Thu, Mar 14 AM
10:00 - 11:15 |
| (1) |
10:00-10:25 |
Hue Correction Scheme Based on CIELAB Color Space |
Yuma Kinoshita, Hitoshi Kiya (Tokyo Metro. Univ.) |
| (2) |
10:25-10:50 |
Blind speech separation based on approximate joint diagonalization utilizing correlation between neighboring frequency bins |
Taiki Asamizu, Toshihiro Furukawa (TUS) |
| (3) |
10:50-11:15 |
Nearest sound source extraction for hearable devices |
Eiji Saito, Arata Kawamura (Kyoto Sangyo Univ.) |
| |
11:15-11:25 |
Break ( 10 min. ) |
Thu, Mar 14 AM
11:25 - 12:15 |
| (4) |
11:25-12:15 |
[Invited Talk: APSIPA Sadaoki Furui Prize Paper Award Lecture]Recent Advances on Active Noise Contro
○Yoshinobu Kajikawa(Kansai Univ.) |
| |
12:15-13:30 |
Break / Lunch ( 75 min. ) |
Thu, Mar 14 PM
Chair: Shigeto Takeoka
13:30 - 15:00 |
| (5) |
13:30-15:00 |
[Poster Presentation]
Voice activity detection under high levels of noise using gated convolutional neural networks |
Li Li, Koshino Yuki, Matsumoto Mitsuo, Makino Shoji (Univ. Tsukuba) |
| (6) |
13:30-15:00 |
[Poster Presentation]
Automatic Design Support System for Micro Speaker Mounted on Smartphone |
Kai Hirai, Yoshinobu Kajikawa (Kansai Univ.) |
| (7) |
13:30-15:00 |
[Poster Presentation]
Prototype of an electronic earplug for music |
Lixue Chen, Yoshinori Yokoo, Kohichi Matsuda, Hirofumi Nakajima (Kogakuin Univ.), Yohichi Fujisaka (RION Co., Ltd.) |
| (8) |
13:30-15:00 |
[Poster Presentation]
An Initialization Method for Multichannel Nonnegative Matrix Factorization using Nonnegative Independent Component Analysis |
Takahiro Ushijima, Takanobu Uramoto, Shingo Uenohara, Ken'ichi Furuya (Oita Univ.) |
| (9) |
13:30-15:00 |
[Poster Presentation]
Snore sound identification using noise suppression and multi-class classification under real environments |
Keisuke Nishijima, Ken'ichi Furuya (Oita Univ.) |
| (10) |
13:30-15:00 |
[Poster Presentation]
Prototyping of Interaction Software Based on Selective Synthesis and Superposition of Multiple Sound Fields |
Toshiharu Horiuchi, Sumaru Niida (KDDI Research) |
| (11) |
13:30-15:00 |
[Poster Presentation]
Steganographic Audio Secret Sharing |
Shu Noguchi, Kotaro Sonoda, Senya Kiyasu (Nagasaki Univ.) |
| (12) |
13:30-15:00 |
[Poster Presentation]
Design of automatic soundscape generation with a privacy protection |
Yoshifumi Chisaki (CIT), Toshiharu Horiuchi (KDDI Research) |
| (13) |
13:30-15:00 |
[Poster Presentation]
Design of an autonomous control for intelligent public address node |
Takumi Kawashima, Takumi Shirai, Yoshifumi Chisaki (CIT) |
| (14) |
13:30-15:00 |
[Poster Presentation]
Multi-channel ANC Window with Virtual Sensing Technique |
Rina Hasegawa (Kansai Univ.), Dong-Yuan Shi (NTU), Yoshinobu Kajikawa (Kansai Univ.), Woon-Seng Gan (NTU) |
| (15) |
13:30-15:00 |
[Poster Presentation]
MR Image Reconstruction Using Two Types of Dictionaries and the Diagonalization of a BCCB Matrix |
Kazuma Nakamoto, Kosuke Fujii, Daichi Kitahara, Akira Hirabayashi (Ritsumeikan Univ.) |
| (16) |
13:30-15:00 |
[Poster Presentation]
A Fricative Sound /z/ Detector Based on Zero-Crossing Rate |
Yuki Katagiri, Arata Kawamura (Kyoto Sangyo Univ.) |
| (17) |
13:30-15:00 |
[Poster Presentation]
Headrest ANC System for Broadband Noise at the Desired Position |
Reo Maeda, Yoshinobu Kajikawa (Kansai Univ.) |
| (18) |
13:30-15:00 |
[Poster Presentation]
