IEICE Technical Report

Print edition: ISSN 0913-5685      Online edition: ISSN 2432-6380

Volume 117, Number 516

Signal Processing

Workshop Date : 2018-03-19 - 2018-03-20 / Issue Date : 2018-03-12

[PREV] [NEXT]

[TOP] | [2014] | [2015] | [2016] | [2017] | [2018] | [2019] | [2020] | [Japanese] / [English]

[PROGRAM] [BULK PDF DOWNLOAD]


Table of contents

SIP2017-111
Adaptive BSS algorithm for approximate joint diagonalization with variable epoch length
Kei Nishiyama, Shinya Saito (TUS), Kunio Oishi (TUT), Toshihiro Furukawa (TUS)
pp. 1 - 6

SIP2017-112
Stable Estimation Method of Spatial Correlation Matrices for Multi-channel NMF
Yuuki Tachioka (Denso IT Lab)
pp. 7 - 12

SIP2017-113
Experimental Evaluation of Multichannel Audio Source Separation Based on IDLMA
Daichi Kitamura, Hayato Sumino, Norihiro Takamune, Shinnosuke Takamichi, Hiroshi Saruwatari (Univ. of Tokyo), Nobutaka Ono (Tokyo Metropolitan Univ.)
pp. 13 - 20

SIP2017-114
Non-parallel and Many-to-Many Voice Conversion Using Variational Autoencoder Conditioned by Phonetic Posteriorgrams and d-vectors
Yuki Saito (NTT/Univ. of Tokyo), Yusuke Ijima, Kyosuke Nishida (NTT), Shinnosuke Takamichi (Univ. of Tokyo)
pp. 21 - 26

SIP2017-115
On the Use of Deep Gaussian Processes for GPR-based Speech Synthesis
Tomoki Koriyama, Takao Kobayashi (Tokyo Inst. of Tech.)
pp. 27 - 32

SIP2017-116

Kazuki Shimada, Yoshiaki Bando, Masato Mimura, Katsutoshi Itoyama, Kazuyoshi Yoshii, Tatsuya Kawahara (Kyoto Univ.)
pp. 33 - 38

SIP2017-117
[Poster Presentation] Acoustic properties of vowel produced under environments with different reberberation time
Rieko Kubo, Masato Akagi (JAIST)
pp. 39 - 44

SIP2017-118
[Poster Presentation] Investigation about LSTM Post-filter for Voice Activity Detection
Kiyoaki Matsui, Takafumi Moriya, Takaaki Fukutomi, Yusuke Shinohara, Yoshikazu Yamaguchi, Manabu Okamoto, Yushi Aono (NTT)
pp. 45 - 50

SIP2017-119
[Poster Presentation] Speaker verification based on non-linear bandwidth extension considering aliasing artifacts for super-wideband applications
Haruna Miyamoto, Sayaka Shiota, Hitoshi Kiya (Tokyo Metropolitan Univ.)
pp. 51 - 55

SIP2017-120
[Poster Presentation] Text-dependent voice liveness detection based on pop-noise detector considering speaker-dependent phoneme information for speaker verification
Shihono Mochizuki, Sayaka Shiota, Hitoshi Kiya (Tokyo Metropolitan Univ.)
pp. 57 - 62

SIP2017-121
[Poster Presentation] Acoustic analysis of speech for emergency speech detection of voicemail
Matsuto Hori (Meiji Univ.), Hosana Kamiyama, Satoshi Kobashikawa (NTT), Shigeki Sagayama (Meiji Univ.)
pp. 63 - 68

SIP2017-122
[Poster Presentation] Quantitative and corpus-based analysis of pronunciation diversity observed in Japanese English
Suguru Kabashima, Haoyu Zhang, Daisuke Saito, Nobuaki Minematsu (Univ. of Tokyo), Satoshi Kobashikawa, Ryo Masumura (NTT)
pp. 69 - 74

SIP2017-123
[Poster Presentation] An Experimental Study on Segmental and Prosodic Comparison of Utterances for Automatic Assessment of Dubbing Speech
Takuya Ozuru, Nobuaki Minematsu, Daisuke Saito (Univ. of Tokyo)
pp. 75 - 80

