Mon, Mar 28 AM EA1
09:00 - 10:30 |
| (1) |
09:00-09:25 |
Method of presenting sound signals for selective listening system |
Tomomi Suzuki (Nagoya Univ.), Takanori Nishino (Mie Univ.), Yoshio Ishiguro, Tomoki Toda, Kazuya Takeda (Nagoya Univ.) |
| (2) |
09:25-09:50 |
The effects of sounds reflected from the shoulder on the sound localization |
Hiroki Adachi, Katuhiro Maki (Aichi Syukutoku Univ) |
| (3) |
09:50-10:30 |
[Invited Talk]
Measurement signals for an acoustical impulse response |
Yutaka Kaneda (Tokyo Denki Unov.) |
| |
10:30-10:45 |
Break ( 15 min. ) |
Mon, Mar 28 AM SIP1
10:45 - 12:15 |
| (4) |
10:45-11:10 |
Distortion Correction of Observed Speech with Optical Microphone Using Reflected Laser |
Tomoyuki Mizuno, Yukoh Wakabayashi, Takahiro Fukumori, Masato Nakayama, Takanobu Nishiura (Ritsumeikan Univ.) |
| (5) |
11:10-11:35 |
Beat Noise Suppression for FM-Radio in Motor Vehicles |
Takahiro Yamashita, Arata Kawamura, Youji Iiguni (Osaka Univ.) |
| (6) |
11:35-12:15 |
[Fellow Memorial Lecture]
Developing new ideas based on study of the past |
Masaaki Ikehara (Keio Univ.) |
| |
12:15-13:15 |
Lunch Break ( 60 min. ) |
Mon, Mar 28 PM Poster1
13:15 - 14:45 |
| (7) |
13:15-14:45 |
[Poster Presentation]
Analysis of Initial-value Dependency in Multichannel Nonnegative Matrix Factorization for Speech Recognition |
Iori Miura (Oita Univ.), Yuuki Tachioka, Tomohiro Narita, Jun Ishii (Mitsubishi Electric Corp.), Fuminori Yoshiyama, Shingo Uenohara, Ken'ichi Furuya (Oita Univ.) |
| (8) |
13:15-14:45 |
[Poster Presentation]
High Output Power Speaker with Digitally Direct Driven Technique
-- 100W at 9V Low Consumption Speaker System -- |
Masayoshi Takahashi, Atsuki Tonomura, Satoshi Saikatsu, Akira Yasuda, Michitake Yoshino (Hosei Univ.) |
| (9) |
13:15-14:45 |
[Poster Presentation]
Determination of Optimal Windowing Length Based on the Cepstrum Ratio for Structural Health Monitoring |
Yoshinori Takahashi (TMCIT) |
| (10) |
13:15-14:45 |
[Poster Presentation]
Optimization of delay and sum beamformer using deep neural network |
Maya Origuchi, Mitsunori Mizumachi (KIT) |
| (11) |
13:15-14:45 |
[Poster Presentation]
Convolutive Blind Source Separation with multi-stage Approximate Joint Diagonalization |
Toshiki Mori, Shinya Saito (TUS), Kunio Oishi (Tokyo Univ. of Tech.), Tosihiro Furukawa (TUS) |
| (12) |
13:15-14:45 |
[Poster Presentation]
A method for improving linear prediction effect by applying recursive type adaptive filter to linear prediction |
Kensaku Fujii (Kodaway Lab.), Mitsuji Muneyasu (Kansai Univ.) |
| (13) |
13:15-14:45 |
[Poster Presentation]
Study on influence of autocorrelation of measurement noise on affine projection algorithm |
Suehiro Shimauchi (NTT) |
| (14) |
13:15-14:45 |
[Poster Presentation]
An Investigation into the Attenuation Depending on the Distance in the Watching System Using an Electromagnetic Wave |
Takuya Ukai (NBU), Hiroki Funabashi (CIT), Manabu Fukushima (NBU), Syun'ichi Kawano (artnet), Yoshitaka Kondo (J-TEC), Mitsuo Matsumoto, Hirofumi Yanagawa (CIT) |
| (15) |
13:15-14:45 |
[Poster Presentation]
An Investigation of the Relationship between Brain Activity and the Articulation material |