Image Super-Resolution via Generative Adversarial Network Considering Objective Quality |
Hiroya Yamamoto, Daichi Kitahara, Akira Hirabayashi (Ritsumeikan Univ.) |
| (19) |
13:30-15:00 |
Beamforming for Brain-Activity Reconstruction under Time-Correlated Interference |
Takehiro Kono (Keio Univ.), Masahiro Yukawa (Keio Univ./Riken), Tomasz Piotrowski (Nicolaus Copernicus Univ./Interdisciplinary Center for Modern Te) |
| (20) |
13:30-15:00 |
[Poster Presentation]
An Efficient Online Learning Method Based on Self-tuned Gaussian Kernels |
Masaaki Takizawa, Masahiro Yukawa (Keio Univ.) |
| (21) |
13:30-15:00 |
[Poster Presentation]
An experimental study of influence of classroom babble noise on automatic assessment of learners' shadowing speech |
Suguru Kabashima, Daisuke Saito, Nobuaki Minematsu (UTokyo), Yutaka Yamauchi (Soka Univ.), Kayoko Ito (Koyasan Univ.) |
| (22) |
13:30-15:00 |
[Poster Presentation]
Modeling learners’ pronunciation variations and its application to automatic phoneme error detection |
Zhang Haoyu, Saito Daisuke, Minematsu Nobuaki (UTokyo), Kobashikawa Satoshi, Masumura Ryo (NTT) |
| (23) |
13:30-15:00 |
[Poster Presentation]
Initial analysis of emotional speech acted in noise |
Yi Zhao (NII), Atsushi Ando (NTT), Shinji Takaki, Junichi Yamagishi (NII), Satoshi Kobashikawa (NTT) |
| (24) |
13:30-15:00 |
[Poster Presentation]
CWT spectral loss for training a DNN-based speech waveform model |
Shinji Takaki (NII), Hirokazu Kameoka (NTT), Junichi Yamagishi (NII) |
| (25) |
13:30-15:00 |
[Poster Presentation]
A robust algorithm of phase recovery for speech enhancement |
Dongxiao Wang, Koichi Shinoda (TokyoTech), Hirokazu Kameoka (NTT) |
| (26) |
13:30-15:00 |
[Poster Presentation]
Adaptive beamformer for desired source extraction with neural network based direction of arrival estimation |
Yu Nakagome (Waseda Univ.), masahito togami (LINE) |
| (27) |
13:30-15:00 |
[Poster Presentation]
MVDR beamformer based on time-frequency-bin-wise switching technique for underdetermined speech enhancement |
Kouei Yamaoka (Univ. of Tsukuba), Nobutaka Ono (Tokyo Metropolitan Univ.), Shoji Makino, Takeshi Yamada (Univ. of Tsukuba) |
| (28) |
13:30-15:00 |
[Poster Presentation]
Diffuse noise reduction using adversarial denoising autoencoder |
Hikari Tanabe, Naohiro Tawara, Tetsunori Kobayashi (Waseda Univ.), Masaru Fujieda, Katagiri Kazuhiro, Takashi Yazu (OKI), Tetsuji Ogawa (Waseda Univ.) |
| (29) |
13:30-15:00 |
[Poster Presentation]
Use and evaluation of Tacotron and context features in rakugo speech synthesis |
Shuhei Kato (SOKENDAI/NII), Shinji Takaki, Junichi Yamagishi (NII), Yusuke Yasuda (SOKENDAI/NII), Xin Wang (NII) |
| |
15:00-15:15 |
Break ( 15 min. ) |
Thu, Mar 14 PM
15:15 - 16:30 |
| (30) |
15:15-15:40 |
Convergence-guaranteed independent positive semidefinite tensor analysis for blind source separation |
Kanta Fukushige, Norihiro Takamune (UTokyo), Daichi Kitamura (Kagawa-NICT), Hiroshi Saruwatari (UTokyo), Rintaro Ikeshita, Tomohiro Nakatani (NTT) |
| (31) |
15:40-16:05 |
Estimation of rank-constrained spatial covariance model based on multivariate complex Student's t distribution for blind source separation |
Yuki Kubo, Norihiro Takamune (UTokyo), Daichi Kitamura (Kagawa NCIT), Hiroshi Saruwatari (UTokyo) |
| (32) |
16:05-16:30 |
A Study on Speech Synthesis Based on Deep Gaussain Processes and Latent Variable Representation of Accent |
