: SPOKEN DIALOG TRAINING SYSTEM FOR CUSTOMER SERVICE IMPROVEMENT

Sano, Yuta, University of Yamanashi, Japan Leow, Chee Siang, University of Yamanashi, Japan Iida, Soichiro, University of Tsukuba, Japan Utsuro, Takehito, University of Tsukuba, Japan Hoshino, Junichi, University of Tsukuba, Japan Kobayashi, Akio, Tsukuba University of Technology, Japan Nishizaki, Hiromitsu, University of Yamanashi, Japan

Tuesday, December 8, 17:15 - 19:15 ∘ Room A
A-1-3 - Signal Processing Systems for Communication and Multimedia

A-1-3.1: AN IMPROVED METHOD FOR INSTANTANEOUS FREQUENCY ESTIMATION USING A FINITE ORDER HILBERT TRANSFORMER

Takao, Keisuke, Tokyo University of Science, Japan Natori, Takahiro, Tokyo University of Science, Japan Miyata, Toma, Salesian Polytechnic, Japan Aikawa, Naoyuki, Tokyo University of Science, Japan

A-1-3.2: A NEW ALGORITHM TO DERIVE HARDWARE EFFICIENT INTEGER DISCRETE COSINE TRANSFORM FOR HEVC

Qin, Boyu, Nanjing University of Aeronautics and Astronautics, China Chen, Jiajia, Nanjing University of Aeronautics and Astronautics, China

A-1-3.3: NON-LINE-OF-SIGHT IMAGING WITH RADIO SIGNALS

He, Ying, University of Electronic Science and Technology of China, China Zhang, Dongheng, University of Electronic Science and Technology of China, China Hu, Yang, University of Science and Technology of China, China Chen, Yan, University of Science and Technology of China, China

A-1-3.4: CONSTRAINED DESIGN OF TWO-DIMENSIONAL FIR FILTERS WITH SPARSE COEFFICIENTS

Itasaka, Tatsuki, The University of Kitakyushu, Japan Matsuoka, Ryo, The University of Kitakyushu, Japan Okuda, Masahiro, Doshisha University, Japan

A-1-3.5: BARK FREQUENCY SPECTRUM IN PARALLEL-FORM REMOTE ACTIVE NOISE CONTROL

Munir, Muhammad Waqas, University of Auckland, New Zealand Abdulla, Waleed, University of Auckland, New Zealand

A-1-3.6: AN EFFICIENT DESCRIPTION WITH HALIDE FOR IIR GAUSSIAN FILTER

Takagi, Hiroyasu, Nagoya Institute of Technology, Japan Fukushima, Norishige, Nagoya Institute of Technology, Japan

A-1-3.7: DOPPLER CENTROID ESTIMATION WITH QUALITY ASSESSMENT FOR REAL-TIME SAR IMAGING

Lee, Yu-Chieh, National Central University, Taiwan Tsai, Pei-Yun, National Central University, Taiwan Lee, Sz-Yuan, National Applied Research Laboratory, Taiwan

A-1-3.8: DRIVER ARRIVAL SENSING FOR SMART CAR USING WIFI FINE TIME MEASUREMENTS

Zeng, Xiaolu, University of Maryland, United States Wang, Beibei, University of Maryland, United States Liu, K. J. Ray, University of Maryland, United States

Tuesday, December 8, 17:15 - 19:15 ∘ Room B
B-1-3 - Signal Processing in Medical/Clinical Sciences

B-1-3.1: DEEP-LEARNING-BASED MR COMPRESSED SENSING USING NON-RANDOMLY UNDER-SAMPLED SIGNAL IN NONLINEAR PHASE ENCODING IMAGING

ITO, Satoshi, Utsunomiya University, Japan OUCHI, Shohei, Utsunomiya University, Japan

B-1-3.2: CONSTRUCTION OF EFFECTIVE HMMS FOR CLASSIFICATION BETWEEN NORMAL AND ABNORMAL RESPIRATION

Yamashita, Masaru, Nagasaki University, Japan

B-1-3.3: COMPARISON OF PSG SIGNALS AND RESPIRATORY MOVEMENT SIGNAL VIA 3D CAMERA IN DETECTING SLEEP RESPIRATORY EVENTS BY LSTM MODELS

Coronel, Carmina, AIT Austrian Institute of Technology GmbH, Austria Wiesmeyr, Christoph, AIT Austrian Institute of Technology GmbH, Austria Garn, Heinrich, AIT Austrian Institute of Technology GmbH, Austria Kohn, Bernhard, AIT Austrian Institute of Technology GmbH, Austria Naghibzadeh-Jalali, Anahid, AIT Austrian Institute of Technology GmbH, Austria Schindler, Alexander, AIT Austrian Institute of Technology GmbH, Austria Wimmer, Markus, Kepler University Hospital, Austria Mandl, Magdalena, Kepler University Hospital, Austria Glos, Martin, Advanced Sleep Research GmbH, Germany Penzel, Thomas, Advanced Sleep Research GmbH, Germany Kloesch, Gerhard, Medical University of Vienna, Austria Stefanic-Kejik, Andrijana, Medical University of Vienna, Austria Boeck, Marion, Medical University of Vienna, Austria Kaniusas, Eugenijus, Technical University of Vienna, Austria Seidel, Stefan, Medical University of Vienna, Austria

B-1-3.4: PERFORMANCE EVALUATION OF BINARY CLASSIFICATION OF TUBERCULOSIS THROUGH UNSHARP MASKING AND DEEP LEARNING TECHNIQUE

Muchtar, Kahlil, Syiah Kuala University, Indonesia Munadi, Khairul, Syiah Kuala University, Indonesia Maulina, Novi, Syiah Kuala University, Indonesia Pradhan, Biswajeet, University of Technology Sydney, Sydney, NSW, Australia, Australia Arnia, Fitri, Syiah Kuala University, Indonesia Yanti, Budi, Syiah Kuala University, Indonesia

B-1-3.5: HYPERPARAMETER TUNING OF THE SHUNT-MURMUR DISCRIMINATION ALGORITHM USING BAYESIAN OPTIMIZATION

Noda, Fumiya, Oita University, Japan Nishijima, Keisuke, Oita University, Japan Furuya, Ken’ichi, Oita University, Japan

B-1-3.6: COMPARISON OF IMAGE FEATURES DESCRIPTIONS FOR DIAGNOSIS OF LEAF DISEASES

Waqas, Muhammad, Nagoya Institute of Technology, Japan Fukushima, Norishige, Nagoya Institute of Technology, Japan

Tuesday, December 8, 17:15 - 19:15 ∘ Room C
C-1-3 - Emerging technologies based on signal processing for wireless sensor networks

C-1-3.1: PROBABILISTIC BINARY OFFLOADING FOR WIRELESS POWERED MOBILE EDGE COMPUTING SYSTEM

Kobayashi, Takuya, The University of Electro-Communications, Japan Adachi, Koichi, The University of Electro-Communications, Japan

C-1-3.2: SCHEDULING ALGORITHM CONSIDERING INTERFERENCE INTERVAL FOR LPWA

Yamazaki, Yudai, The University of Electro-Communications, Japan Fujii, Takeo, The University of Electro-Communications, Japan

C-1-3.3: ESTIMATION OF DESIRED POWER AND UNDESIRED POWER USING CHIRP DEMODULATION AND EVALUATION OF ACCURACY

Kobayashi, Gaku, Shinshu University, Japan Takyu, Osamu, Shinshu University, Japan Adachi, Koichi, The University of Electro-Communications, Japan Ohta, Mai, Fukuoka University, Japan Fujii, Takeo, The University of Electro-Communications, Japan

C-1-3.4: ON PLACEMENT OF END DEVICES IN LPWAN BASED WSN FOR ENVIRONMENTAL MONITORING APPLICATIONS

Kaichi, Ayumi, Mie University, Japan Narieda, Shusuke, Mie University, Japan Fujii, Takeo, The University of Electro-Communications, Japan Umebayashi, Kenta, Tokyo University of Agriculture and Technology, Japan Naruse, Hiroshi, Mie University, Japan

C-1-3.5: SPECTRUM SHARING FOR INTERNET OF THINGS SYSTEM IN PERIODIC TRANSMISSION

Ohta, Mai, Fukuoka University, Japan Amano, Masaki, Fukuoka University, Japan Taromaru, Makoto, Fukuoka University, Japan

Tuesday, December 8, 17:15 - 19:15 ∘ Room D
D-1-3 - Image/Video Coding

D-1-3.1: SUBJECTIVE QUALITY DRIVEN IMAGE ENCODING METHOD USING IMAGE COMPLETION

Orihashi, Shota, NTT Corporation, Japan Kudo, Shinobu, NTT Corporation, Japan Tanida, Ryuichi, NTT Corporation, Japan Kimata, Hideaki, NTT Corporation, Japan

D-1-3.2: ULTRA FAST SCREEN CONTENT CODING VIA RANDOM FOREST

Tsang, Sik-Ho, The Hong Kong Polytechnic University, Hong Kong (SAR of China) Kwong, Ngai-Wing, The Hong Kong Polytechnic University, Hong Kong (SAR of China) Chan, Yui-Lam, The Hong Kong Polytechnic University, Hong Kong (SAR of China)

D-1-3.3: TWO-LAYER LOSSLESS CODING OF HDR IMAGES SPECIALIZED FOR RADIANCE FORMAT

Yang, Kai, University of Tsukuba, Japan Suzuki, Taizo, University of Tsukuba, Japan Yoshida, Taichi, The University of Electro-Communications, Japan

D-1-3.4: SSIM MOTIVATED QUALITY CONTROL FOR VERSATILE VIDEO CODING

Wang, Meng, City University of Hong Kong, Hong Kong (SAR of China) Wang, Shiqi, City University of Hong Kong, Hong Kong (SAR of China) Li, Junru, Peking University, China Zhang, Li, Bytedance Inc., United States Wang, Yue, Bytedance (HK) Limited., Hong Kong (SAR of China) Ma, Siwei, Peking University, China

D-1-3.5: RATE-DISTORTION OPTIMIZATION FOR 360-DEGREE IMAGE CONSIDERING VISUAL ATTENTION

Yang, Cheng-Yu, National Chung Cheng University, Tanzania Chiang, Jui-Chiu, National Chung Cheng University, Tanzania Lie, Wen-Nung, National Chung Cheng University, Tanzania

D-1-3.6: EVALUATION OF THE ENCODING ACCURACY OF THE PQ BASED HDR CONTENT DELIVERY FORMATS

Siddiq, Asif, Riphah International University, Pakistan Khan, Ishtiaq Rasool, University of Jeddah, Saudi Arabia Ahmed, Jameel, Riphah International University Islamabad, Pakistan

D-1-3.7: CHECKERBOARD-ARTIFACT-FREE IMAGE-ENHANCEMENT NETWORK CONSIDERING LOCAL AND GLOBAL FEATURES

Kinoshita, Yuma, Tokyo Metropolitan University, Japan Kiya, Hitoshi, Tokyo Metropolitan University, Japan

Tuesday, December 8, 17:15 - 19:15 ∘ Room E
E-1-3 - Array Processing of Microphones and Loud Speakers

E-1-3.1: EVALUATION OF A MULTI-WAY PARAMETRIC ARRAY LOUDSPEAKER BASED ON MULTIPLEXED DOUBLE SIDEBAND MODULATION

GENG, Yuting, Ritsumeikan University, Japan NAKAYAMA, Masato, Osaka Sangyo University, Japan NISHIURA, Takanobu, Ritsumeikan University, Japan