Manabu Fukushima, Takuya Ukai, Yuhei Kamada, Rin Shimabukuro, Shuhei Yonekawa, Risa Maruo (NBU), Syun'ichi Kawano (artnet), Yoshitaka Kondo (J-TEC), Kubota Yasuya (Aural Sonic), Mitsuo Matsumoto, Hirofumi Yanagawa (CIT) |
| (16) |
13:15-14:45 |
[Poster Presentation]
The evaluation of high-speed railway vehicle sound by Fractal dimension |
Yoshiaki Makabe, Tomoaki Kimura (Kanagawa Institute of Technology), Kenji Muto (Shibaura Institute of Technology) |
| (17) |
13:15-14:45 |
[Poster Presentation]
Lombard effects on speech annoyance and speech intelligibility in noisy environments |
Rieko Kubo, Daisuke Morikawa, Masato Akagi (JAIST) |
| (18) |
13:15-14:45 |
[Poster Presentation]
Super-Resolution Vocal Tract Spectrum Estimation with Missing Data Imputation Using Non-Negative Matrix Factorization |
Tomohiko Nakamura (Todai), Hirokazu Kameoka (Todai/NTT) |
| (19) |
13:15-14:45 |
[Poster Presentation]
An evaluation of F0 transformation for statistical singing voice conversion based on spectral differential filtering |
Kazuhiro Kobayashi (NAIST), Tomoki Toda (Nagoya Univ./NAIST), Satoshi Nakamura (NAIST) |
| (20) |
13:15-14:45 |
[Poster Presentation]
An evaluation of acoustic-to-articulatory inversion mapping with latent trajectory Gaussian mixture model |
Patrick Lumban Tobing (NAIST), Tomoki Toda (Nagoya Univ./NAIST), Hirokazu Kameoka (NTT), Satoshi Nakamura (NAIST) |
| (21) |
13:15-14:45 |
[Poster Presentation]
Nonaudible murmur enhancement based on non-negative tensor factorization of air- and body-conducted signals in real environments |
Yusuke Tajiri (NAIST), Hirokazu Kameoka (NTT), Tomoki Toda (Nagoya Univ./NAIST), Satoshi Nakamura (NAIST) |
| (22) |
13:15-14:45 |
[Poster Presentation]
Verification of Circuit Scale and Design Error for CSD Coefficient FIR Filters |
Tomohiro Sasahara, Kenji Suyama (Tokyo Denki Univ.) |
| (23) |
13:15-14:45 |
[Poster Presentation]
Sound Source Tracking via Two Microphones Using PSO with Variable Search Parameters |
Kenta Omiya, Masato Hirakawa, Kenji Suyama (Tokyo Denki Univ.) |
| (24) |
13:15-14:45 |
[Poster Presentation]
Target Sound Enhancement Based on Sound Source Distribution in Nonstationary Noise Environment |
Naoki Shinohara, Kenji Suyama (Tokyo Denki Univ.) |
| (25) |
13:15-14:45 |
[Poster Presentation]
Subjective Evaluation of Compensation Performance for the 2nd-order Nonlinear Distortion of Parametric Array Loudspeaker |
Yuta Hatano, Satoshi Kinoshita, Chuang Shi, Yoshinobu Kajikawa (Kansai Univ.) |
| (26) |
13:15-14:45 |
[Poster Presentation]
A Study on Compensation Ability of 3rd-order Nonlinear Distortions using Mirror Filter |
Kenta Iwai, Yoshinobu Kajikawa (Kansai Univ.) |
| (27) |
13:15-14:45 |
[Poster Presentation]
Noise Suppression by Modified Zero Phase Signal Analysis |
Akira Tanaka, Yuki Amma (Hokkaido Univ.), Arata Kawamura (Osaka Univ.) |
| (28) |
13:15-14:45 |
[Poster Presentation]
Space Diversity FM Receiver Using Real-Coefficient Constant Modulus Algorithm |
Osamu Hoshuyama, Akihiko Sugiyama (NEC) |
| (29) |
13:15-14:45 |
[Poster Presentation]
Voice Recognition using Signal Clustering Neural Network with Wavelet Transform Feature Extraction |