Tomoki Koriyama, Takao Kobayashi (Tokyo Tech) |
| |
16:30-16:40 |
Break ( 10 min. ) |
Thu, Mar 14 PM
16:40 - 17:30 |
| (33) |
16:40-17:30 |
[Invited Talk]
Encouragement of Participation in Competition
-- Looking Back on Hitachi's Participation in DCASE 2018 Challenge -- |
Yohei Kawaguchi, Ryo Tanabe, Takashi Endo, Yuki Nikaido, Kenji Ichige, Phong Nguyen, Koichi Hamada (Hitachi) |
Fri, Mar 15 AM
10:00 - 11:15 |
| (34) |
10:00-10:25 |
Consideration on Effectiveness of Relative Phase from Residual Speech for Speaker Recognition |
Seiichi Nakagawa, Kazumasa Yamamoto, Kazumasa Yamamoto (Chubu Univ.) |
| (35) |
10:25-10:50 |
Neural Language Models based on Conditional Hierarchical Recurrent Encoder-Decoder for Multi-Party Conversational Speech Recognition |
Ryo Masumura, Tomohiro Tanaka, Atsushi Ando, Takanobu Oba, Yushi Aono (NTT) |
| (36) |
10:50-11:15 |
Likability Estimation Model Training of Call-center Agents Based on Annotators' Skills |
Hosana Kamiyama, Atsushi Ando, Ryo Masumura, Satoshi Kobashikawa, Yushi Aono (NTT) |
| |
11:15-11:25 |
Break ( 10 min. ) |
Fri, Mar 15 AM
Chair: Suehiro Shimauchi
11:25 - 12:15 |
| (37) |
11:25-12:15 |
[Invited Talk]
Realization of real-time blind source separation with auxiliary-function-based algorithms |
Nobutaka Ono (TMU) |
| |
12:15-13:30 |
Break / Lunch ( 75 min. ) |
Fri, Mar 15 PM
13:30 - 15:00 |
| (38) |
13:30-15:00 |
[Poster Presentation]
A Design of Reduced Phoneme Set Based on a Language Model |
Shuji Komeiji, Toshihisa Tanaka (Tokyo Univ. of Agriculture and Tech.) |
| (39) |
13:30-15:00 |
[Poster Presentation]
Pseudo-Multidimensional Processing of Geomagnetic Field Data Measured using HTS-SQUID Magnetometers for Removing Flux Trapping Noise |
Kai Yokoyama, Kiyoshi Nishikawa (Tokyo Metro Univ) |
| (40) |
13:30-15:00 |
|
|
| (41) |
13:30-15:00 |
[Poster Presentation]
A compressed sensing approach to hyperspectral pansharpening |
Saori Takeyama, Shunsuke Ono, Itsuo Kumazawa (Tokyo Tech) |
| (42) |
13:30-15:00 |
[Poster Presentation]
Epileptic Focus Detection from Interictal Electroencephalogram using RNN |
Byambadorj Nyamradnaa, Kosuke Fukumori, Toshihisa Tanaka (TAT), Yasushi Iimura, Takumi Mitsuhashi, Hidenori Sugano (Juntendo Univ.) |
| (43) |
13:30-15:00 |
[Poster Presentation]
Epileptic Spike Detection and Identification of Effective Frequency Band with Neural Networks |
Kosuke Fukumori (TUAT), Noboru Yoshida (Juntendo Univ.), Toshihisa Tanaka (TUAT) |
| (44) |
13:30-15:00 |
[Poster Presentation]
Effect of Entrainment by Selective Attention to Music and Speech |
Ryosuke Matsui, Toshihisa Tanaka (TUAT) |
| (45) |
13:30-15:00 |
[Poster Presentation]
A study on sound source direction detection method using coefficients of adaptive filter |
Kensaku Fujii (Kodaway Lab.), Mitsuji Muneyasu (Kansai Univ.) |
| (46) |
13:30-15:00 |
[Poster Presentation]
Study of acoustic scene analysis using sound-to-light conversion devices "blinky'' |
Yuto Oishi, Jin-cheng Zhang, Yutaka Yamamoto, Fumikazu Saze, Hiroyuki Moriyama, Robin Scheibler, Yukoh Wakabayashi, Nobutaka Ono (TMU) |
| (47) |
13:30-15:00 |
[Poster Presentation]
Multimodal Blind Source Separation using Microphones and Sound-to-light Conversion Devices "Blinkies" |
Robin Scheibler, Nobutaka Ono (TMU) |
| (48) |
13:30-15:00 |
[Poster Presentation]
Subjective evaluation of power saving audio playback algorithm based on auditory masking |