E-1-3.2: MULTI-BEAM DESIGN METHOD FOR A STEERABLE PARAMETRIC ARRAY LOUDSPEAKER

Shi, Chuang, University of Electronic Science and Technology of China, China Bai, Ruyu, University of Electronic Science and Technology of China, China Gou, Jiacheng, University of Electronic Science and Technology of China, China Liang, Jiangnan, University of Electronic Science and Technology of China, China

E-1-3.3: APPLYING VIRTUAL MICROPHONES TO TRIANGULAR MICROPHONE ARRAY IN IN-CAR COMMUNICATION

Segawa, Hanako, University of Tsukuba, Japan Takahashi, Riki, University of Tsukuba, Japan Jinzai, Ryoga, University of Tsukuba, Japan Makino, Shoji, University of Tsukuba, Japan Yamada, Takeshi, University of Tsukuba, Japan

E-1-3.4: SEMI-ADAPTIVE BEAMFORMING FOR CO-PRIME CIRCULAR MICROPHONE ARRAYS

Zhao, Jiahong, University of Wollongong, Australia Ritz, Christian, University of Wollongong, Australia

E-1-3.5: FULL-SPHERE BINAURAL SOUND SOURCE LOCALIZATION USING MULTI-TASK NEURAL NETWORK

Yang, Yichen, Northwestern Polytechnical University, China Xi, Jingwei, Northwestern Polytechnical University, China Zhang, Wen, Northwestern Polytechnical University, China Zhang, Lijun, Northwestern Polytechnical University, China

E-1-3.6: LEARNING BASED DOA ESTIMATION IN ADVERSE ACOUSTIC ENVIRONMENT USING CO-PRIME CIRCULAR MICROPHONE ARRAY

Gohil, Raj, IIT Kanpur, India Raikar, Aditya, TCS Research and Innovation, India Routray, Gyanajyoti, IIT Kanpur, India Hegde, Rajesh, IIT Kanpur, India

E-1-3.7: ENERGY-BASED MULTIPLE SOURCE LOCALIZATION WITH BLINKIES

Horiike, Daiki, Tokyo Metropolitan University, Japan Scheibler, Robin, Tokyo Metropolitan University, Japan Kinoshita, Yuma, Tokyo Metropolitan University, Japan Wakabayashi, Yukoh, Tokyo Metropolitan University, Japan Ono, Nobutaka, Tokyo Metropolitan University, Japan

Tuesday, December 8, 17:15 - 19:15 ∘ Room F
F-1-3 - Speech Enhancement 1

F-1-3.1: SPEECH ENHANCEMENT FOR OPTICAL LASER MICROPHONE WITH DEEP NEURAL NETWORK

CAI, Chengkai, Ritsumeikan University, Japan Iwai, Kenta, Ritsumeikan University, Japan Nishiura, Takanobu, Ritsumeikan University, Japan Yamashita, Yoichi, Ritsumeikan University, Japan

F-1-3.2: BOOSTING OBJECTIVE SCORES OF A SPEECH ENHANCEMENT MODEL BY METRICGAN POST-PROCESSING

Fu, Szu-Wei, Academia Sinica, Taiwan Liao, Chien-Feng, Academia Sinica, Taiwan Hsieh, Tsun-An, Academia Sinica, Taiwan Hung, Kuo-Hsuan, Academia Sinica, Taiwan Wang, Syu-Siang, Academia Sinica, Taiwan Yu, Cheng, Academia Sinica, Taiwan Kuo, Heng-Cheng, Academia Sinica, Taiwan Zezario, Ryandhimas E., Academia Sinica, Taiwan Li, You-Jin, Academia Sinica, Taiwan Chuang, Shang-Yi, Academia Sinica, Taiwan Lu, Yen-Ju, Academia Sinica, Taiwan Lin, Yu-Chen, Academia Sinica, Taiwan Tsao, Yu, Academia Sinica, Taiwan

F-1-3.3: SPEECH ENHANCEMENT FOR DEMODULATED SIGNALS UNDER MULTIPATH FADING COMMUNICATION CHANNELS

Kobayashi, Akio, Tsukuba University of Technology, Japan

F-1-3.4: FREQUENCY GATING: IMPROVED CONVOLUTIONAL NEURAL NETWORKS FOR SPEECH ENHANCEMENT IN THE TIME-FREQUENCY DOMAIN

Oostermeijer, Koen, University of Science and Technology of China, China Wang, Qing, University of Science and Technology of China, China Du, Jun, University of Science and Technology of China, China

F-1-3.5: GAMMA BOLTZMANN MACHINE FOR SIMULTANEOUSLY MODELING LINEAR- AND LOG-AMPLITUDE SPECTRA

Nakashika, Toru, The University of Electro-Communications, Japan Yatabe, Kohei, Waseda University, Japan

F-1-3.6: A DEEP LEARNING-BASED TIME-DOMAIN APPROACH FOR NON-INTRUSIVE SPEECH QUALITY ASSESSMENT

Jia, Xupeng, Tsinghua University, China Li, Dongmei, Tsinghua University, China

F-1-3.7: STOI-NET: A DEEP LEARNING BASED NON-INTRUSIVE SPEECH INTELLIGIBILITY ASSESSMENT MODEL

Zezario, Ryandhimas, National Taiwan University, Taiwan Fu, Szu-Wei, Academia Sinica, Taiwan Fuh, Chiou-Shann, National Taiwan University, Taiwan Tsao, Yu, Academia Sinica, Taiwan Wang, Hsin-Min, Academia Sinica, Taiwan

Wednesday, December 9, 12:30 - 14:00 ∘ Room B
B-2-1 - Multidimensional Biomedical Signal and Image Processing

B-2-1.1: DEEP-LEARNING BASED MOTION-CORRECTED IMAGE RECONSTRUCTION IN 4D MAGNETIC RESONANCE IMAGING OF THE BODY TRUNK

Küstner, Thomas, University Hospital Tübingen, Germany Pan, Jiazhen, University of Stuttgart, Germany Gilliam, Christopher, RMIT University, Australia Qi, Haikun, King's College London, United Kingdom Cruz, Gastao, King's College London, United Kingdom Hammernik, Kerstin, Imperial College London, United Kingdom Yang, Bin, University of Stuttgart, Germany Blu, Thierry, Chinese University of Hong Kong, Hong Kong (SAR of China) Rueckert, Daniel, Imperial College London, United Kingdom Botnar, René, King's College London, United Kingdom Prieto, Claudia, King's College London, United Kingdom Gatidis, Sergios, University Hospital Tübingen, Germany

B-2-1.2: FRI SENSING: 2D LOCALIZATION FROM 1D MOBILE SENSOR DATA

Guo, Ruiming, The Chinese university of Hong Kong, Hong Kong (SAR of China) Blu, Thierry, The Chinese university of Hong Kong, Hong Kong (SAR of China)

B-2-1.3: APPLICATION OF IMAGE PROCESSING AND CIRCULAR STATISTICS TO 3D CELLULAR ALIGNMENT

Jelfs, Beth, RMIT University, Australia Gilliam, Christopher, RMIT University, Australia

Wednesday, December 9, 12:30 - 14:00 ∘ Room C
C-2-1 - Signal and Information Processing Methods

C-2-1.1: SIMULTANEOUS MEASUREMENT OF TIME-INVARIANT LINEAR AND NONLINEAR, AND RANDOM AND EXTRA RESPONSES USING FREQUENCY DOMAIN VARIANT OF VELVET NOISE

Kawahara, Hideki, Wakayama University, Japan Sakakibara, Ken-Ichi, Health Science University of Hokkaido, Japan Mizumachi, Mitsunori, Kyushu Institute of Technology, Japan Morise, Masanori, Meiji University, Japan Banno, Hideki, Meijo University, Japan

C-2-1.2: AGE CLASSIFICATION OF EVACUEES AT TIMES OF DISASTER USING A VIBRATION SENSOR

Yamashita, Toru, Kogakuin University, Japan Asano, Futoshi, Kogakuin University, Japan Nakadai, Kazuhiro, Honda Research Institute Japan, Japan

C-2-1.3: ON THE BEHAVIOUR OF PERMUTATION ENTROPY ON FRACTIONAL BROWNIAN MOTION IN A MULTIVARIATE SETTING

Mohr, Marisa, University of Luebeck, Germany Finke, Nils, University of Luebeck, Germany Moeller, Ralf, University of Luebeck, Germany

C-2-1.4: MODELING DECISION PROCESS IN MULTI-AGENT SYSTEMS: A GRAPHICAL MARKOV GAME BASED APPROACH

Li, Hao, Tsinghua University, China Li, Yuejiang, Tsinghua University, China Zhao, H.Vicky, Tsinghua University, China

C-2-1.5: SAMPLING POLICY DESIGN FOR TRACKING TIME-VARYING GRAPH SIGNALS WITH ADAPTIVE BUDGET ALLOCATION

Xie, Xuan, Fudan University, China Feng, Hui, Fudan University, China Hu, Bo, Fudan University, China

C-2-1.6: DIFFERENTIATED PROSODIC ADAPTION OF CHINESE AND ENGLISH POETRY: AN ACOUSTIC APPROACH TO READING OF CHINESE TANG POETRY AND SHAKESPEAREAN SONNETS

Xu, Yizhong, Nanjing University of Aeronautics and Astronautics, China Cao, Siyi, Nanjing University of Aeronautics and Astronautics, China Ji, Jiafang, Nanjing University of Aeronautics and Astronautics, China Xiao, Qin, Nanjing University of Aeronautics and Astronautics, China Wu, Anqi, Nanjing University of Aeronautics and Astronautics, China Wang, Xiuyuan, Nanjing University of Aeronautics and Astronautics, China

Wednesday, December 9, 12:30 - 14:00 ∘ Room D
D-2-1 - Digital Convergence of 5G, AIoT and Security I

D-2-1.1: DUAL ADAPTIVE MODULATION AND CODING FOR MITIGATING UE-UE INTERFERENCE IN HETEROGENEOUS TDD SLOT CONFIGURATIONS

Pan, Jen-Yi, National Chung Cheng University, Taiwan Chen, Chih-Yang, National Chung Cheng University, Taiwan Lin, Wen-Hsueh, National Chung Cheng University, Taiwan Pao, Wei-Chen, Industrial Technology Research Institute, Taiwan Liang, Jhe-Hao, National Chung Cheng University, Taiwan Wu, Bo-Yen, National Chung Cheng University, Taiwan

D-2-1.2: OPTIMIZATION OF VIRTUAL MACHINE PLACEMENT FOR BALANCING NETWORK AND SERVER LOAD IN EDGE COMPUTING ENVIRONMENTS

Nangu, Shota, Kansai University, Japan Kimura, Tomotaka, Doshisha University, Japan Hirata, Kouji, Kansai University, Japan

D-2-1.3: PREDICTION METHOD OF MALWARE INFECTION SPREADING CONSIDERING NETWORK SCALE

Nagasawa, Yurina, Kansai University, Japan Kishioka, Keita, Kansai University, Japan Kimura, Tomotaka, Doshisha University, Japan Hirata, Kouji, Kansai University, Japan

D-2-1.4: JOINT OPTIMIZATION OF EDGE SERVER AND VIRTUAL MACHINE PLACEMENT IN EDGE COMPUTING ENVIRONMENTS

Takeda, Ayaka, Kansai University, Japan Kimura, Tomotaka, Doshisha University, Japan Hirata, Kouji, Kansai University, Japan