Bandhit Suksiri, Masahiro Fukumoto (KUT) |
| (30) |
13:15-14:45 |
[Poster Presentation]
A Study on Feedforward ANC System Using FPGA |
Takumi Harada, Yoshinobu Kajikawa (Kansai Univ.), Masaharu Nishimura (Tottori Univ.) |
| (31) |
13:15-14:45 |
[Poster Presentation]
A Control Method of Adaptive Filters Using Past Input Signals and Filter Coefficients |
Tomoahru Awano, Atsuyoshi Yano, Jun Ishii (Mitsubishi Electric Corp) |
| (32) |
13:15-14:45 |
[Poster Presentation]
Study on Personal Authentication Using Pinna Related Transfer Function. |
Tatsuya Miki, Masashi Nakamura (Kansai Univ.), Shunsuke Kita (TRI), Yoshinobu Kajikawa (Kansai Univ.) |
| (33) |
13:15-14:45 |
[Poster Presentation]
Evaluation on Variable Radiation Characteristics with Flexible Parametric Loudspeaker |
Shinya Komori, Daisuke Ikefuji, Takahiro Fukumori, Masato Nakayama, Takanobu Nishiura (Ritsumeikan Univ.) |
| |
14:45-15:00 |
Break ( 15 min. ) |
Mon, Mar 28 PM Special Invited Talk (Co-sponsored by IEEE Signal Processing Society Tokyo Joint, Kansai and Sendai Chapter)
15:00 - 17:00 |
| (34) |
15:00-16:00 |
[Special Invited Talk]
Progress in LPC-based Audio Coders
-- Reduction of quantization distortion by efficient representation of LPC envelope -- |
Takehiro Moriya, Ryosuke Sugiura, Yutaka Kamamoto, Hirokazu Kameoka, Noboru Harada (NTT) |
| (35) |
16:00-17:00 |
[Special Invited Talk]
Signal Processing for Robot Audition
-- A history of PaPeRo from a laptop PC to a single chip -- |
Akihiko Sugiyama (NEC) |
Tue, Mar 29 AM Poster2
09:00 - 10:30 |
| (36) |
09:00-10:30 |
[Poster Presentation]
A virtual concert system based on network auditory display system |
Shuhei Ito, Yukio Iwaya (Tohoku Gakuin Univ.), Makoto Otani (Kyoto Univ.), Takao Tsuchiya (Doshisha Univ.) |
| (37) |
09:00-10:30 |
[Poster Presentation]
Discrimination among synthesized sound fields different in upper-limit frequency of the spatial aliasing |
Shoya Yarimizu, Yukio Iwaya (Tohoku Gatuin Univ.), Makoto Otani (Kyoto Univ.), Takao Tsuchiya (Doshishya Univ.) |
| (38) |
09:00-10:30 |
[Poster Presentation]
Virtual Extrapolation of Microphone Array Length for Two Sound Sources Visualization |
Maureen, Yoichi Haneda (UEC) |
| (39) |
09:00-10:30 |
[Poster Presentation]
Direction of arrival estimation using the rise and fall period of the utterance covariance matrix in the case of reverberation |
Ryusuke Tanaka, Yoichi Haneda (UEC) |
| (40) |
09:00-10:30 |
[Poster Presentation]
Directivity control for a regular icosahedron loudspeaker based on the adaptive weighted least-squares method. |
Makoto Daikohara, Yoichi Haneda (UEC) |
| (41) |
09:00-10:30 |
[Poster Presentation]
Design of a directive loudspeaker array filter based on weighted least-squares method by controlling window function for desired sound pressure |
Koya Sato, Takayuki Seki, Yoihi Haneda (UEC) |
| (42) |
09:00-10:30 |
[Poster Presentation]
Numerical Analysis of Acoustic Field Propagation with Advection Using Method of Characteristics |
Akihiro Fukuda, Kan Okubo (Tokyo Met. Univ.), Takuya Oshima (Niigata Univ.), Takao Tsuchiya (Doshisha Univ.), Masashi Kanamori (JAXA) |
| (43) |
09:00-10:30 |
[Poster Presentation]