Tsukasa Nakashima (Kyutech), Mitsuhiro Nakagawara (Panasonic), Mitsunori Mizumachi (Kyutech) |
| (49) |
13:30-15:00 |
[Poster Presentation]
Study on 3D audio coding based on spatial auditory masking |
Kodai Kato, Masayuki Nishiguchi, Kanji Watanabe, Shouichi Takane, Koji Abe (Akita Pref. Univ.) |
| (50) |
13:30-15:00 |
[Poster Presentation]
A Study on Stimuli Bandwidth of Monaural Directional Band |
Michika Yamada, Fumikazu Saze (TMU), Toshiharu Horiuchi (KDDI Research), Kan Okubo (TMU) |
| (51) |
13:30-15:00 |
[Poster Presentation]
Acoustic particle cannon using ultrasonic hemispherical transducers array |
Yutaka Yamamoto, Kan Okubo (Tokyo Met. Univ.) |
| (52) |
13:30-15:00 |
[Poster Presentation]
Effective Hammering Method for Determining Dead Alkaline Dry Battery |
Tomoaki Magome, Kan Okubo (Tokyo Metropolitan Univ.) |
| (53) |
13:30-15:00 |
[Poster Presentation]
Distributed Microphone Wireless Network System for Wide Area Synchronous Recording |
Akihiro Watanabe, Kan Okubo, Norio Tagawa (TMU) |
| (54) |
13:30-15:00 |
[Poster Presentation]
Classification of Coins with Similar Designs Using High Resolution Acoustic Characteristics |
Naoko Nakazato, Yuka Manabe, Kan Okubo (TMU) |
| (55) |
13:30-15:00 |
[Poster Presentation]
Faster than real-time and audio sampling rate extraction of fo candidates using an analytic signal with prolate spheroidal wave function as envelope |
Hideki Kawahara (Wakayama Univ.), Ken-Ichi Sakakibara (Health Science Univ. Hokkaido), Masanori Morise (Univ. Yamanashi), Yuichi Ishimoto (NINJAL) |
| (56) |
13:30-15:00 |
[Poster Presentation]
F0 estimation using TV-CAR speech analysis based on Regularized LP |
Keiichi Funaki (Univ. of the Ryukyus) |
| (57) |
13:30-15:00 |
[Poster Presentation]
Robustness of statistical voice conversion based on waveform modification against external noise |
Yusuke Kurita, Kazuhiro Kobayashi, Kazuya Takeda (Nagoya Univ.), Tomoki Toda (Nagoya Univ./JST PRESTO) |
| (58) |
13:30-15:00 |
[Poster Presentation]
An Evaluation of Underdetermined Source Separation Based on Multichannel Variational Autoencoder |
Shogo Seki (Nagoya Univ.), Hirokazu Kameoka (NTT), Li Li (Univ. Tsukuba), Tomoki Toda, Kazuya Takeda (Nagoya Univ.) |
| (59) |
13:30-15:00 |
[Poster Presentation]
Design and Evaluation of Ladder Denoising Autoencoder for Auditory Speech Feature Extraction of Overlapped Speech Separation |
Hiroshi Sekiguchi, Yoshiaki Narusue, Hiroyuki Morikawa (Univ. of Tokyo) |
| (60) |
13:30-15:00 |
[Poster Presentation]
Data augmentation using multiple databases for end-to-end dysarthric speech recognition |
Yuki Takashima, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) |
| (61) |
13:30-15:00 |
[Poster Presentation]
Simultaneous Japanese Flexible-Keyword Detection and Speaker Recognition for Low-Resource Devices |
Hiroshi Fujimura (TOSHIBA) |
| (62) |
13:30-15:00 |
[Poster Presentation]
Evaluation of non-linear artificial bandwidth extension with x-vector-based speaker verification |
Ryota Kaminishi, Sayaka Shiota, Hitoshi Kiya (Tokyo Metro. Univ.) |
| |
15:00-15:15 |
Break ( 15 min. ) |
Fri, Mar 15 PM
Chair: Kanji Watanabe
15:15 - 15:40 |
| (63) |
15:15-15:40 |
A Basic Study on Azimuth Estimation Model of Sound Image in Car Cabin by Using a Gammachirp Auditory Filterbank |
Koji Sakamoto (Denso Ten Technology), Masashi Nakamura, Masanobu Maeda (Denso Ten) |
: kobashikawa.satoshi[at]lab.ntt.co.jp 
i
k-
b
s