SIP2017-124
[Poster Presentation] Investigation of Brain Magnetic Fields Associated with Sound Imagery -- Speech and Pure Tone with Similar Envelopes --
Shihomi Uzawa (Kobe Univ./AIST), Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.), Yoshiharu Soeta (AIST), Seiji Nakagawa (Chiba Univ./AIST)
pp. 81 - 86

SIP2017-125
[Poster Presentation] Intelligibility of speech with additive bubble noise and enhancement under hearing impairment simulation
Narumi Ohashi, Naoko Yomura, Katsuhiko Yamamoto (Wakayama Univ.), Shoko Araki, Keisuke Kinoshita, Tomohiro Nakatani (NTT), Toshio Irino (Wakayama Univ.)
pp. 87 - 92

SIP2017-126
[Poster Presentation] Automatic transcription of playing the shamisen by harmonic structure and positions on pressable string
Keita Masaki, Hiroaki Kudo, Tetsuya Matsumoto, Noboru Ohnishi (Nagoya Univ.), Yoshinori Takeuchi (Daido Univ.)
pp. 93 - 100

SIP2017-127
[Poster Presentation] A Study on Acoustic Design Support System for Compact Acoustic Devices Using DNN -- Application for Compact Acoustic Devices with Multiple Acoustic Holes --
Kai Nakamura, Yoshinobu Kajikawa (Kansai Univ.)
pp. 101 - 106

SIP2017-128
[Poster Presentation] The sound spot reproduction by recomposing decomposed signals using multiple loudspeaker arrays
Kazuya Yasueda, Daisuke Shinjo, Akitoshi Kataoka (Ryukoku Univ.)
pp. 107 - 110

SIP2017-129
[Poster Presentation] A Study on Mitigation Processing of Binaural Reproduction Controller Applying Output Tracking Control
Kentaro Matsui, Atsuro Ito (NHK), Shohei Mori, Masaki Inoue, Shuichi Adachi (Keio Univ.)
pp. 111 - 116

SIP2017-130
[Poster Presentation] Horizontal sound localization with binaural signals obtained by numerical simulation and experiment
Mio Aoyama, Daichi Sakamoto, Takao Tsuchiya (Doshisha Univ.)
pp. 117 - 120

SIP2017-131
[Poster Presentation] Reproduction of the Roaring Dragon "Nakiryu" Phenomenon in Yakushido Hall by Sound Field Rendering
Issei Takenuki, Takuya Kambara, Takao Tsuchiya (Doshisha Univ.), Hiroshi Hasegawa (Utsunomiya Univ.)
pp. 121 - 126

SIP2017-132
[Poster Presentation] Tolerance of local linear predictive coding against disturbance noise
Fumihiko Ishiyama (NTT)
pp. 127 - 132

SIP2017-133
[Poster Presentation] Sound Source Separation Using Supervised NMF Based on One-dimensional Oblique Projections
Misaki Komatsu, Akira Tanaka (Hokkaido Univ.)
pp. 133 - 134

SIP2017-134
[Poster Presentation] A Study on Head-mounted Feedforward ANC System -- Noise Reduction Performance When Extended to Case(2,1,1) ANC System --
Takumi Miyake, Kenta Iwai, Yoshinobu Kajikawa (Kansai Univ.)
pp. 135 - 140

SIP2017-135
[Poster Presentation] Supervised Clustering Based on Mahalanobis Metric Learning and Principal Component Matching
Yuya Sugie, Akira Tanaka (Hokkaido Univ.)
pp. 141 - 142

SIP2017-136
[Poster Presentation] A new hyperspectral pansharpening method using noisy panchromatic image
Saori Takeyama, Shunsuke Ono, Itsuo Kumazawa (Tokyo Inst. of Tech.)
pp. 143 - 148

SIP2017-137
[Poster Presentation] Optimization of Computational Scheduling for Acceleration of Directional Cubic Convolution Interpolation
Tomohiro Sasaki, Yoshihiro Maeda, Masahiro Nakamura, Norishige Fukushima (Nagoya Inst. of Tech.)
pp. 149 - 154