D-2-1.5: REALIZATION OF 5G NETWORK SLICING USING OPEN SOURCE SOFTWARES

Chen, Sheng, National Sun Yat-sen University, Taiwan, Taiwan Lee, Chung-Nan, National Sun Yat-sen University, Taiwan, Taiwan Lee, Ming-Feng, National Sun Yat-sen University, Taiwan, Taiwan

D-2-1.6: CELL OUTAGE DETECTION USING DEEP CONVOLUTIONAL AUTOENCODER IN MOBILE COMMUNICATION NETWORKS

Ping, Yeh-Hong, Yuan Ze University, Taiwan Lin, Po-Chiang, Yuan Ze University, Taiwan

Wednesday, December 9, 12:30 - 14:00 ∘ Room E
E-2-1 - Music Information Processing 2, Voice Conversion

E-2-1.1: PJS: PHONEME-BALANCED JAPANESE SINGING-VOICE CORPUS

Koguchi, Junya, Meiji University, Japan Takamichi, Shinnosuke, The University of Tokyo, Japan Morise, Masanori, Meji University, Japan

E-2-1.2: SPECTRAL FEATURES AND PITCH HISTOGRAM FOR AUTOMATIC SINGING QUALITY EVALUATION WITH CRNN

Huang, Lin, National University of Singapore, Singapore Gupta, Chitralekha, National University of Singapore, Singapore Li, Haizhou, National University of Singapore, Singapore

E-2-1.3: A VARIATIONAL AUTOENCODER FOR JOINT CHORD AND KEY ESTIMATION FROM AUDIO CHROMAGRAMS

Wu, Yiming, Kyoto University, Japan Nakamura, Eita, Kyoto University, Japan Yoshii, Kazuyoshi, Kyoto University, Japan

E-2-1.4: SPECTRUM AND PROSODY CONVERSION FOR CROSS-LINGUAL VOICE CONVERSION WITH CYCLEGAN

Du, Zongyang, National University of Singapore, Singapore Zhou, Kun, National University of Singapore, Singapore Sisman, Berrak, Singapore University of Technology and Design, Singapore Li, Haizhou, National University of Singapore, Singapore

E-2-1.5: VAW-GAN FOR SINGING VOICE CONVERSION WITH NON-PARALLEL TRAINING DATA

Lu, Junchen, National University of Singapore, Singapore Zhou, Kun, National University of Singapore, Singapore Sisman, Berrak, Singapore University of Technology and Design, Singapore Li, Haizhou, National University of Singapore, Singapore

E-2-1.6: CROSS-LINGUAL VOICE CONVERSION USING A CYCLIC VARIATIONAL AUTO-ENCODER AND A WAVENET VOCODER

Nakatani, Hikaru, Nagoya University, Japan Lumban Tobing, Patrick, Nagoya University, Indonesia Takeda, Kazuya, Nagoya University, Japan Toda, Tomoki, Nagoya University, Japan

Wednesday, December 9, 12:30 - 14:00 ∘ Room F
F-2-1 - Speaker Recognition 1, Language Recognition

F-2-1.1: QUASI-NEWTON ADVERSARIAL ATTACKS ON SPEAKER VERIFICATION SYSTEMS

Goto, Keita, Tokyo Institute of Technology, Japan Inoue, Nakamasa, Tokyo Institute of Technology, Japan

F-2-1.2: SIGNIFICANCE OF CMVN FOR REPLAY SPOOF DETECTION

Patil, Ankur T., Dhirubhai Ambani Institute of Information and Communication Technology, India Patil, Hemant A., Dhirubhai Ambani Institute of Information and Communication Technology, India

F-2-1.3: SUBBAND CHANNEL SELECTION USING TEO FOR REPLAY SPOOF DETECTION IN VOICE ASSISTANTS

Kotta, Harsh, Dhirubhai Ambani Institute of Information and Communication Technology, India Patil, Ankur T., Dhirubhai Ambani Institute of Information and Communication Technology, India Acharya, Rajul, Dhirubhai Ambani Institute of Information and Communication Technology, India Patil, Hemant A., Dhirubhai Ambani Institute of Information and Communication Technology, India

F-2-1.4: DESIGN OF VOICE PRIVACY SYSTEM USING LINEAR PREDICTION

Gupta, Priyanka, Dhirubhai Ambani Institute of Information and Communication Technology, India Prajapati, Gauri, Dhirubhai Ambani Institute of Information and Communication Technology, India Singh, Shrishti, Dhirubhai Ambani Institute of Information and Communication Technology, India Kamble, Madhu, Dhirubhai Ambani Institute of Information and Communication Technology, India Patil, Hemant A., Dhirubhai Ambani Institute of Information and Communication Technology, India

F-2-1.5: AP20-OLR CHALLENGE: THREE TASKS AND THEIR BASELINES

Li, Zheng, Xiamen University, China Zhao, Miao, Xiamen University, China Hong, Qingyang, Xiamen University, China Li, Lin, Xiamen University, China Tang, Zhiyuan, Tsinghua University, China Wang, Dong, Tsinghua University, China Song, Liming, Speechocean, China Yang, Cheng, Speechocean, China

F-2-1.6: ADVERSARIAL POST-PROCESSING OF VOICE CONVERSION AGAINST SPOOFING DETECTION

Ding, Yi-Yang, University of Science and Technology of China, China Zhang, Jing-Xuan, University of Science and Technology of China, China Liu, Li-Juan, iFLYTEK Co., Ltd., China Jiang, Yuan, iFLYTEK Co., Ltd., China Hu, Yu, iFLYTEK Co., Ltd., China Ling, Zhen-Hua, University of Science and Technology of China, China

Wednesday, December 9, 15:30 - 17:00 ∘ Room B
B-2-2 - Data hiding in multimedia content and unconventional domain

B-2-2.1: DEEPWATERMARK: EMBEDDING WATERMARK INTO DNN MODEL

Kuribayashi, Minoru, Okayama University, Japan Tanaka, Takuro, Okayama University, Japan Funabiki, Nobuo, Okayama University, Japan

B-2-2.2: FLEXIBLE DATA HIDING AND EXTRACTION IN ETC IMAGES

HIRASAWA, Ryoichi, Chiba University, Japan IMAIZUMI, Shoko, Chiba University, Japan KIYA, Hitoshi, Tokyo Metropolitan University, Japan

B-2-2.3: DENSELY CONNECTED CONVOLUTIONAL NETWORK FOR AUDIO SPOOFING DETECTION

Wang, Zheng, Sun Yat-sen University, China Cui, Sanshuai, Sun Yat-sen University, China kang, Xiangui, Sun Yat-sen University, China Sun, Wei, Sun Yat-sen University, China Li, Zhonghua, Sun Yat-sen University, China

B-2-2.4: DATA EMBEDDING METHOD USING PHOTO EFFECTS WITH RESISTANCE TO COMPRESSION

Yeong, William K.W., University of Malaya, Malaysia Ong, Simying, University of Malaya, Malaysia Wong, KokSheik, Monash University Malaysia, Malaysia

Wednesday, December 9, 15:30 - 17:00 ∘ Room C
C-2-2 - Advanced Topics in Signal Processing & Machine Learning - Acoustic & Biomedical Applications
Wednesday, December 9, 15:30 - 17:00 ∘ Room D
D-2-2 - Recent Advances in Deep Learning with Multimedia Applications

D-2-2.1: FUSION TECHNOLOGY OF RADAR AND RGB CAMERA SENSORS FOR OBJECT DETECTION AND TRACKING AND ITS EMBEDDED SYSTEM IMPLEMENTATION

Lu, Jian Xian, National Chiao Tung University, Taiwan Lin, Jia Cheng, National Chiao Tung University, Taiwan Malligere Shivanna, Vinay, National Chiao Tung University, Taiwan Chen, Po-Yu, MediaTek Inc., Taiwan Guo, Jiun-In, National Chiao Tung University, Taiwan

D-2-2.2: CHROMA COMPONENT GENERATION OF GRAY IMAGES USING MULTI-SCALE CONVOLUTIONAL NEURAL NETWORK

Kuo, Tien-Ying, National Taipei University of Technology, Taiwan Wei, Yu-Jen, National Taipei University of Technology, Taiwan You, Bin-Yen, National Taipei University of Technology, Taiwan

D-2-2.3: SCENE TEXT-LINE EXTRACTION WITH FULLY CONVOLUTIONAL NETWORK AND REFINED PROPOSALS

Zeng, Guan-Xin, National Central University, Taiwan Hou, Yu-Hong, National Central University, Taiwan Su, Po-Chyi, National Central University, Taiwan Kang, Li-Wei, National Taiwan Normal University, Taiwan

Wednesday, December 9, 15:30 - 17:00 ∘ Room E
E-2-2 - Speech Analysis

E-2-2.1: HARMONIC PRESERVING NEURAL NETWORKS FOR EFFICIENT AND ROBUST MULTIPITCH ESTIMATION

Yu, Chin-Yun, Academia Sinica, Taiwan Lin, Jing-Hua, Academia Sinica, Taiwan Su, Li, Academia Sinica, Taiwan

E-2-2.2: TV-CAR SPEECH ANALYSIS BASED ON THE L2-NORM REGULARIZATION IN THE TIME-DOMAIN AND FREQUENCY DOMAIN

FUNAKI, KEIICHI, University of the Ryukyus, Japan

E-2-2.3: PHONEME EMBEDDINGS ON PREDICTING FUNDAMENTAL FREQUENCY PATTERN FOR ELECTROLARYNGEAL SPEECH

Eshghi, Mohammad, Nagoya University, Japan Kobayashi, Kazuhiro, Nagoya University, Japan Tanaka, Kou, Nippon Telegraph and Telephone Corporation, Japan Kameoka, Hirokazu, Nippon Telegraph and Telephone Corporation, Japan Toda, Tomoki, Nagoya University, Japan

E-2-2.4: A DATA AUGMENTATION TECHNIQUE FOR AUTOMATIC DETECTION OF CHEWING SIDE AND SWALLOWING

Nakamura, Akihiro, Shizuoka University, Japan Saito, Takato, NTT DOCOMO, INC., Japan Ikeda, Daizo, NTT DOCOMO, INC., Japan Ohta, Ken, NTT DOCOMO, INC., Japan Mineno, Hiroshi, Shizuoka University, Japan Nishimura, Masafumi, Shizuoka University, Japan

E-2-2.5: ACOUSTIC ANALYSIS OF NASALIZATION IN MANDARIN PRENASAL VOWELS PRODUCED BY WENZHOU AND RUGAO SPEAKERS

Zhang, Xinya, Nanjing University of Science and Technology, China Chen, Yanyang, Nanjing University of Science and Technology, China Wang, Jiazheng, Nanjing University of Science and Technology, China Chen, Ying, Nanjing University of Science and Technology, China

E-2-2.6: TEMPORAL AND FORMANT TRAJECTORY ANALYSIS OF ENGLISH TENSE-LAX VOWELS PRODUCED BY NATIVE CHINESE SPEAKERS

Gong, Jian, Jiangsu University of Science and Technology, China Xue, Di, SIP Xingwan School, China William, Bellamy, Jiangsu University of Science and Technology, China Wang, Feng, Jiangsu University of Science and Technology, China Ji, Xiaoli, Jiangsu University of Science and Technology, China

Wednesday, December 9, 15:30 - 17:00 ∘ Room F
F-2-2 - Speaker Recognition 2, Sound Classification