Instantaneous Frequency and Phase Angle Measurement Method by using Delay Devices and Pseudo Quadrature Signal Generation |
Suminori Nishie (PRIMO Sig.Lab.), Hayashi Ryotarou (Meitech) |
| (44) |
09:00-10:30 |
[Poster Presentation]
A Study on Sound Field Analysis for Parametric Array Loudspeaker |
Hiroaki Bessho, Chuang Shi, Yoshinobu Kajikawa (Kansai Univ.) |
| (45) |
09:00-10:30 |
[Poster Presentation]
Study on Realization of Design Support Method for Compact Acoustic Systems |
Hayato Takimoto, Yoshinobu Kajikawa (Kansai Univ.), Takashi Miyakura (HOSIDEN) |
| (46) |
09:00-10:30 |
[Poster Presentation]
Amplitude limiters based on phase optimization |
Akira Kakitani, Daisuke Saito, Yasuhiro Kosugi, Nobuaki Minematsu (UTokyo) |
| (47) |
09:00-10:30 |
[Poster Presentation]
An experimental study of designing context labels for infant-directed storytelling speech synthesis |
Kyota Hyakutake, Daisuke Saito, Nobuaki Minematsu (UTokyo) |
| (48) |
09:00-10:30 |
[Poster Presentation]
Quality improvement of HMM-based synthesized speech based on decomposition of naturalness and intelligibility using asymmetric bilinear model with non-negative matrix factorization |
Anh-Tuan Dinh, Masato Akagi (JAIST) |
| (49) |
09:00-10:30 |
[Poster Presentation]
Speaker verification using weight-adapted score fusion in noisy reverberant environments |
Ryosuke Nakanishi, Sayaka Shiota, Hitoshi Kiya (Tokyo Metropolitan Univ.) |
| (50) |
09:00-10:30 |
[Poster Presentation]
Majorisation-minimization based composite autoregressive system optimization with a glottal source model prior |
Lauri Juvela (Aalto Univ.), Hirokazu Kameoka (Tokyo Univ.), Junichi Yamagishi (NII) |
| (51) |
09:00-10:30 |
[Poster Presentation]
A Study on Feedforward ANC System for Infant Incubator |
Satoru Hase, Yoshinobu Kajikawa (Kansai Univ.), Cheng-Yuan Chang, Sen M. Kuo (CYCU) |
| (52) |
09:00-10:30 |
[Poster Presentation]
Examination of Acoustic Sensing Using Super-directivity Speaker and Super-resolution Signal Processing |
Yuya Asakura, Kan Okubo, Norio Tagawa (Tokyo Met. Univ.) |
| (53) |
09:00-10:30 |
[Poster Presentation]
An Effectiveness of Headrest CICO ANC System Using Virtual Microphone |
Satoshi Kinoshita (Kansai Univ.), Antonius Siswanto, Cheng-Yuan Chang, Sen M. Kuo (Chung Yuan Christian Univ.), Yoshinobu Kajikawa (Kansai Univ.) |
| (54) |
09:00-10:30 |
[Poster Presentation]
Pre-invese Type Active Noise Control with Power Scheduling |
Ryousuke Minagi, Kazushi Otsuki, Naoto Sasaoka, Yoshio Itoh (Tottori Univ.) |
| (55) |
09:00-10:30 |
[Poster Presentation]
A Study of Auditory Masking toward Discomfort Reduction of Railway Brake Sounds |
Sayaka Okayasu, Daisuke Ikefuji, Takahiro Fukumori, Masato Nakayama, Takanobu Nishiura (Ritsumeikan University) |
| (56) |
09:00-10:30 |
[Poster Presentation]
A Study of Indoor-environmental Sound Discrimination Based on Deep Neural Network with Mel-cepstrum |
Sakiko Mishima, Yukoh Wakabayashi, Takahiro Fukumori, Masato Nakayama, Takanobu Nishiura (Ritsumeikan University) |
| (57) |
09:00-10:30 |
[Poster Presentation]
Speech Enhancement Based on Phase Reconstruction Using Fundamental Frequency and a Priori SNR |
