Thu, Dec 12 AM
11:00 - 11:50 |
| (1) |
11:00-11:25 |
An improvement of applause detection precision on APRICOT system |
Kazuhiro Ouchi, Kazuhiko Kawahara (Kyushu Unv.), Yutaka Kamamoto, Takashi G. Sato (NTT), Akira Omoto (Kyushu Unv.), Takehiro Moriya (NTT) |
| (2) |
11:25-11:50 |
Signal Representation Based on Modulated Complex Sine Waves for Sound Mixing |
Takumi Wakabayashi, Kota Takahashi (UEC) |
| |
11:50-13:00 |
Break ( 70 min. ) |
Thu, Dec 12 PM
13:00 - 13:50 |
| (3) |
13:00-13:50 |
[Invited Talk]
Technical Listening Training
-- An acoustic education program for acoustic engineers at Kyushu University -- |
Kazuhiko Kawahara (Kyushu Univ.) |
| |
13:50-14:00 |
Break ( 10 min. ) |
Thu, Dec 12 PM
14:00 - 14:50 |
| (4) |
14:00-14:25 |
Removal of musical noise using deep learning without pre-training |
Takuya Fujimura, Ryoichi Miyazaki (NITTC) |
| (5) |
14:25-14:50 |
Performance improvement of speech enhancement network by multitask learning including noise information |
Haruki Tanaka (NITTC), Yosuke Sugiura, Nozomiko Yasui, Tetsuya Shimamura (Saitama Univ.), Ryoichi Miyazaki (NITTC) |
| |
14:50-15:00 |
Break ( 10 min. ) |
Thu, Dec 12 PM
15:00 - 16:15 |
| (6) |
15:00-15:25 |
Fundamental Study on Sound Source exploration method inside structure using DNN and CAE |
Shunsuke Kita (ORIST), Yoshinobu Kajikawa (Kansai Univ.) |
| (7) |
15:25-15:50 |
Performance evaluation of a non-linear beamformer with a small-scale microphone array |
Ryoutarou Oka, Mitunori Mizumachi (KIT) |
| (8) |
15:50-16:15 |
Experimental study of robustness to spatial information in spatial cepstrum |
Taiga Kawamura, Ryoichi Miyazaki (NITTC), Keisuke Imoto (Ritsumeikan Univ.) |
Fri, Dec 13 AM
10:30 - 11:45 |
| (9) |
10:30-10:55 |
Effect of speech conversion for power-saving playback on word intelligibility |
Tsukasa Nakashima (Kyutech), Mitsuhiro Nakagawara (Panasonic), Mizumachi Mitsunori (Kyutech) |
| (10) |
10:55-11:20 |
Detection of individuality of the Lombard effect in case of hearing colored noise |
Satoshi Ito, Ayane Kitazato, Yoichi Midorikawa, Masanori Akita (Oita Univ) |
| (11) |
11:20-11:45 |
Listening difficulty rating prediction model using STOI-type objective intelligibility index for outdoor public address speech |
Keita Noguchi, Yosuke Kobayashi, Jay Kishigami (Muroran-IT), Kiyohiro Kurisu (TOA) |
| |
11:45-13:00 |
Break ( 75 min. ) |
Fri, Dec 13 PM
13:00 - 14:15 |
| (12) |
13:00-13:25 |
Speaker-independent source separation with multichannel variational autoencoder |
Li Li (Univ. Tsukuba), Hirokazu Kameoka (NTT), Shota Inoue, Shoji Makino (Univ. Tsukuba) |
| (13) |
13:25-13:50 |
Rank-constrained spatial covariance matrix estimation based on multivariate complex generalized Gaussian distribution and its acceleration for blind speech extraction |
Yuki Kubo, Norihiro Takamune (UTokyo), Daichi Kitamura (NIT, Kagawa), Hiroshi Saruwatari (UTokyo) |
| (14) |
13:50-14:15 |
Robust sound source separation for whitening by using Mel-filter |
Takahiro Ushijima (Oita Univ.), Yuuki Tachioka (Denso IT Laboratory), Shingo Uenohara, Ken'ichi Furuya (Oita Univ.) |
| |
14:15-14:25 |
Break ( 10 min. ) |
Fri, Dec 13 PM
14:25 - 15:40 |
| (15) |
14:25-14:50 |
An investigation on the distance and reflection characteristics measurment method by analytic signal representation of impulse response |
Ryosuke Yamashita, Kazuya Osato, Manabu Fukushima (Nippon Bunri Univ.), Hirofumi Yanagawa (arsl) |
| (16) |
14:50-15:15 |
Effects of audio insulator having horn shape on vibration transmission characteristics |
Masahide Kita, Kiminobu Nishimura (Kindai) |
| (17) |
15:15-15:40 |
A study on method for stabilizing the noise reduction effect in the system applying the simultaneous equations method to active noise control |
Kensaku Fujii (Kodaway Lab.), Mitsuji Muneyasu (Kansai Univ.) |
: s
i
_
ipc
i