F-2-2.1: CONTEXT-ADAPTIVE GAUSSIAN ATTENTION FOR TEXT-INDEPENDENT SPEAKER VERIFICATION

Peng, Junyi, Peking University Shenzhen Graduate School, China Gu, Rongzhi, Peking University Shenzhen Graduate School, China Zhang, Haoran, Peking University Shenzhen Graduate School, China Zou, Yuexian, Peking University Shenzhen Graduate School, China

F-2-2.2: OPTIMIZING SPEAKER EMBEDDINGS USING META-TRAINING SETS

Inoue, Nakamasa, Tokyo Institute of Technology, Japan Goto, Keita, Tokyo Institute of Technology, Japan

F-2-2.3: HLT-NUS SUBMISSION FOR 2019 NIST MULTIMEDIA SPEAKER RECOGNITION EVALUATION

Das, Rohan Kumar, National University of Singapore, Singapore Tao, Ruijie, National University of Singapore, Singapore Yang, Jichen, National University of Singapore, Singapore Rao, Wei, National University of Singapore, Singapore Yu, Cheng, National University of Singapore, Singapore Li, Haizhou, National University of Singapore, Singapore

F-2-2.4: EMOTION INVARIANT SPEAKER EMBEDDINGS FOR SPEAKER IDENTIFICATION WITH EMOTIONAL SPEECH

Dev Sarma, Biswajit, Indian Institute of Technology Guwahati, India Das, Rohan Kumar, National University of Singapore, Singapore

F-2-2.5: A PITCH-AWARE SPEAKER EXTRACTION SERIAL NETWORK

Jiang, Yu, TianJin University, China Ge, Meng, TianJin University, China Wang, Longbiao, TianJin University, China Dang, Jianwu, Japan Advanced Institute of Science and Technology&Tianjin University, Japan Honda, Kiyoshi, TianJin University, China Zhang, Sulin, Automotive Data of China Co., Ltd, China Yu, Bo, Automotive Data of China Co., Ltd, China

F-2-2.6: ANALYSIS OF BIT SEQUENCE REPRESENTATION FOR SOUND CLASSIFICATION

Wang, Yikang, University of Yamanashi, Japan Okawa, Masaki, University of Yamanashi, Japan Nishizaki, Hiromitsu, University of Yamanashi, Japan

Wednesday, December 9, 17:15 - 19:15 ∘ Room A
A-2-3 - Design and Implementation for Advanced Wireless Communication Systems
Wednesday, December 9, 17:15 - 19:15 ∘ Room A
A-2-3 - Reconfigurable Computing and Performance Evaluation

A-2-3.1: A PARALLELIZATION METHOD OF INCEPTION ARCHITECTURE BASED ON ARRAY PROCESSOR

Xie, Xiaoyan, Xi’an University of Posts and Telecommunications, China Du, Zhuolin, Xi’an University of Posts and Telecommunications, China Hu, Chuanzhan, Xi’an University of Posts and Telecommunications, China Yang, Kun, Xi’an University of Posts and Telecommunications, China Wang, Anqi, Xi’an University of Posts and Telecommunications, China

A-2-3.2: RSP-BT:AN ADVANCED PARALLEL METHOD FOR DEPTH MAP MOTION ESTIMATION

Xie, Xiaoyan, Xi'an University of Posts and Telecommunications, China Wang, Anqi, Xi'an University of Posts and Telecommunications, China Zhu, Yun, Xi'an University of Posts and Telecommunications, China Hu, Chuanzhan, Xi'an University of Posts and Telecommunications, China Du, Zhuolin, Xi'an University of Posts and Telecommunications, China

A-2-3.3: FAST INTER-FRAME PREDICTION BASED ARRAY PROCESSOR FOR DEPTH MAPS IN 3D-HEVC

Zhu, Yun, Xi’an University of Posts and Telecommunications, China Jiang, Lin, Xi’an University of Science and Technology, China Song, Hui, Xi’an University of Posts and Telecommunications, China Xie, Xiaoyan, Xi’an University of Posts and Telecommunications, China Wang, Anqi, Xi’an University of Posts and Telecommunications, China Shen, Xubang, Xi'an Microelectronic Technology Research Institute, China

A-2-3.4: OPTIMIZATION OF FALSE-OVERLAP DETECTION OF TILE ASSEMBLY IN TILE-BASED RENDERING

Yang, Bowen, Northwestern Polytechnical University, China Fan, Meng, Xi’an University of Posts and Telecommunications, China Han, Mengqiao, Xi’an University of Posts and Telecommunications, China Geng, Yurong, Xi’an University of Posts and Telecommunications, China

Wednesday, December 9, 17:15 - 19:15 ∘ Room B
B-2-3 - Deep Generative Models for Media Clones and Its Detection

B-2-3.1: AN EXTENSION OF ENCRYPTION-INSPIRED ADVERSARIAL DEFENSE WITH SECRET KEYS AGAINST ADVERSARIAL EXAMPLES

MaungMaung, AprilPyone, Tokyo Metropolitan University, Japan Kiya, Hitoshi, Tokyo Metropolitan University, Japan

B-2-3.2: DETECTION OF CLONED RECOGNIZERS: A DEFENDING METHOD AGAINST RECOGNIZER CLONING ATTACK

Mori, Yuto, Osaka University, Japan Nakamura, Kazuaki, Osaka University, Japan Nitta, Naoko, Osaka University, Japan Babaguchi, Noboru, Osaka University, Japan

B-2-3.3: CLASSIFICATION OF VIDEO RECAPTURED FROM DISPLAY DEVICE

Kuribayashi, Minoru, Okayama University, Japan Kamakari, Kodai, Okayama University, Japan Kawata, Kento, Okayama University, Japan Funabiki, Nobuo, Okayama University, Japan

B-2-3.4: DETECTION OF ADVERSARIAL EXAMPLES BASED ON SENSITIVITIES TO NOISE REMOVAL FILTER

Higashi, Akinori, Okayama University, Japan Kuribayashi, Minoru, Okayama University, Japan Funabiki, Nobuo, Okayama University, Japan Nguyen, Huy, National Institute of Informatics, Japan Echizen, Isao, National Institute of Informatics, Japan

B-2-3.5: A QR SYMBOL WITH ECDSA FOR BOTH PUBLIC AND SECRET AREAS USING RHOMBIC SUB-CELLS

Teraura, Nobuyuki, Terrara Code Research Institute, Japan Echizen, Isao, National Institute of Informatics, Japan Iwamura, Keiichi, Tokyo University of Science, Japan

B-2-3.6: DEEP FACE RECOGNIZER PRIVACY ATTACK: MODEL INVERSION INITIALIZATION BY A DEEP GENERATIVE ADVERSARIAL DATA SPACE DISCRIMINATOR

Khosravy, Mahdi, Osaka University, Japan Nakamura, Kazuki, Osaka University, Japan Nitta, Naoko, Osaka University, Japan Babaguchi, Noboru, Osaka University, Japan

B-2-3.7: COLOR TRANSFER TO ANONYMIZED GAIT IMAGES WHILE MAINTAINING ANONYMIZATION

Tieu, Ngoc-Dung T., National Institute of Informatics,, Japan Yamagishi, Junichi, National Institute of Informatics,, Japan Echizen, Isao, National Institute of Informatics,, Japan

Wednesday, December 9, 17:15 - 19:15 ∘ Room C
C-2-3 - Machine Learning and Data Analysis 1

C-2-3.1: MERGING WELL-TRAINED DEEP CNN MODELS FOR EFFICIENT INFERENCE

Wu, Cheng-En, Academia Sinica, Taiwan Lee, Jia-Hong, Academia Sinica, Taiwan Wan, Timmy S.T., Academia Sinica, Taiwan Chan, Yi-Ming, Academia Sinica, Taiwan Chen, Chu-Song, Academia Sinica, Taiwan

C-2-3.2: EFFICIENT DIVERSE RESPONSE GENERATION IN ATTENTION-BASED NEURAL CONVERSATIONAL MODEL WITH MAXIMUM MUTUAL INFORMATION

Kishida, Yuki, Doshisha University, Japan Kato, Tsuneo, Doshisha University, Japan Wang, Yanan, KDDI Research, Inc., China Wu, Jianming, KDDI Research, Inc., China Hattori, Gen, KDDI Research, Inc., Japan

C-2-3.3: EXTENDING CONDITIONAL CONVOLUTION STRUCTURES FOR ENHANCING MULTITASKING CONTINUAL LEARNING

Tu, Cheng-Hao, Academia Sinica, Taiwan Wu, Cheng-En, Academia Sinica, Taiwan Chen, Chu-Song, Academia Sinica, Taiwan

C-2-3.4: MULTIPLE TARGET PREDICTION FOR DEEP REINFORCEMENT LEARNING

Chien, Jen-Tzung, National Chiao Tung University, Taiwan Hung, Po-Yen, National Chiao Tung University, Taiwan

C-2-3.5: CAN-SIN: A CROSS-LAYER HETEROGENEOUS ACADEMIC NETWORK WITH SEMANTIC INFORMATION

Tian, Yufei, Tsinghua University, China Hu, Hong, Tsinghua University, China Li, Yuejiang, Tsinghua University, China Zhao, H. Vicky, Tsinghua University, China Chen, Yan, University of Science and Technology of China, China

C-2-3.6: NATURAL LANGUAGE PROCESSING METHODS FOR DETECTION OF INFLUENZA-LIKE ILLNESS FROM CHIEF COMPLAINTS

Hsu, Jia-Hao, National Cheng Kung University, Taiwan Weng, Ting-Chia, National Cheng Kung University, Taiwan Wu, Chung-Hsien, National Cheng Kung University, Taiwan Ho, Tzong-Shiann, National Cheng Kung University, Taiwan

C-2-3.7: GENERALISATION TECHNIQUES USING A VARIATIONAL CEAE FOR CLASSIFYING MANUKA HONEY QUALITY

Phillips, Tessa, University of Auckland, New Zealand Abdulla, Waleed, University of Auckland, New Zealand

Wednesday, December 9, 17:15 - 19:15 ∘ Room D
D-2-3 - Image Analysis

D-2-3.1: VISUAL TRACKING VIA SPATIAL-TEMPORAL REGULARIZED CORRELATION FILTERS WITH ADVANCED STATE ESTIMATION

TANG, ZHAO-QIAN, Meiji University, Japan Arakawa, Kaoru, Meiji University, Japan

D-2-3.2: A NEW POLARIZED IMAGE FUSION ALGORITHM BASED ON TWO-SCALE GUIDED FILTERING

Xie, Fei, Nanjing University of Aeronautics and Astronautics, China CHEN, JIAJIA, Nanjing University of Aeronautics and Astronautics, China

D-2-3.3: AN IMPROVED GUIDED FILTERING ALGORITHM FOR POLARIZED IMAGES BY USING LOG OPERATOR

Zhan, Le, Nanjing University of Aeronautics and Astronautics, China Chen, Jiajia, Nanjing University of Aeronautics and Astronautics, China

D-2-3.4: DYNAMIC MATCHING OF LOCAL FEATURES FOR RE-IDENTIFICATION OF PEDESTRIANS

Ahn, Seokhyun, INMC, Seoul National University, Korea (South) Cho, Nam Ik, INMC, Seoul National University, Korea (South)

D-2-3.5: IMPLEMENTATION OF BI-RADS CLASSIFICATION AND PRIORITY PREDICTION FOR MAMMOGRAM PRE-SCREENING BASED ON MULTI-DECISION FRAMEWORK