SIP2017-138
[Poster Presentation] Formulation of frequency characteristic of second-order nonlinear IIR filter
Kenta Iwai, Yoshinobu Kajikawa (Kansai Univ.)
pp. 155 - 160

SIP2017-139
[Poster Presentation] Performance Evaluation of Initial Value Setting Method for Spatial Correlation Matrices in Multi-channel NMF
Yu Tajima, Akira Tanaka (Hokkaido Univ.)
pp. 161 - 162

SIP2017-140
[Poster Presentation] Study on the implementation of the Feedforward ANC system using virtual sensing technique
Shoma Edamoto, Yoshinobu Kajikawa (Kansai Univ.)
pp. 163 - 168

SIP2017-141
[Poster Presentation] Modeling and Performance Analysis of Blind Source Separation with Nonlinear Mixing
Wang Lu, Tomoaki Ohtsuki (Keio Univ.)
pp. 169 - 174

SIP2017-142
[Poster Presentation] Edge signal processing for water leak detection
Kenji Ichige (Hitachi)
pp. 175 - 178

SIP2017-143
[Poster Presentation] A Study on Identification of Loudspeaker System Using Adaptive Wiener Filter with Cross-correlation Method
Ryota Saika, Kenta Iwai, Yoshinobu Kajikawa (Kansai Univ.)
pp. 179 - 184

SIP2017-144
Optimization of Gaussian Kernel Parameters for Kernel Logistic Regression
Kosuke Fukumori, Tomoya Wada, Toshihisa Tanaka (TUAT)
pp. 185 - 190

SIP2017-145
A Multi-Exposure Image Fusion Scheme based on Automatic Exposure Compensation
Yuma Kinoshita, Sayaka Shiota, Hitoshi Kiya (Tokyo Metro. Univ.)
pp. 191 - 196

SIP2017-146
Accuracy Improvement of Fashon Style Classification by Appropriate Training Data and Estimation of Human Regions
Takeshi Nakajima, Takuro Oki, Ryusuke Miyamoto (Meiji Univ.)
pp. 197 - 202

SIP2017-147
[Poster Presentation] Development of NU Voice Conversion System 2018
Patrick Lumban Tobing, Yi-Chiao Wu, Tomoki Hayashi, Kazuhiro Kobayashi (Nagoya Univ.), Tomoki Toda (Nagoya Univ./JST PRESTO)
pp. 203 - 208

SIP2017-148
[Poster Presentation] An investigation of singing voice separation methods for a statistical approach to singing voice modification in music
Tomoya Yamada, Shogo Seki, Kazuhiro Kobayashi, Tomoki Toda (Nagoya Univ.)
pp. 209 - 214

SIP2017-149
[Poster Presentation] Do prosodic manual annotations matter for Japanese speech synthesis systems with WaveNet vocoder?
Hieu-Thi Luong, Xin Wang, Junichi Yamagishi (NII), Nobuyuki Nishizawa (KDDI Research)
pp. 215 - 220

SIP2017-150
[Poster Presentation] A Hybrid Approach on Electrolaryngeal Speech Enhancement based on Spectral Differential Features and Noise Suppression
Mohammad Eshghi, Kazuhiro Kobayashi, Tomoki Toda (Nagoya Univ.)
pp. 221 - 226

SIP2017-151
[Poster Presentation] Speech Enhancement Using Non-Local Means
Kyohei Mitani, Yosuke Sugiura, Tetsuya Shimamura (Saitama Univ.)
pp. 227 - 230

SIP2017-152
[Poster Presentation] Voiceless Consonant Detection and Artificial Bandwidth Extension of Narrow Band Speech
Shun Asawa, Yosuke Sugiura, Tetsuya Shimamura (Saitama Univ.)
pp. 231 - 234

SIP2017-153
(See Japanese page.)
pp. 235 - 240

SIP2017-154
[Poster Presentation] Perceptual influence of spectral envelope and aperiodicity quantization for encoding high-quality speech
Genta Miyashita, Masanori Morise (Univ. of Yamanashi)
pp. 241 - 244

