Wed, Mar 1 AM 09:20 - 10:10 |
(1) |
09:20-09:45 |
Speech waveform synthesis based on WaveNet considering speech generation process |
Akira Tamamori, Tomoki Hayashi, Tomoki Toda, Kazuya Takeda (Nagoya Univ.) |
(2) |
09:45-10:10 |
Nonaudible murmur enhancement based on non-negative tensor factorization with segment feature regularization in noisy environments |
Yusuke Tajiri (Nagoya Univ.), Hirokazu Kameoka (NTT), Tomoki Toda (Nagoya Univ.) |
|
10:10-10:25 |
Break ( 15 min. ) |
Wed, Mar 1 AM 10:25 - 11:40 |
(3) |
10:25-10:50 |
Noisy speech reconstruction based on deep neural network with optical microphone |
Tomoyuki Mizuno, Takahiro Fukumori, Masato Nakayama, Takanobu Nishiura (Ritsumeikan Univ.) |
(4) |
10:50-11:15 |
Missing Component Restoration for Speech Spectrogram Based on Time-domain Signal Estimation |
Shogo Seki (Nagoya Univ.), Hirokazu Kameoka (NTT), Tomoki Toda, Kazuya Takeda (Nagoya Univ.) |
(5) |
11:15-11:40 |
Study on tolerance of time axis fluctuation of pure white pseudonoisesignal1for impulse response measurement |
Kentaro Mori, Yutaka Kaneda (Tokyo Denki Univ.) |
|
11:40-12:40 |
Lunch Break ( 60 min. ) |
Wed, Mar 1 PM 12:40 - 14:10 |
(6) |
12:40-14:10 |
[Poster Presentation]
Indoor-environmental sound identification based on deep neural network with higher-dimensional features |
Sakiko Mishima, Yukoh Wakabayashi, Takahiro Fukumori, Masato Nakayama, Takanobu Nishiura (Ritsumeikan Univ.) |
(7) |
12:40-14:10 |
[Poster Presentation]
Feature analysis of electrocardiogram based on non-orthogonal wavelet expansions |
Suehiro Shimauchi, Kana Eguchi, Toki Takeda, Ryosuke Aoki (NTT) |
(8) |
12:40-14:10 |
[Poster Presentation]
Conversion from linear microphone array signal to cylindrical binaural signal |
Asuka Yamazato, Yoichi Haneda (UEC) |
(9) |
12:40-14:10 |
[Poster Presentation]
Application and Evaluation of CIP Methods to Acoustic Wave Propagation Analysis with Multi-dimensional Advection |
Akihiro Fukuda, Kan Okubo (Tokyo Met. Univ.), Takuya Oshima (Niigata Univ.), Takao Tsuchiya (Doshisha Univ.), Masashi Kanamori (JAXA) |
(10) |
12:40-14:10 |
[Poster Presentation]
Comparison Analysis of Screeching Sound Using High-resolution Recording System
-- Are different types of screeching sound similar to each other? -- |
Shuya Ogino, Yuka Manabe (Tokyo Met. Univ.), Kunio Hara (USC)), Kan Okubo (Tokyo Met. Univ.) |
(11) |
12:40-14:10 |
[Poster Presentation]
Analysis of Acoustic Characteristics of Wind Bells Using 24 bit/192 kHz High-resolution Measurement System |
Fumikazu Saze, Yuto Oishi, Natsuhiko araki, Shun Kamikokura, Ryoya Kozai, Shuya Ogino, Yuka Manabe, Yuta Katori, Kan Okubo (Tokyo Met. Univ.) |
(12) |
12:40-14:10 |
[Poster Presentation]
Performance Evaluation of Initial Value Setting Method for Multi-channel NMF Using Single-channel NMF |
Yu Tajima, Akira Tanaka (HU) |
(13) |
12:40-14:10 |
[Poster Presentation]
A Simple Self-Tuning Technique for Adaptive Proximal Forward-Backward Splitting |
Kwangjin Jeong, Masahiro Yukawa (Keio Univ.), Masao Yamagishi, Isao Yamada (Tokyo Inst. Tech.) |
(14) |
12:40-14:10 |
[Poster Presentation]
Reflectance Spectra Estimation and Color Reproduction Based on Neugebauer Model |
Kohei Inoue, Kenji Hara, Kiichi Urahama (Kyushu Univ.) |
(15) |
12:40-14:10 |
[Poster Presentation]
Improvement of the Similarity Calculation of B-Spline Open Curves by the Optimal Normalization |
Yuuma Kubouchi, Akira Tanaka (Hokkaido Univ.) |
(16) |
12:40-14:10 |
[Poster Presentation]
On Radar Image Denoising with Complex Nonseparable Oversampled Lapped Transforms |