Zeng, Yi-Chong, Institute for Information Industry, Taiwan Chan, Kai-Hsuan, Institute for Information Industry, Taiwan Chen, Yu-Hao, Institute for Information Industry, Taiwan Lai, Hsin-Yi, Institute for Information Industry, Taiwan

D-2-3.6: VARIATIONAL MODE DECOMPOSITION BASED IMAGE SEGMENTATION USING SINE COSINE ALGORITHM

Chouksey, Mausam, Indian Institute of Technology Patna, India Jha, Rajib Kumar, Indian Institute of Technology Patna, India

D-2-3.7: IMAGE RESTORATION BY GROUP SPARSITY WITH UNION OF HIERARCHICAL DIRLOTS

Sakashita, Kazuki, Niigata University, Japan Muramatsu, Shogo, Niigata University, Japan

Wednesday, December 9, 17:15 - 19:15 ∘ Room E
E-2-3 - Speech Recognition

E-2-3.1: PRIVACY PRESERVING ACOUSTIC MODEL TRAINING FOR SPEECH RECOGNITION

Tachioka, Yuuki, Denso IT Laboratory, Japan

E-2-3.2: END-TO-END AUTOMATIC SPEECH RECOGNITION WITH DEEP MUTUAL LEARNING

Masumura, Ryo, NTT Corporation, Japan Ihori, Mana, NTT Corporation, Japan Takashima, Akihiko, NTT Corporation, Japan Tanaka, Tomohiro, NTT Corporation, Japan Ashihara, Takanori, NTT Corporation, Japan

E-2-3.3: ATTENTIVE FUSION ENHANCED AUDIO-VISUAL ENCODING FOR TRANSFORMER BASED ROBUST SPEECH RECOGNITION

Wei, Liangfa, University of Science and Technology of China, China Zhang, Jie, University of Science and Technology of China, China Hou, Junfeng, University of Science and Technology of China, China Dai, Lirong, University of Science and Technology of China, China

E-2-3.4: QUERY-BY-EXAMPLE SPOKEN TERM DETECTION USING GENERATIVE ADVERSARIAL NETWORK

Shah, Neil, Dhirubhai Ambani Institute of Information and Communication Technology, India R, Sreeraj, Dhirubhai Ambani Institute of Information and Communication Technology, India Madhavi, Maulik, National University of Singapore, Singapore Shah, Nirmesh, Dhirubhai Ambani Institute of Information and Communication Technology, India Patil, Hemant, Dhirubhai Ambani Institute of Information and Communication Technology, India

E-2-3.5: REDUCTION OF SPEECH DATA POSTERIORGRAMS BY COMPRESSING MAXIMUM-LIKELIHOOD STATE SEQUENCES IN QUERY BY EXAMPLE

Yokota, Takashi, Iwate Prefectural University, Japan Kojima, Kazunori, Iwate Prefectural University, Japan Lee, Shi-wook, National Institute of Advanced Industrial Science and Technology, Japan Itoh, Yoshiaki, Iwate Prefectural University, Japan

E-2-3.6: EFFECTS OF END-TO-END ASR AND SCORE FUSION MODEL LEARNING FOR IMPROVED QUERY-BY-EXAMPLE SPOKEN TERM DETECTION

Kurokawa, Takumi, Shizuoka University, Japan Kai, Atsuhiko, Shizuoka University, Japan Kondo, Hiroki, Shizuoka University, Japan

Wednesday, December 9, 17:15 - 19:15 ∘ Room F
F-2-3 - Speech Enhancement 2

F-2-3.1: HARMONIC STRUCTURE MASK FOR SPEECH ENHANCEMENT USING SPARSITY REGULARIZATION

Wang, Haonan, Ritsumeikan University, Japan Iwai, Kenta, Ritsumeikan University, Japan Nishiura, Takanobu, Ritsumeikan University, Japan

F-2-3.2: DEEP RESIDUAL NETWORK-BASED AUGMENTED KALMAN FILTER FOR SPEECH ENHANCEMENT

Roy, Sujan Kumar, Griffith University, Australia Paliwal, Kuldip K., Griffith University, Australia

F-2-3.3: A STUDY ON MORE REALISTIC ROOM SIMULATION FOR FAR-FIELD KEYWORD SPOTTING

Bezzam, Eric, Sonos Inc., France Scheibler, Robin, Line Corporation, Japan Cadoux, Cyril, École Polytechnique Fédérale de Lausanne, Switzerland Gisselbrecht, Thibault, Sonos Inc., France

F-2-3.4: A VARIABLE STEP SIZE IMPROVED MULTIBAND-STRUCTURED SUBBAND ADAPTIVE FEEDBACK CANCELLATION SCHEME FOR HEARING AIDS

Pradhan, Somanath, University of Technology Sydney, Australia Qiu, Xiaojun, University of Technology Sydney, Australia Ji, Jinchen, University of Technology Sydney, Australia

F-2-3.5: LOCALIZATION CUES PRESERVATION IN HEARING AIDS BY COMBINING NOISE REDUCTION AND DYNAMIC RANGE COMPRESSION

Llave, Adrien, CentraleSupelec/IETR, France Leglaive, Simon, CentraleSupelec/IETR, France Séguier, Renaud, CentraleSupelec/IETR, France

F-2-3.6: MODELLING ROOM REVERBERATION DIRECTIVITY USING VON MISES-FISHER MIXTURE DISTRIBUTION

Bastine, Amy, The Australian National University, Australia Abhayapala, Thushara, The Australian National University, Australia Zhang, Jihui, The Australian National University, Australia Sun, Huiyuan, The Australian National University, Australia

F-2-3.7: EXPERIMENTAL INVESTIGATION OF ROBUSTNESS OF SPATIAL CEPSTRUM FEATURES UNDER VARIOUS RECORDING CONDITIONS

Kawamura, Taiga, National Institute of Technology, Tokuyama College, Japan Miyazaki, Ryoichi, National Institute of Technology, Tokuyama College, Japan Imoto, Keisuke, Doshisha University, Japan Ono, Nobutaka, Tokyo Metropolitan University, Japan

Thursday, December 10, 12:30 - 14:00 ∘ Room B
B-3-1 - Information Processing for Understanding Human Attentional and Affective States

B-3-1.1: PREDICTION OF SOCIAL MALADAPTATION USING EMOTIONAL ENTRAINMENT OF DISGUST DURING COMPREHENSIVE PSYCHIATRIC INTERVIEWS

Yokotani, Kenji, Tokushima University, Japan Takagi, Gen, Tohoku Fukushi University, Japan Wakashima, Kobun, Tohoku University, Japan

B-3-1.2: PREDICTING EXPERTISE AMONG NOVICE PROGRAMMERS WITH PRIOR KNOWLEDGE ON PROGRAMMING TASKS

Ahsan, Zubair, University of Malaya, Malaysia Obaidellah, Unaizah, University of Malaya, Malaysia

B-3-1.3: DISCOVERY OF EVENT-RELATED POTENTIALS DURING A COGNITIVE PROCESS OF COMPARISON OPERATION

Murai, Keisuke, National Institute of Technology, Nara College, Japan Hidetake, Uwano, National Institute of Technology, Nara College, Japan Ikutani, Yoshiharu, Nara Institute of Science and Technology, Japan Kubo, Takatomi, Nara Institute of Science and Technology, Japan

B-3-1.4: MAXIMUM CREDIBILITY VOTING (MCV): AN INTEGRATIVE APPROACH FOR ACCURATE DIAGNOSIS OF MAJOR DEPRESSIVE DISORDER FROM CLINICALLY READILY AVAILABLE DATA

Shimizu, Yu, Okinawa Institute of Science and Technology, Japan Yoshimoto, Junichiro, Nara Institute of Science and Technology, Japan Takamura, Masahiro, Hiroshima University, Japan Okada, Go, Hiroshima University, Japan Matsumoto, Tomoya, Hiroshima University, Japan Fuchikami, Manabu, Hiroshima University, Japan Okada, Satoshi, Hiroshima University, Japan Morinobu, Shigeru, Hiroshima University, Japan Okamoto, Yasumasa, Hiroshima University, Japan Yamawaki, Shigeto, Hiroshima University, Japan Doya, Kenji, Okinawa Institute of Science and Technology, Japan

Thursday, December 10, 12:30 - 14:00 ∘ Room C
C-3-1 - Recent devopments on signal processing theory and techniques in fractional Fourier and linear cannonical domain

C-3-1.1: IMAGE SEGMENTATION METHOD BASED ON FRACTIONAL VARYING-ORDER DIFFERENTIAL

Tian, Yuru, China University of Petroleum, China Zhang, Yanshan, Zhengzhou University of Aeronautics, China

C-3-1.2: WINDOWED FRACTIONAL FOURIER TRANSFORM ON GRAPHS: FRACTIONAL TRANSLATION OPERATOR AND HAUSDORFF-YOUNG INEQUALITY

Yan, Fang-Jia, Beijing Institute of Technology, China Gao, Wen-Biao, Beijing Institute of Technology, China Li, Bing-Zhao, Beijing Institute of Technology, China

C-3-1.3: A NOVEL ISAR IMAGING ALGORITHM FOR MANEUVERING TARGET BASED ON PARAMETER ESTIMATION METHOD

Xin, Hong-cai, Beijing Institute of Technology, China Li, Bing-zhao, Beijing Institute of Technology, China

Thursday, December 10, 12:30 - 14:00 ∘ Room D
D-3-1 - Digital Convergence of 5G, AIoT and Security II

D-3-1.1: LORA-BASED AIR QUALITY MONITORING SYSTEM USING CHATBOT

Kan, Yao-Chiang, Yuan Ze University, Taiwan Lin, Hsueh-Chun, China Medical University Hospital and College of Medicine, Taiwan Wu, Han-Yu, Yuan Ze University, Taiwan Lee, Junghsi, Yuan Ze University, Taiwan

D-3-1.2: REAL-TIME DDOS ATTACK DETECTION USING SKETCH-BASED ENTROPY ESTIMATION ON THE NETFPGA SUME PLATFORM

Lai, Yu-Kuen, Chung-Yuan Christian University, Taiwan Huang, Po-Yu, Chung-Yuan Christian University, Taiwan Lee, Ho-Ping, Chung-Yuan Christian University, Taiwan Tsai, Cheng-Lin, Chung-Yuan Christian University, Taiwan Chang, Cheng-Sheng, Chung-Yuan Christian University, Taiwan Nguyen, Manh Hung, Chung-Yuan Christian University, Taiwan Lin, Yu-Jau, Chung-Yuan Christian University, Taiwan Liu, Te-Lung, National Center for High Performance Computing, Taiwan Chen, Jim Hao, Northwestern University, United States

D-3-1.3: A DESIGN FRAMEWORK OF AUTOMATIC DEPLOYMENT FOR 5G NETWORK SLICING

Lai, Wen-Ping, Yuan Ze University, Taiwan Lai, Hong-Lun, Yuan Ze University, Taiwan Lai, Ming-Jay, National Central University, Taiwan

D-3-1.4: PRIVACY-PRESERVING DATA SHARING WITH ATTRIBUTE-BASED PRIVATE MATCHING BASED ON EDGE COMPUTATION IN THE INTERNET-OF-THINGS

Hsu, Ruei-Hau, National Sun Yat-sen University, Taiwan Hu, Yu-Hsaing, National Sun Yat-sen University, Taiwan Lin, Guan-Wei, National Sun Yat-sen University, Taiwan Ko, Bing-Cheng, National Sun Yat-sen University, Taiwan