SIP2017-155
[Poster Presentation] Optimization of Outdoor Loudspeaker Level Based on U50 for Disaster Prevention Administrative Radio
Ryouichi Nishimura (NICT), Shuichi Sakamoto (Tohoku Univ.), Yoshifumi Chisaki (Chiba Inst. of Tech.), Zhenglie Cui (Tohoku Univ.)
pp. 245 - 250

SIP2017-156
[Poster Presentation] Design and implementation of resilient node networks for outdoor loudspeaker system
Yuki Ueda, Yoshifumi Chisaki (Chiba Inst. of Tech.), Shuichi Sakamoto (Tohoku Univ.), Ryouichi Nishimura (NICT), Cui Zhenglie (Tohoku Univ.)
pp. 251 - 254

SIP2017-157
[Poster Presentation] Convolutive Residual Echo Power Estimation for Addressing Long Reverberation-Time Problem
Masahiro Fukui, Suehiro Shimauchi (NTT), Yusuke Hioka (Univ. of Auckland)
pp. 255 - 260

SIP2017-158
[Poster Presentation] MUSIC Algorithm Based on the Temporal DRR and Generalized Rayleigh Quotient under Reverberant Environment
Ryusuke Tanaka, Yoichi Haneda (UEC)
pp. 261 - 266

SIP2017-159
[Poster Presentation] Relationship between subjective impressions and physical parameters on vowel Japanese vowel space
Haruka Matsumoto, Mitsunori Mizumachi (Kyushu Inst. of Tech.), Ken-Ichi Sakakibara (Health Sciences Univ. of Hokkaido)
pp. 267 - 274

SIP2017-160
[Poster Presentation] A study on suitable modulation parameters for spectral peak noise reduction based on frequency modulated carrier in parametric loudspeaker
Kairi Mori, Takahiro Fukumori, Masato Nakayama, Takanobu Nishiura (Ritsumeikan Univ.)
pp. 275 - 276

SIP2017-161
[Poster Presentation] Performance evaluation of unknown sound clustering for indoor-environmental sound classification based on self-generated acoustic model
Sakiko Mishima, Yukoh Wakabayashi, Takahiro Fukumori, Keisuke Imoto, Masato Nakayama, Takanobu Nishiura (Ritsumeikan Univ.)
pp. 277 - 280

SIP2017-162
[Poster Presentation] Nonnegative Matrix Factorization for Determined Multichannel Systems under Reverberant Environments
Hideaki Kagami (Keio Univ.), Hirokazu Kameoka (NTT), Masahiro Yukawa (Keio Univ.)
pp. 281 - 286

SIP2017-163
[Poster Presentation] Consideration on Fingertip Gesture Input System for Wearable Devices with Head Movements
Ayaka Mineo, Tomoki Tanaka, Yoshihiro Yamashita, Takao Nishitani, Kiyoshi Nishikawa (Tokyo Metropolitan Univ.)
pp. 287 - 290

SIP2017-164
[Poster Presentation] Adaptive beat noise estimation for FM radio in motor vehicle
Kosuke Hasada, Arata Kawamura, Youji Iiguni (Osaka Univ.)
pp. 291 - 296

SIP2017-165
[Poster Presentation] Image Super-resolution with Complex Nonseparable Oversampled Lapped Transforms
Satoshi Nagayama, Shogo Muramatsu, Hiroyoshi Yamada (Niigata Univ.)
pp. 297 - 298

SIP2017-166
[Poster Presentation] M-CHANNEL CRITICALLY SAMPLED SPECTRAL GRAPH FILTER BANKS WITH SYMMETRIC STRUCTURE
Akie Sakiyama, Kana Watanabe, Yuichi Tanaka (TUAT)
pp. 299 - 304

SIP2017-167
[Poster Presentation] Phase-aware spectral gain estimation using phase reconstruction based on phase distortion averaging
Yukoh Wakabayashi, Masato Nakayama, Takanobu Nishiura (Ritsumeikan Univ.)
pp. 305 - 310