Satoshi Nagayama, Shogo Muramatsu, Hiroyoshi Yamada (Niigata Univ.), Yuuichi Sugiyama (FUJITSU TEN) |
(17) |
12:40-14:10 |
[Poster Presentation]
Improvement Method for Removing Noise due to Magnetic Flux Trap in HTS-SQUID Magnetometers Based on Mean-Shift Clustering |
Marina Taniguchi, Yuta Katori, Kan Okubo (TMU), Nobunao Takeuchi (THU), Kiyoshi Nishikawa (TMU) |
(18) |
12:40-14:10 |
[Poster Presentation]
GPU Implementation of Blur-Based Object Detection Using Spatial Domain Filtering |
Shuhei Aoki, Shingo Kobayashi, Ryusuke Miyamoto (Meiji Univ.) |
(19) |
12:40-14:10 |
[Poster Presentation]
Implementation and Evaluation of Cursor Moving Interface Using Electrooculogram |
Shohei Ogai, Toshihisa Tanaka (TUAT) |
(20) |
12:40-14:10 |
[Poster Presentation]
A Study on Magnetic Fluctuation Estimation Using Observation Data of Orthogonal Ternary Geomagnetic Field |
Mami Sekigawa, Kan Okubo (TMU), Nobunao Takeuchi (THU), Kiyoshi Nishikawa (TMU) |
(21) |
12:40-14:10 |
[Poster Presentation]
Dual-Sparsification of Kernel Regression Based on Sampling |
Atsushi Kojima, Toshihisa Tanaka (TUAT) |
(22) |
12:40-14:10 |
[Poster Presentation]
Estimation of Music Genres from Spontaneous Brain Activity Analysis by Using Neural Network |
Hiroki Itoga, Yoshikazu Washizawa (UEC) |
(23) |
12:40-14:10 |
[Poster Presentation]
Representation Method Using Hermite Interpolating Polynomials and Compact Finite Difference for Natural Spline Interpolation and its Application |
Hotaka Maruyama, Kan Okubo, Norio Tagawa (Tokyo Met. Univ.) |
(24) |
12:40-14:10 |
[Poster Presentation]
Estimation of playing position from music and speech sources based on music database |
Satoshi Inui, Toru Takahashi (OSU) |
(25) |
12:40-14:10 |
[Poster Presentation]
Influence of the Fletcher effect, the Lombard effect and the high-pass filtered auditory feedback on singing voice |
Satoshi Iijima, Shunsuke Ishimitsu, Masashi Nakayama (Hiroshima City Univ.) |
(26) |
12:40-14:10 |
[Poster Presentation]
Reverberant speech enhancement with deep auto encoder based on harmonic structure |
Rikuto Ota, Yukoh Wakabayashi, Takahiro Fukumori, Masato Nakayama, Takanobu Nishiura (Ritsumeikan Univ.) |
(27) |
12:40-14:10 |
[Poster Presentation]
An investigation of speaker adaptation method for DNN-based speech synthesis using speaker codes |
Nobukatsu Hojo, Yusuke Ijima (NTT) |
(28) |
12:40-14:10 |
[Poster Presentation]
Prosodic Word Embeddings for DNN-based speech synthesis |
Yusuke Ijima, Nobukatsu Hojo, Ryo Masumura, Taichi Asami (NTT) |
|
14:10-14:25 |
Break ( 15 min. ) |
Wed, Mar 1 PM 14:25 - 15:40 |
(29) |
14:25-14:50 |
TDOA Estimation Based on Phase-Voting Cross Correlation and Circular Standard Deviation |
Masanori Kato, Yuzo Senda, Reishi Kondo (NEC) |
(30) |
14:50-15:15 |
Image restoration based on weighted average of multiple blurred and noisy images |
Ryo Tanikawa, Takanori Fujisawa, Masaaki Ikehara (Keio Univ.) |
(31) |
15:15-15:40 |
Study on a Reduction of Calculated Amount in a Time-Domain Blind Source Separation |
Tsubasa Inoue (NIT) |
|
15:40-15:55 |
Break ( 15 min. ) |
Wed, Mar 1 PM 15:55 - 17:20 |
(32) |
15:55-16:35 |
[Invited Talk]
Multikernel Adaptive Filtering: Signal Processing and Machine Learning |
Masahiro Yukawa (Keio Univ.) |
|
16:35-16:40 |
Break ( 5 min. ) |
(33) |
16:40-17:20 |
[Invited Talk]
An Introduction to Example-based Speech Enhancement and Its Improvements |
Atsunori Ogawa, Keisuke Kinoshita, Marc Delcroix, Tomohiro Nakatani (NTT) |
Thu, Mar 2 AM 09:00 - 10:30 |
(34) |