D-3-1.5: COORDINATED DOWNLINK/UPLINK TRANSMISSION ASSIGNMENT AND DYNAMIC SWITCHING IN HYBRID TDD SYSTEM

Liu, Chun-Tai, National Chung Cheng University, Taiwan Pan, Jen-Yi, National Chung Cheng University, Taiwan Huang, Chun-Kai, National Chung Cheng University, Taiwan Pao, Wei-Chen, Industrial Technology Research Institute, Taiwan

Thursday, December 10, 12:30 - 14:00 ∘ Room E
E-3-1 - Speech Separation 1

E-3-1.1: OVER-DETERMINED SPEECH SOURCE SEPARATION AND DEREVERBERATION

Togami, Masahito, Line corporation, Japan Scheibler, Robin, Line corporation, Japan

E-3-1.2: OPTIMAL SCALE-INVARIANT SIGNAL-TO-NOISE RATIO AND CURRICULUM LEARNING FOR MONAURAL MULTI-SPEAKER SPEECH SEPARATION IN NOISY ENVIRONMENT

Ma, Chao, Tsinghua University, China Li, Dongmei, Tsinghua University, China Jia, Xupeng, Tsinghua University, China

E-3-1.3: MULTI-CHANNEL SPEECH SEPARATION USING DEEP EMBEDDING WITH MULTILAYER BOOTSTRAP NETWORKS

Yang, Ziye, Northwestern Polytechnical University, China Zhang, Xiao-Lei, Northwestern Polytechnic University, China Fu, Zhonghua, Northwestern Polytechnic University, China

E-3-1.4: INDEPENDENT VECTOR ANALYSIS FOR BLIND SPEECH SEPARATION USING COMPLEX GENERALIZED GAUSSIAN MIXTURE MODEL WITH WEIGHTED VARIANCE

Tang, Xinyu, Chongqing University of Posts and Telecommunications, China Chen, Rilin, Tencent, China Wang, Xiyuan, Beijing Information Science and Technology University, China Zhou, Yi, Chongqing University of Posts and Telecommunications, China Su, Dan, Tencent, China

E-3-1.5: IMPACT OF MINIMUM HYPERSPHERICAL ENERGY REGULARIZATION ON TIME-FREQUENCY DOMAIN NETWORKS FOR SINGING VOICE SEPARATION

Shah, Neil, TCS Research, Tata Consultancy Services Pvt. Ltd., Pune, India, India Agrawal, Dharmeshkumar, TCS Research, Tata Consultancy Services Pvt. Ltd., Pune, India, India

E-3-1.6: ON THE USE OF THE RELATIVE TRANSFER FUNCTION FOR SOURCE SEPARATION USING TWO-CHANNEL RECORDINGS

Bates, Alice, Australian National University, Australia Grixti-Cheng, Daniel, Australian National University, Australia Samarasinghe, Prasanga, Australian National University, Australia Abhayapala, Thushara, Australian National University, Australia

Thursday, December 10, 12:30 - 14:00 ∘ Room F
F-3-1 - Speech Enhancement 3

F-3-1.1: DYNAMIC NOISE EMBEDDING: NOISE AWARE TRAINING AND ADAPTATION FOR SPEECH ENHANCEMENT

Lee, Joohyung, KAIST, Korea (South) Jung, Youngmoon, KAIST, Korea (South) Jung, Myunghun, KAIST, Korea (South) Kim, Hoirin, KAIST, Korea (South)

F-3-1.2: CLASSIFICATION OF SPEECH WITH AND WITHOUT FACE MASK USING ACOUSTIC FEATURES

Das, Rohan Kumar, National University of Singapore, Singapore Li, Haizhou, National University of Singapore, Singapore

F-3-1.3: ENHANCEMENT OF SPEECH INTELLIGIBILITY UNDER NOISY REVERBERANT CONDITIONS BASED ON MODULATION SPECTRUM CONCEPT

Ngo, Thuanvan, Japan Advanced Institute of Science and Technology, Japan Ho, Tuanvu, Japan Advanced Institute of Science and Technology, Japan Unoki, Masashi, Japan Advanced Institute of Science and Technology, Japan Kubo, Rieko, National Institute of Information and Communications Technology, Japan Akagi, Masato, Japan Advanced Institute of Science and Technology, Japan

F-3-1.4: EXPLORING FEATURE ENHANCEMENT IN THE MODULATION SPECTRUM DOMAIN VIA IDEAL RATIO MASK FOR ROBUST SPEECH RECOGNITION

Yan, Bi-Cheng, National Taiwan Normal University, Taiwan, Taiwan Wu, Meng-Che, ASUS, Taiwan chen, Berlin, National Taiwan Normal University, Taiwan, Taiwan

F-3-1.5: AN INTEGRATED CNN-GRU FRAMEWORK FOR COMPLEX RATIO MASK ESTIMATION IN SPEECH ENHANCEMENT

Hasannezhad, Mojtaba, Concordia University, Canada Ouyang, Zhiheng, Concordia University, Canada Zhu, Wei-Ping, Concordia University, Canada Champagne, Benoit, McGill University, Canada

F-3-1.6: A TIME-DOMAIN MONAURAL SPEECH ENHANCEMENT WITH FEEDBACK LEARNING

Li, Andong, Institute of Acoustics, Chinese Academy of Sciences, China Zheng, Chengshi, Institute of Acoustics, Chinese Academy of Sciences, China Cheng, Linjuan, Institute of Acoustics, Chinese Academy of Sciences, China Peng, Renhua, Institute of Acoustics, Chinese Academy of Sciences, China Li, Xiaodong, Institute of Acoustics, Chinese Academy of Sciences, China

Thursday, December 10, 15:30 - 17:15 ∘ Room B
B-3-2 - The Future of Biometrics beyond Recognition and Security

B-3-2.1: PERFORMANCE EVALUATION OF FACE ANTI-SPOOFING METHOD USING DEEP METRIC LEARNING FROM A FEW FRAMES OF FACE VIDEO

Ito, Koichi, Tohoku University, Japan Kimura, Asateru, Tohoku University, Japan Aoki, Takafumi, Tohoku University, Japan

B-3-2.2: STUDY ON POSSIBILITY OF ESTIMATING SMARTPHONE INPUTS FROM TAP SOUNDS

Ouchi, Yumo, Shizuoka University, Japan Okudera, Ryosuke, Shizuoka University, Japan Shiomi, Yuya, Shizuoka University, Japan Uehara, Kota, Shizuoka University, Japan Sugimoto, Ayaka, Shizuoka University, Japan Ohki, Tetsushi, Shizuoka University, Japan Nishigaki, Masakatsu, Shizuoka University, Japan

B-3-2.3: A NOVEL QUALITY ASSESSMENT METHOD FOR EYE MOVEMENT AUTHENTICATION

Abe, Narishige, FUJITSU LABORATORIES LTD., Japan Yamada, Shigefumi, FUJITSU LABORATORIES LTD., Japan

Thursday, December 10, 15:30 - 17:15 ∘ Room B
B-3-2 - Privacy Preserving and Multimedia Security

B-3-2.1: A FRAMEWORK FOR TRANSFORMATION NETWORK TRAINING IN COORDINATION WITH SEMI-TRUSTED CLOUD PROVIDER FOR PRIVACY-PRESERVING DEEP NEURAL NETWORKS

Ito, Hiroki, Tokyo Metropolitan University, Japan Kinoshita, Yuma, Tokyo Metropolitan University, Japan Kiya, Hitoshi, Tokyo Metropolitan University, Japan

B-3-2.3: A PRIVACY-PRESERVING CONTENT-BASED IMAGE RETRIEVAL SCHEME ALLOWING MIXED USE OF ENCRYPTED AND PLAIN IMAGES

Iida, Kenta, Tokyo Metropolitan University, Japan Kiya, Hitoshi, Tokyo Metropolitan University, Japan

B-3-2.4: A GENERATIVE ADVERSARIAL NETWORK FRAMEWORK FOR JPEG ANTI-FORENSICS

Wu, Jianyuan, Sun Yat-Sen University, China Liu, Li, Kwai Incorporated, United States Kang, Xiangui, Sun Yat-Sen University, China Sun, Wei, Sun Yat-sen University, China

Thursday, December 10, 15:30 - 17:15 ∘ Room C
C-3-2 - Machine Learning and Data Analysis 2

C-3-2.1: SEMI-SUPERVISED CONTRASTIVE LEARNING WITH GENERALIZED CONTRASTIVE LOSS AND ITS APPLICATION TO SPEAKER RECOGNITION

Inoue, Nakamasa, Tokyo Institute of Technology, Japan Goto, Keita, Tokyo Institute of Technology, Japan

C-3-2.2: MPOP600: A MANDARIN POPULAR SONG DATABASE WITH ALIGNED AUDIO, LYRICS, AND MUSICAL SCORES FOR SINGING VOICE SYNTHESIS

Chu, Chan-Chuan, National Tsing Hua University, Taiwan Yang, Fu-Rong, National Tsing Hua University, Taiwan Lee, Yi-Jhe, National Tsing Hua University, Taiwan Liu, Yi-Wen, National Tsing Hua University, Taiwan Wu, Shan-Hung, National Tsing Hua University, Taiwan

C-3-2.3: IMPROVING KEYWORDS SPOTTING PERFORMANCE IN NOISE WITH AUGMENTED DATASET FROM VOCODED SPEECH

Li, Ruohao, University of Washington Bothell, United States Nie, Kaibao, University of Washington Bothell, United States

C-3-2.4: DECODING MUSIC GENRES BASED ON HIGH RESOLUTION BRAIN ACTIVITY INFORMATION

Hou, Qinhan, Tianjin University, China Zhang, Gaoyan, Tianjin University, China

C-3-2.5: 3D POINT CLOUD LABELING TOOL FOR DRIVING AUTOMATICALLY

Li, MingHui, Shenzhen Unity-Drive Innovation Technology Co, Ltd, China Zhang, Yanshan, Zhengzhou University of Aeronautics, China

C-3-2.6: DETECTING OBJECT SURFACE KEYPOINTS FROM A SINGLE RGB IMAGE VIA DEEP LEARNING NETWORK FOR 6DOF POSE ESTIMATION

Lie, Wen-Nung, National Chung Cheng University, Taiwan Aing, Lee, National Chung Cheng University, Taiwan

C-3-2.7: INTERVENTION FORCE-BASED IMITATION LEARNING FOR AUTONOMOUS NAVIGATION IN DYNAMIC ENVIRONMENTS

Yokoyama, Tomoya, Nagoya University, Japan Seiya, Shunya, Nagoya University, Japan Takeuchi, Eijiro, Nagoya University / Tier IV, Japan Takeda, Kazuya, Nagoya University / Tier IV, Japan

Thursday, December 10, 15:30 - 17:15 ∘ Room D
D-3-2 - Multimedia Analysis and Others

D-3-2.1: DIVERSE AUDIO-TO-IMAGE GENERATION VIA SEMANTICS AND FEATURE CONSISTENCY

Yang, Pei-Tse, National Taiwan University, Taiwan Su, Feng-Guang, National Taiwan University, Taiwan Wang, Yu-Chiang Frank, National Taiwan University, Taiwan

D-3-2.2: MULTISCALE SALIENCY DETECTION FOR COLORED 3D POINT CLOUDS BASED ON RANDOM WALK

Jeong, Se-Won, Ulsan National Institute of Science and Technology, Korea (South) Yun, Jae-Seong, Ulsan National Institute of Science and Technology, Korea (South) Sim, Jae-Young, Ulsan National Institute of Science and Technology, Korea (South)