SIP2017-168
[Poster Presentation] Effective Frequency Bands and Features for Epileptic Focus Detectionfrom Interical Electrocorticogram
Tatsunori Itakura, Shintaro Ito, Toshihisa Tanaka (TUAT), Hidenori Sugano (Juntendo Univ.)
pp. 311 - 316

SIP2017-169
[Poster Presentation] Haze Removal based on Surface Approximation of Color-Line
Takuro Yamaguchi, Koichiro Manabe, Masaaki Ikehara (Keio Univ.)
pp. 317 - 322

SIP2017-170
[Poster Presentation] Anomaly Detection by Reconstructing Features from Subsampled Audio Signals
Yohei Kawaguchi (Hitachi)
pp. 323 - 327

SIP2017-171
[Poster Presentation] Singing voice separation based on constrained robust PCA and dictionary-based fundamental frequency tracking
Takanori Fujisawa, Tomohiro Watanabe, Masaaki Ikehara (Keio Univ.)
pp. 329 - 334

SIP2017-172
[Poster Presentation] Multiple Far Noise Suppression for Meeting Scene with Various Devices Using Transfer-function-gain NMF
Yutaro Matsui, Shoji Makino (Univ. of Tsukuba), Nobutaka Ono (Tokyo Metropolitan Univ.), Takeshi Yamada (Univ. of Tsukuba)
pp. 335 - 340

SIP2017-173
[Poster Presentation] Blind Source Separation Based on the Sparsity of Impulse Responses
Ryota Oda, Daichi Kitahara, Akira Hirabayashi (Ritsumeikan Univ.)
pp. 341 - 346

SIP2017-174
[Poster Presentation] Image Super-Resolution via Convolutional Neural Network Using An Orthogonal Projection Layer
Nobuyuki Baba, Hidetomo Kataoka, Daichi Kitahara, Akira Hirabayashi (Ritsumeikan Univ.)
pp. 347 - 352

SIP2017-175
[Invited Talk] Progress of Research on Cross-modal Scene Analysis
Kunio Kashino (NTT)
p. 353

SIP2017-176
Analysis of transmission characteristics of bone-conducted speech using spoken voice
Teruki Toya (JAIST), Peter Birkholz (Tech. Univ. of Dresden), Masashi Unoki (JAIST)
pp. 355 - 360

SIP2017-177
Study on Noise Suppression Method based on Modulation Spectrum
Takuto Isoyama, Masashi Unoki (JAIST)
pp. 361 - 366

SIP2017-178
Speech Dereverberation Based on Recursive Weighted Prediction Error
Takehiko Kagoshima, Ui-Hyun Kim, Masami Akamine (Toshiba)
pp. 367 - 372

SIP2017-179
DNN prefiltering for enhancement of voice recognition in noise environment
Jun Takahashi, Kentaro Murase (Fujitsu Labs.)
pp. 373 - 378

SIP2017-180
A Study on Structure of Deep Neural Network for Speech Enhancement
Yosuke Sugiura, Tetsuya Shimamura (Saitama Univ.)
pp. 379 - 384

SIP2017-181
Development of NU non-parallel Voice Conversion System 2018
Yi-Chiao Wu, Patrick Lumban Tobing, Tomoki Hayashi, Kazuhiro Kobayashi, Tomoki Toda (Nagoya Univ.)
pp. 385 - 390

SIP2017-182
Fast Singular Value Decomposition Using Polar Decomposition Based on Chebyshev Polynomial Approximation
Masaki Onuki, Yuichi Tanaka (TUAT)
pp. 391 - 396

SIP2017-183
Dynamic Coding for Relative Positioning in Device Swarms using Sound
Marat Zhanikeev (Tokyo Univ. of Science)
pp. 397 - 400

SIP2017-184
Design of packet detection algorithm for PPLC-PV communication
Daichi Kouda (Univ. of Tokyo), Min Li (Girasol Energy), Hideya Ochiai (Univ. of Tokyo), Ikusaburo Kurimoto (NIT, Kisarazu College), Hiroshi Esaki (Univ. of Tokyo)
pp. 401 - 406

Note: Each article is a technical report without peer review, and its polished version will be published elsewhere.


The Institute of Electronics, Information and Communication Engineers (IEICE), Japan