09:00-10:30 |
[Poster Presentation]
Fast Approximate Joint Diagonalization for Convolutive Blind Speech Separation |
Toshiki Mori, Shinya Saito (TUS), Kunio Oishi (Tokyo Univ. of Tech.), Tosihiro Furukawa (TUS) |
(35) |
09:00-10:30 |
[Poster Presentation]
Study of room acoustic characteristics calculation from an impulse response measured at high sound pressure |
Ryo Takebayashi, Yutaka Kaneda (Tokyo Denki Univ.) |
(36) |
09:00-10:30 |
[Poster Presentation]
Study on the noise reduction effect of band-limited impulse response measurement signal |
Kouta Motegi, Yutaka Kaneda (Tokyo Denki Univ.) |
(37) |
09:00-10:30 |
[Poster Presentation]
Development of a communication system for smartphones using information hiding in audio signal |
Chihiro Terayama, Niitsuma Masahiro, Yamashita Yoichi (Ritsumeikan Univ.) |
(38) |
09:00-10:30 |
[Poster Presentation]
Three-dimensional directivity control based on circular harmonic modes using a circular loudspeaker array |
Koya Sato, Yoichi Haneda (UEC) |
(39) |
09:00-10:30 |
[Poster Presentation]
Sound localization using shoulder-type wearable loudspeaker with end-fire array |
Imaizumi Kenta, Yoichi Haneda (UEC) |
(40) |
09:00-10:30 |
[Poster Presentation]
Network-oriented virtual auditory display system based on edge computing |
Shuhei Ito, Yukio Iwaya (Tohoku Gakuin Univ.), Makoto Otani (Kyoto Univ.), Takao Tsuchiya (Doshisha Univ.) |
(41) |
09:00-10:30 |
[Poster Presentation]
Convergence rate analysis of stereo echo canceller with pre-processing units in both channels |
Arata Honda, Kazushi Ikeda (NAIST) |
(42) |
09:00-10:30 |
[Poster Presentation]
Beat Noise Canceling Based on Adaptive Line Enhancer for FM Radio in Motor Vehicles |
Takahiro Yamashita, Arata Kawamura, Youji Iiguni (Osaka Univ.) |
(43) |
09:00-10:30 |
[Poster Presentation]
Switchable Adaptive Feedback Canceller for Hearing Aids |
Kakeru Kashima, Arata Kawamura (Osaka Univ.), Masahiro Sunohara, Kazuteru Nishiyama, Nobuhiko Hiruma (Rion Co., Ltd.), Youji Iiguni (Osaka Univ.) |
(44) |
09:00-10:30 |
[Poster Presentation]
Realization of a Headrest ANC System |
Shoma Edamoto (Kansai Univ.), Chuang Shi (NTU), Yoshinobu Kajikawa (Kansai Univ.) |
(45) |
09:00-10:30 |
[Poster Presentation]
An evaluation of voice intelligibility in factory noise environment based on active noise control and auditory masking |
Rumi Ito, Takahiro Fukumori, Masato Nakayama, Takanobu Nishiura (Ritsumeikan Univ.) |
(46) |
09:00-10:30 |
[Poster Presentation]
Parameter estimation method for mirror filter based on quadratically constrained quadratic optimization
-- A study on a estimation using measured displacement of the diaphragm -- |
Kenta Iwai (Kansai Univ.), Masao Yamagishi (Tokyo Tech), Yoshinobu Kajikawa (Kansai Univ.) |
(47) |
09:00-10:30 |
[Poster Presentation]
An adaptive ARMA fitting model for conventional room transfer function a comparison study |
Chibana Kengo, Bruno Senzio Savino Barzel (Ryukyu Univ) |
(48) |
09:00-10:30 |
[Poster Presentation]
NLMS algorithm using shift operation |
Takumi Miyake, Yoshinobu Kajikawa (Kansai Univ.) |
(49) |
09:00-10:30 |
[Poster Presentation]
Spatial propagation analysis of indoor parametric array |
Ryosuke Imamoto (Kansai Univ.), Chuang Shi (NTU), Yoshinobu Kajikawa (Kansai Univ.) |
(50) |
09:00-10:30 |
[Poster Presentation]
Study of branch selecting DNN acoustic model for robustness to environmental variation |
Takafumi Moriya, Taichi Asami, Yoshikazu Yamaguchi, Yushi Aono (NTT) |
(51) |
09:00-10:30 |
[Poster Presentation]