Yukoh Wakabayashi, Takahiro Fukumori, Masato Nakayama, Takanobu Nishiura, Yoichi Yamashita (Ritsumeikan Univ.) |
| (58) |
09:00-10:30 |
[Poster Presentation]
Camera motion compensation using the method for removing shadows and reflections
-- Application of motion compensation -- |
Yuki Hiyori, Yoshihiro Yamashita, Takao Nishitani, Kiyoshi Nishikawa, Toru Yamaguchi (TMU) |
| (59) |
09:00-10:30 |
[Poster Presentation]
Method for Removing Noise due to Magnetic Flux Trap in HTS-SQUID Magnetometers Based on Mean-Shift Clustering |
Takuma Tsuji, Yuta Katori, Kan Okubo (TMU), Nobunao Takeuchi (THU), Kiyoshi Nishikawa (TMU) |
| (60) |
09:00-10:30 |
[Poster Presentation]
Fast Computation of Similarity of Curves Based on B-Spline |
Yuuma Kubouchi, Akira Tanaka (Hokkaido Univ.) |
| (61) |
09:00-10:30 |
[Poster Presentation]
Sparse Kernel Regression Based on Nonparametric Bayesian Model |
Atsushi Kojima, Suguru Yasutomi, Toshihisa Tanaka (TUAT) |
| |
10:30-10:45 |
Break ( 15 min. ) |
Tue, Mar 29 AM SP1
10:45 - 12:15 |
| (62) |
10:45-11:10 |
Tensor-based Speech Representation and its Application to Identification of Languages and Speakers |
So Suzuki, Daisuke Saito, Nobuaki Minematsu (UTokyo) |
| (63) |
11:10-11:35 |
Voice liveness detection using phoneme information for speaker verification |
Sayaka Shiota (Tokyo Metropolitan Univ.), Fernando Villavicencio, Junichi Yamagishi, Nobutaka Ono, Isao Echizen (NII), Tomoko Matsui (ISM), Hitoshi Kiya (Tokyo Metropolitan Univ.) |
| (64) |
11:35-12:15 |
[Invited Talk]
An overview of the 2015 Jelinek workshop on speech and language technology |
Marc Delcroix (NTT) |
| |
12:15-13:15 |
Lunch Break ( 60 min. ) |
Tue, Mar 29 PM EA2
13:15 - 14:05 |
| (65) |
13:15-13:40 |
Effective basis learning for sound source separation by semi-supervised nonnegative matrix factorization |
Daichi Kitamura (SOKENDAI), Nobutaka Ono (NII/SOKENDAI), Hiroshi Saruwatari (UT), Yu Takahashi, Kazunobu Kondo (Yamaha) |
| (66) |
13:40-14:05 |
Investigation on Fast Learning of Neural Network Using by Quadratic Auxiliary Functions |
Nobutaka Ono (NII) |
| |
14:05-14:15 |
Break ( 10 min. ) |
Tue, Mar 29 PM SP2
14:15 - 15:05 |
| (67) |
14:15-14:40 |
Analysis of a fast fundamental frequency estimation method using recursive moving-average filters
-- As a method for making DIO even faster -- |
Ryunosuke Daido, Yuji Hisaminato (Yamaha Corp.) |
| (68) |
14:40-15:05 |
Product-of-Experts approach to integration of F0 generative process model to statistical F0 prediction for electrolaryngeal speech enhancement |
Kou Tanaka (NAIST), Hirokazu Kameoka (NTT), Tomoki Toda (The University of Nagoya/NAIST), Satoshi Nakamura (NAIST) |
| |
15:05-15:15 |
Break ( 10 min. ) |
Tue, Mar 29 PM SIP2
15:15 - 16:30 |
| (69) |
15:15-15:40 |
Method of disaggregating appliances from an aggregate current waveform on a power distribution board |
Fumihiko Ishiyama, Hiroshi Inoue, Yasunao Suzuki (NTT) |
| (70) |
15:40-16:05 |
Study of Feature in Emotion Recognition Using EEG during Music Listening |
Hiroki Itoga, Yoshikazu Washizawa (UEC) |
| (71) |
16:05-16:30 |
Popularity Analysis of "Yuru-chara" Using Images and Names |
Yuri Nakasato, Toshihisa Tanaka (TUAT) |
: 
-
u
s
c
i