D-3-2.3: THE VALIDITY OF A DUAL AZURE KINECT-BASED MOTION CAPTURE SYSTEM FOR GAIT ANALYSIS: A PRELIMINARY STUDY

Ma, Yunru, The University of Auckland, New Zealand Sheng, Bo, The University of Auckland, New Zealand Hart, Rylea, The University of Auckland, New Zealand Zhang, Yanxin, The University of Auckland, New Zealand

D-3-2.4: PART-IN-WHOLE TYPE 3D PARTIAL SHAPE RETREIVAL BASED ON CONNECTED FACES WITH POINTNET FEATURES

Aono, Masaki, Toyohashi University of Technology, Japan Iwabuchi, Wataru, Toyohashi University of Technology, Japan

D-3-2.5: FIXED-POINT ARITHMETIC OF L2-NORM APPROXIMATION FOR 2-TUPLE ARRAYS WITH ROTATED L1-NORM EVALUATION

Kodama, Yuya, Niigata University, Japan Muramatsu, Shogo, Niigata University, Japan Yamada, Hiroyoshi, Niigata University, Japan

D-3-2.6: RAPID AND ACCURATE LOCAL GAUSSIAN NOISE REMOVAL

seta, shogo, Keio University, Japan Nakahara, Yusuke, Keio University, Japan Yamaguchi, Takuro, Keio University, Japan ikehara, Masaaki, Keio University, Japan

D-3-2.7: EFFICIENT HUMAN-IN-THE-LOOP OBJECT DETECTION USING BI-DIRECTIONAL DEEP SORT AND ANNOTATION-FREE SEGMENT IDENTIFICATION

Madono, Koki, Waseda University, Japan Nakano, Teppei, Waseda University, Intelligent Framework Lab, Japan Kobayashi, Tetsunori, Waseda University, Japan Ogawa, Tetsuji, Waseda University, Japan

Thursday, December 10, 15:30 - 17:15 ∘ Room E
E-3-2 - Speech Separation 2, Sound source separation

E-3-2.1: INTEGRATION OF SEMI-BLIND SPEECH SOURCE SEPARATION AND VOICE ACTIVITY DETECTION FOR FLEXIBLE SPOKEN DIALOGUE

Wake, Masaya, Graduate School of Informatics, Kyoto University, Japan Togami, Masahito, LINE Corporation, Japan Yoshii, Kazuyoshi, Graduate School of Informatics, Kyoto University, Japan Kawahara, Tatsuya, Graduate School of Informatics, Kyoto University, Japan

E-3-2.2: DNN-BASED PERMUTATION SOLVER FOR FREQUENCY-DOMAIN INDEPENDENT COMPONENT ANALYSIS IN TWO-SOURCE MIXTURE CASE

Yamaji, Shuhei, National Institute of Technology, Kagawa College, Japan Kitamura, Daichi, National Institute of Technology, Kagawa College, Japan

E-3-2.3: COMPUTER-RESOURCE-AWARE DEEP SPEECH SEPARATION WITH A RUN-TIME-SPECIFIED NUMBER OF BLSTM LAYERS

Togami, Masahito, Line corporation, Japan Masuyama, Yoshiki, Waseda University, Japan Komatsu, Tatsuya, Line corporation, Japan Yoshii, Kazuyoshi, Kyoto University, Japan Kawahara, Tatsuya, Kyoto University, Japan

E-3-2.4: SELF-ATTENTION FOR MULTI-CHANNEL SPEECH SEPARATION IN NOISY AND REVERBERANT ENVIRONMENTS

Liu, Conggui, Fairy Devices, Japan Sato, Yoshinao, Fairy Devices, Japan

E-3-2.5: END-TO-END MUSIC-MIXED SPEECH RECOGNITION

Woo, Jeongwoo, Kyoto University, Japan Mimura, Masato, Kyoto University, Japan Yoshii, Kazuyoshi, Kyoto University, Japan Kawahara, Tatsuya, Kyoto University, Japan

E-3-2.6: ADAPTIVE NOISE SUPPRESSION FOR WAKE-WORD DETECTION BY TEMPORAL-DIFFERENCE GENERALIZED EIGENVALUE BEAMFORMER

Kagoshima, Takehiko, Toshiba Corporation, Japan Ding, Ning, Toshiba Corporation, Japan Fujimura, Hiroshi, Toshiba Corporation, Japan

Thursday, December 10, 15:30 - 17:15 ∘ Room F
F-3-2 - Speech Synthesis

F-3-2.1: LP-WAVENET: LINEAR PREDICTION-BASED WAVENET SPEECH SYNTHESIS

Hwang, Min-Jae, Search Solution, Korea (South) Soong, Frank, Microsoft, China Song, Eunwoo, Naver, Korea (South) Wang, Xi, Microsoft, China Kang, Hong-Goo, Yonsei University, Korea (South)

F-3-2.2: ONLINE SPEAKER ADAPTATION FOR WAVENET-BASED NEURAL VOCODERS

Huang, Qiuchen, University of Science and Technology of China, China Ai, Yang, University of Science and Technology of China, China Ling, Zhenhua, University of Science and Technology of China, China

F-3-2.3: IMPLEMENTATION OF SEQUENTIAL REAL-TIME WAVEFORM GENERATOR FOR HIGH-QUALITY VOCODER

Morise, Masanori, Meiji University, Japan

F-3-2.4: MODULE COMPARISON OF TRANSFORMER-TTS FOR SPEAKER ADAPTATION BASED ON FINE-TUNING

Inoue, Katsuki, Okayama university, Japan Hara, Sunao, Okayama university, Japan Abe, Masanobu, Okayama university, Japan

F-3-2.5: EXCITGLOW: IMPROVING A WAVEGLOW-BASED NEURAL VOCODER WITH LINEAR PREDICTION ANALYSIS

Oh, Suhyeon, Yonsei University, Korea (South) Lim, Hyungseob, Yonsei University, Korea (South) Byun, Kyungguen, Yonsei University, Korea (South) Hwang, Min-Jae, Search Solutions, Incorporated, Korea (South) Song, Eunwoo, Naver Corporation, Korea (South) Kang, Hong-Goo, Yonsei University, Korea (South)

F-3-2.6: PERSONALIZED END-TO-END MANDARIN SPEECH SYNTHESIS USING SMALL-SIZED CORPUS

Yuan, Chenhan, Virginia Polytechnic Institute and State University, China Huang, Yi-Chin, National Pingtung University, Taiwan

Thursday, December 10, 17:30 - 19:30 ∘ Room A
A-3-3 - Behavior Measurement and Analysis

A-3-3.1: MATHEMATICAL MODEL OF HORSE AND RIDER INTERACTION DURING HORSE JUMPING

Tsuruo, Asahi, Nara Institute of Science and Technology, Japan Ringhofer, Monamie, Kyoto University, Japan Yamamoto, Shinya, Kyoto University, Japan Ikeda, Kazushi, Nara Institute of Science and Technology, Japan

A-3-3.2: HUMAN HAND MOVEMENT RECOGNITION BASED ON HMM WITH HYPERPARAMETERS OPTIMIZED BY MAXIMUM MUTUAL INFORMATION

Wen, Ruoshi, Harbin Institute of Technology, China Wang, Qiang, Harbin Institute of Technology, China Ma, Xiang, Harbin Institute of Technology, China Li, Zhibin, The University of Edinburgh, United Kingdom

A-3-3.3: QUANTIFICATION ANALYSIS OF BEHAVIORAL CHANGES AFTER SCIATIC NERVE LIGATION IN RATS

Sri-iesaranusorn, Panyawut, Nara Institute of Science and Technology, Japan Shimochi, Saeka, University of Turku, Finland Ono, Naoki, Nara Institute of Science and Technology, Japan Yatkin, Emrah, University of Turku, Finland Iida, Hidehiro, University of Turku, Finland Ikeda, Kazushi, Nara Institute of Science and Technology, Japan Yoshimoto, Junichiro, Nara Institute of Science and Technology, Japan

A-3-3.4: SHEET-TYPE DEVICE FOR UNCONSTRAINED HEART SOUND MEASUREMENT AND WHITE NOISE REDUCTION BY WIENER FILTER

Nishio, Keita, Aoyama Gakuin University, Japan Matsumoto, Toshiyuki, Aoyama Gakuin University, Japan Kumagai, Satoshi, Aoyama Gakuin University, Japan Kurihara, Yosuke, Aoyama Gakuin University, Japan Kaburagi, Takashi, International Christian Univerisity, Japan Hamada, Yuri, Aoyama Gakuin University, Japan

A-3-3.5: BOWEL MOVEMENT SIGNAL MODELING AND PARAMETERS EXTRACTION

Chen, Zhaoqi, , Montlouis, Webert, Johns Hopkins University, United States

A-3-3.6: A NEURAL NETWORK APPROACH FOR ANOMALY DETECTION IN GENOMIC SIGNALS

Sawyer, Erica, California State University, Fresno, United States Banuelos, Mario, California State University, Fresno, United States Marcia, Roummel, University of California, Merced, United States Sindi, Suzanne, University of California, Merced, United States

A-3-3.7: EVALUATION OF THE PRESSURE MEASUREMENT FUNCTION OF AN IMPLANTABLE MULTIMODALITY PROBE

Wakuya, Manami, Kumamoto University, Japan Yamakawa, Toshitaka, Kumamoto University, Japan Inoue, Takao, Yamaguchi University, Japan Suzuki, Michiyasu, Yamaguchi University, Japan

Thursday, December 10, 17:30 - 19:30 ∘ Room B
B-3-3 - Recent Advances in Multimedia Security and Forensics

B-3-3.1: A METHOD FOR IDENTIFYING ORIGIN OF DIGITAL IMAGES USING A CONVOLUTIONAL NEURAL NETWORK

Huang, Rong, Donghua University, China Fang, Fuming, National Institute of Informatics, Japan Nguyen, Huy H., SOKENDAI (The Graduate University for Advanced Studies), Japan Yamagishi, Junichi, National Institute of Informatics, Japan Echizen, Isao, National Institute of Informatics, Japan

B-3-3.2: COST SENSITIVE OPTIMIZATION OF DEEPFAKE DETECTOR

Kukanov, Ivan, A*STAR, Singapore Karttunen, Janne, University of Eastern Finland, Finland Sillanpää, Hannu, University of Eastern Finland, Finland Hautamäki, Ville, University of Eastern Finland, Finland

B-3-3.3: VISUAL SECURITY EVALUATION OF LEARNABLE IMAGE ENCRYPTION METHODS AGAINST CIPHERTEXT-ONLY ATTACKS

Sirichotedumrong, Warit, Tokyo Metropolitan University, Japan Kiya, Hitoshi, Tokyo Metropolitan University, Japan

B-3-3.4: VEIN PATTERN VISUALISATION USING CONDITIONAL GENERATIVE ADVERSARIAL NETWORKS

Keivanmarz, Ali, Unitec Institute of Technology, New Zealand Sharifzadeh, Hamid, Unitec Institute of Technology, New Zealand Fleming, Rachel, Institute of Environmental Science and Research (ESR), New Zealand

B-3-3.5: MULTIMODAL PERSONAL EAR AUTHENTICATION USING MULTIPLE SENSOR INFORMATION

Itani, Shunji, Kansai University, Japan Kita, Shunsuke, Osaka Research Institute of Industrial Science and Technology, Japan Kajikawa, Yoshinobu, Kansai Univercity, Japan