Performance evaluation of noisy shouted speech detection based on acoustic model with rahmonic and mel-frequency cepstrum coefficients |
Takahiro Fukumori, Masato Nakayama, Takanobu Nishiura (Ritsumeikan Univ.), Hiroaki Nanjo (Kyoto Univ.) |
(52) |
09:00-10:30 |
[Poster Presentation]
Use of the end of sentence and speaker-derived information in recurrent neural network language models for multiparty conversations. |
Hiroto Ashikawa, Naohiro Tawara (Waseda Univ.), Atsunori Ogawa, Tomoharu Iwata (NTT), Tetsuji Ogawa, Tetsunori Kobayashi (Waseda Univ.) |
(53) |
09:00-10:30 |
[Poster Presentation]
Acoustic-to-articulatory inversion mapping with variational latent trajectory Gaussian mixture model |
Patrick Lumban Tobing (Nagoya Univ.), Hirokazu Kameoka (NTT), Tomoki Toda (Nagoya Univ.) |
(54) |
09:00-10:30 |
[Poster Presentation]
Hardware Speech Sensor Based on Deep Neural Network Feature Extractor and Template Matching |
Yi Liu, Boyu Qian, Jian Wang, Takahiro Shinozaki (Titech) |
(55) |
09:00-10:30 |
[Poster Presentation]
Individuality-Preserving HMM Sound Synthesis System for Articulation Disorders |
Reina Ueda (Kobe Univ.), Tetsuya Takiguchi (Kobe Univ./JST PRESTO), Yasuo Ariki (Kobe Univ.) |
(56) |
09:00-10:30 |
[Poster Presentation]
Statistical Voice Conversion Including Duration for Dytharthric Speech |
Ryo Aihara, Tetsuya Takigichi, Yasuo Ariki (Kobe Univ.) |
|
10:30-10:45 |
Break ( 15 min. ) |
Thu, Mar 2 AM 10:45 - 11:45 |
(57) |
10:45-11:45 |
[Special Invited Talk]
Speech and Audio Coding for High-Quality Services of Mobile-Phone and Broadcasting |
Takehiro Moriya (NTT) |
|
11:45-12:45 |
Lunch Break ( 60 min. ) |
Thu, Mar 2 PM 12:45 - 13:35 |
(58) |
12:45-13:10 |
Non-native speech conversion with consistency-aware recursive network and generative adversarial network |
Keisuke Oyamada (Univ. of Tsukuba), Hirokazu Kameoka, Takuhiro Kaneko (NTT), Hiroyasu Ando (Univ. of Tsukuba), Kaoru Hiramatsu, Kunio Kashino (NTT) |
(59) |
13:10-13:35 |
Feature Extraction Using Adaptive Restricted Boltzmann Machine for Dysarthric Speech Recognition |
Yuki Takashima (Kobe Univ.), Toru Nakashika (UEC), Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) |
|
13:35-13:50 |
Break ( 15 min. ) |
Thu, Mar 2 PM 13:50 - 15:05 |
(60) |
13:50-14:15 |
An Efficient Approximate Joint Diagonalization Algorithm and its Application to Blind Source Separation |
Shinya Saito (Tokyo Univ. of Science), Kunio Oishi (Tokyo Univ. of Tech.), Toshihiro Furukawa (Tokyo Univ. of Science) |
(61) |
14:15-14:40 |
Reproduction method of 22.2 multichannel sound in noisy environment considering inter-channel correlation |
Shu Kitajima, Takehiro Sugimoto, Kazuho Ono (NHK) |
(62) |
14:40-15:05 |
Multiple sound zone generation by using multi-point control method in real environment |
Kazuya Yasueda, Daishuke Shinjo, Akitoshi Kataoka (Ryukoku Univ.) |
|
15:05-15:20 |
Break ( 15 min. ) |
Thu, Mar 2 PM 15:20 - 16:35 |
(63) |
15:20-15:45 |
Distance Distinction Using Variance of Phase Difference for Source Signals in Same Direction |
Tomoyasu Uchiyama, Arata Kawamura (Osaka Univ.), Youichi Fujisaka, Nobuhiko Hiruma (Rion Co.,Ltd.), Youji Iiguni (Osaka Univ.) |
(64) |
15:45-16:10 |
Speech enhancement with phase reconstruction using phase distortion in harmonic frequency |
Yukoh Wakabayashi, Takahiro Fukumori, Masato Nakayama, Takanobu Nishiura, Yoichi Yamashita (Ritsumeikan Univ.) |
(65) |
16:10-16:35 |
A Method of Reducing Discomfort in Acoustic Communication using Phase Modulation by Processing per Subcarrier |
Yuichi Sato, Hitoshi Aida (UTokyo) |