B-3-3.6: SPEECH INFORMATION HIDING BY MODIFICATION OF LSF QUANTIZATION INDEX IN CELP CODEC

Mawalim, Candy Olivia, Japan Advanced Institute of Science and Technology, Japan Wang, Shengbei, Tianjin Polytechnic University, China Unoki, Masashi, Japan Advanced Institute of Science and Technology, Japan

B-3-3.7: A SECURE OPUS PULSE STEGANOGRAPHIC SCHEME BASED ON MESSAGE TRANSFORM

Ren, Yanzhen, Wuhan University, China Zhong, Shan, Wuhan University, China Tu, Weiping, Wuhan University, China Wang, Lina, Wuhan University, China

Thursday, December 10, 17:30 - 19:30 ∘ Room C
C-3-3 - Machine Learning for Small-sample Data Analysis

C-3-3.1: SPEAKER VERIFICATION SYSTEM BASED ON DEFORMABLE CNN AND TIME-FREQUENCY ATTENTION

Zhang, Yiming, Beijing University of Posts and Telecommunications, China Yu, Hong, Ludong University, China Ma, Zhanyu, Beijing University of Posts and Telecommunications, China

C-3-3.2: CLOSED-FORM PRE-TRAINING FOR SMALL-SAMPLE ENVIRONMENTAL SOUND RECOGNITION

Inoue, Nakamasa, Tokyo Institute of Technology, Japan Goto, Keita, Tokyo Institute of Technology, Japan

C-3-3.3: NITES: A NON-PARAMETRIC INTERPRETABLE TEXTURE SYNTHESIS METHOD

Lei, Xuejing, University of Southern California, United States Zhao, Ganning, University of Southern California, United States Kuo, C.-C. Jay, University of Southern California, United States

C-3-3.4: ADAPTIVE MULTI-PROTOTYPE RELATION NETWORK

Li, Xiaoxu, Lanzhou University of Technology, China Tian, Tao, Lanzhou University of Technology, China Liu, Yuxin, The University of Melbourne, Australia Yu, Hong, Ludong University, China Cao, Jie, Lanzhou University of Technology, China Ma, Zhanyu, Beijing University of Posts and Telecommunications, China

C-3-3.5: SUPPORTIVE AND SELF ATTENTIONS FOR IMAGE CAPTION

Chien, Jen-Tzung, National Chiao Tung University, Taiwan Lin, Ting-An, National Chiao Tung University, Taiwan

C-3-3.6: ANTI-NOISE RELATION NETWORK FOR FEW-SHOT LEARNING

Li, Xiaoxu, Lanzhou University of Technology, China Yan, Jintao, Lanzhou University of Technology, China Wu, Jijie, Lanzhou University of Technology, China Liu, Yuxin, University of Melbourne, Australia Yang, Xiaochen, University College London, United Kingdom Ma, Zhanyu, Beijing University of Posts and Telecommunications, China

C-3-3.7: SMALL DATA-DRIVEN ELECTRICAL INSULATOR DEFECT DETECTION

Song, YuXin, Beijing University of Posts and Telecommunications, China Susun, Dingkai, Beijing University of Posts and Telecommunications, China Pan, Lei, Institute of Microelectronics of the Chinese academy of Sciences, University of the Chinese academy of Sciences, China Wu, Ming, Beijing University of Posts and Telecommunications, China Zhu, Shengli, Beijing Ikingtec intelligent technology Co., Ltd, China Ma, Hui, Beijing Ikingtec intelligent technology Co., Ltd, China

Thursday, December 10, 17:30 - 19:30 ∘ Room D
D-3-3 - Image and video processing based on deep learning

D-3-3.1: DEEP LEARNING BASED DEPTH ESTIMATION AND RECONSTRUCTION OF LIGHT FIELD IMAGES

Yun, Jae-Seong, UNIST, Korea (South) Sim, Jae-Young, UNIST, Korea (South)

D-3-3.2: PROGRESSIVE DEEP NETWORK WITH CHANNEL BACK-PROJECTION FOR HYPERSPECTRAL RECOVERY FROM RGB

Lee, Sang-Ho, Korea University, Korea (South) Park, Min-Je, Korea University, Korea (South) Kim, Jong-Ok, Korea University, Korea (South)

D-3-3.3: IMAGE INPAINTING USING WEIGHTED MASK CONVOLUTION

Kang, Jiwoo, Yonsei University, Korea (South) Lee, Seongmin, Yonsei University, Korea (South) Heo, Suwoong, Yonsei University, Korea (South) Lee, Sanghoon, Yonsei University, Korea (South)

D-3-3.4: MOIRÉ ARTIFACTS REMOVAL IN SCREEN-SHOT IMAGES VIA MULTIPLE DOMAIN LEARNING

Vien, An Gia, Dongguk University, Korea (South) Park, Hyunkook, Dongguk University, Korea (South) Lee, Chul, Dongguk University, Korea (South)

D-3-3.5: DATA REDUCTION USING CLUSTER SAMPLING

Park, Ye seung, Yonsei University, Republic of Korea, Korea (South) Jang, Mingyu, Yonsei University, Republic of Korea, Korea (South) Huh, Jungwoo, Yonsei University, Republic of Korea, Korea (South) Lee, Kyoungoh, Yonsei University, Republic of Korea, Korea (South) Lee, Sanghoon, Yonsei University, Republic of Korea, Korea (South)

D-3-3.6: TEMPORAL ATTENTION FEATURE ENCODING FOR VIDEO CAPTIONING

Kim, Nayoung, Ewha W. University, Korea (South) Ha, Seong Jong, NCSOFT, Korea (South) Kang, Jewon, Ewha W. University, Korea (South)

D-3-3.7: SUPER-RESOLUTION OF MULTI-VIEW ERP 360-DEGREE IMAGES WITH TWO-STAGE DISPARITY REFINEMENT

Kim, Hee-Jae, Ewha W. University, Korea (South) Kang, Jewon, Ewha W. University, Korea (South) Lee, Byung-Uk, Ewha W. University, Korea (South)

D-3-3.8: HUMAN POSE ESTIMATION USING SKELETAL HEATMAPS

Jun, Jinyoung, Korea University, Korea (South) Lee, Jae-Han, Korea University, Korea (South) Kim, Chang-Su, Korea University, Korea (South)

Thursday, December 10, 17:30 - 19:30 ∘ Room E
E-3-3 - Advanced Signal Processing and Machine Learning for Audio and Speech Applications

E-3-3.1: A JOINT-LOSS APPROACH FOR SPEECH ENHANCEMENT VIA SINGLE-CHANNEL NEURAL NETWORK AND MVDR BEAMFORMER

Tan, Zhi-Wei, Nanyang Technological University, Singapore Nguyen, Anh H. T., Nanyang Technological University, Singapore Tran, Linh T. T., Nanyang Technological University, Singapore Khong, Andy W. H., Nanyang Technological University, Singapore

E-3-3.2: SOURCE ENHANCEMENT FOR UNMANNED AERIAL VEHICLE RECORDING USING MULTI-SENSORY INFORMATION

Yen, Benjamin, University of Auckland, New Zealand Hioka, Yusuke, University of Auckland, New Zealand Mace, Brian, University of Auckland, New Zealand

E-3-3.3: A STUDY ON GEOMETRICALLY CONSTRAINED IVA WITH AUXILIARY FUNCTION APPROACH AND VCD FOR IN-CAR COMMUNICATION

Goto, Kana, University of Tsukuba, Japan Li, Li, University of Tsukuba, Japan Takahashi, Riki, University of Tsukuba, Japan Makino, Shoji, University of Tsukuba, Japan Yamada, Takeshi, University of Tsukuba, Japan

E-3-3.4: DYNAMIC SYNCHRONOUS AVERAGING FOR ENHANCEMENT OF PERIODIC SIGNAL UNDER SAMPLING FREQUENCY VARIATION

Sumiyoshi, Kyosuke, Tokyo Metropolitan University, Japan Wakabayashi, Yukoh, Tokyo Metropolitan University, Japan Ono, Nobutaka, Tokyo Metropolitan University, Japan

E-3-3.5: JOINT-DIAGONALIZABILITY-CONSTRAINED MULTICHANNEL NONNEGATIVE MATRIX FACTORIZATION BASED ON MULTIVARIATE COMPLEX STUDENT'S T-DISTRIBUTION

Kamo, Keigo, The University of Tokyo, Japan Kubo, Yuki, The University of Tokyo, Japan Takamune, Norihiro, The University of Tokyo, Japan Kitamura, Daichi, National Institute of Technology, Kagawa Collage, Japan Saruwatari, Hiroshi, The University of Tokyo, Japan Takahashi, Yu, Yamaha Corporation, Japan Kondo, Kazunobu, Yamaha Corporation, Japan

Thursday, December 10, 17:30 - 19:30 ∘ Room F
F-3-3 - Signal Processing Systems for AI

F-3-3.1: NOISE SUPPRESSION USING A DIFFERENTIAL-TYPE MICROPHONE ARRAY AND TWO-DIMENSIONAL AMPLITUDE AND PHASE SPECTRA

Shiozawa, Koichiro, University of Yamanashi, Japan Ozawa, Kenji, University of Yamanashi, Japan Ise, Tomohiko, Alps Alpine Co., Ltd., Japan

F-3-3.2: ROBUST SPEECH DEREVERBERATION BASED ON WPE AND DEEP LEARNING

Li, Hao, Inner Mongolia University, China Zhang, Xueliang, Professor, China Gao, Guanglai, Professor, China

F-3-3.3: AN ACOUSTIC SIGNAL PROCESSING SYSTEM FOR IDENTIFICATION OF QUEEN-LESS BEEHIVES

Peng, Rui, Unitec Institute of Technology, New Zealand Ardekani, Iman, Unitec Institute of Technology, New Zealand Sharifzadeh, Hamid, Unitec Institute of Technology, New Zealand

F-3-3.4: SEGMENTATION OF PALM VEIN IMAGES USING U-NET

Marattukalam, Felix, The University of Auckland, New Zealand Abdulla, Waleed H., The University of Auckland, New Zealand

F-3-3.5: DEEP NEURAL NETWORK COMPRESSION WITH KNOWLEDGE DISTILLATION USING CROSS-LAYER MATRIX, KL DIVERGENCE AND OFFLINE ENSEMBLE

Chou, Hsing-Hung, National Tsing Hua University, Taiwan Chiu, Ching-Te, National Tsing Hua University, Taiwan Liao, Yi-Ping, National Tsing Hua University, Taiwan

F-3-3.6: ENHANCED CHANNEL TRACKING IN THZ BEAMSPACE MASSIVE MIMO: A DEEP CNN APPROACH

Kaur, Navjot, McGill University, Canada Hosseini, Seyyed Saleh, McGill University, Canada Champagne, Benoit, McGill University, Canada

F-3-3.7: PROCESSING ELEMENT ARCHITECTURE DESIGN FOR DEEP REINFORCEMENT LEARNING WITH FLEXIBLE BLOCK FLOATING POINT EXPLOITING SIGNAL STATISTICS

Su, Juyn-Da, National Central University, Taiwan Tsai, Pei-Yun, National Central University, Taiwan

F-3-3.8: ACOUSTIC ECHO CANCELLATION BASED ON RECURRENT NEURAL NETWORK

Tsai, Yao Cheng, National Central University, Taiwan Liang, Kai Wen, National Central University, Taiwan Chang, Pao Chi, National Central University, Taiwan

Main Menu