Tue, Mar 1 AM 09:20 - 11:20 |
(1) EA |
09:20-11:20 |
[Poster Presentation]
Methods applied to active sinusoidal noise control and their merits and demerits |
Kensaku Fujii (Kodaway Lab.), Mitsuji Muneyasu (Kansai Univ.), Yushifumi Chisaki (CIT) |
(2) EA |
09:20-11:20 |
[Poster Presentation]
Direction-of-Arrival Estimation of Wideband Sound field based on Microphone Array Signals at Two Time Points |
Takahiro Iwami, Ken-ichi Sawai, Akira Omoto (Kyushu Univ.) |
(3) EA |
09:20-11:20 |
[Poster Presentation]
Amplitude modulation on high frequency noise induced by non-stationary audio system and its effect in audible range |
Masahide Kita, Shinichi Miyamoto, Yukiyasu Okamura, Kiminobu Nishimura (Kindai Univ.) |
(4) EA |
09:20-11:20 |
[Poster Presentation]
A Study on BoSC Recording Using a Small Rigid Sphere Microphone Array
-- Evaluation of prototype system of a small rigid sphere microphone array -- |
Shusei Takayama, Shiro Ise (TDU) |
(5) EA |
09:20-11:20 |
[Poster Presentation]
Computational Reduction of Sound Field Synthesis by Approximating Source Trajectory |
Kentaro Matsui, Yo Sasaki (NHK) |
(6) SIP |
09:20-11:20 |
[Poster Presentation]
A Locally Constrained Sampling Strategy for Generalized Graph Signal Sampling |
Kazuki Asakura, Shunsuke Ono (Tokyo Tech) |
(7) SIP |
09:20-11:20 |
[Poster Presentation]
Hyperspectral Image Denoising by Graph Spatio-Spectral Total Variation Minimization |
Shingo Takemoto, Kazuki Naganuma, Shunsuke Ono (Tokyo Tech) |
(8) SIP |
09:20-11:20 |
[Poster Presentation]
Robust Hyperspectral Anomaly Detection via Component Decomposition Based on Convex Optimization |
Koyo Sato, Shunsuke Ono (Tokyo Tech) |
|
11:20-12:20 |
Break ( 60 min. ) |
Tue, Mar 1 PM 12:20 - 13:35 |
(9) SP |
12:20-12:45 |
Training Algorithm for Multispeaker Text-To-Speech Synthesis Considering Adversarial Regularizer |
Yusuke Nakai, Kenta Udagawa, Yuki Saito, Hiroshi Saruwatari (UTokyo) |
(10) SP |
12:45-13:10 |
Incorporating Acoustic and Textual Information for Language Modeling in Code-switching Speech Recognition |
Roland Hartanto, Kuniaki Uto, Koichi Shinoda (TokyoTech) |
(11) SP |
13:10-13:35 |
The upper limit of subjective intelligibility score of speech enhancement using IRM
-- comparison between laboratory and crowdsourcing experiments -- |
Ayako Yamamoto, Toshio Irino (Wakayama Univ.), Shoko Araki, Kenichi Arai, Atsunori Ogawa, Keisuke Kinoshita, Tomohiro Nakatani (NTT) |
|
13:35-13:45 |
Break ( 10 min. ) |
Tue, Mar 1 PM 13:45 - 14:10 |
|
- |
|
|
14:10-14:20 |
Break ( 10 min. ) |
Tue, Mar 1 PM 14:20 - 15:35 |
(12) SIP |
14:20-14:45 |
Fast Distortion Pedal Modeling with Fine-Tuning |
Haruki Shoji, Kento Yoshimoto, Daiki Saka, Hiroki Kuroda, Daichi Kitahara, Kenichiro Tanaka, Akira Hirabayashi (Ritsumeikan Univ.) |
(13) EA |
14:45-15:10 |
Target speaker extraction based on conditional variational autoencoder and directional information in underdetermined condition |
Rui Wang, Li Li, Tomoki Toda (Nagoya Univ) |
(14) EA |
15:10-15:35 |
Prototyping acoustical system measurement tool using music and other auditory contents |
Hideki Kawahara (Wakayama Univ.), Kohei Yatabe (Waseda Univ.), Ken-Ichi Sakakibara (Health Science Univ. Hokkaido), Mitsunori Mizumachi (Kyushu Inst Tech.), Tatsuya Kitamura (Konan Univ.), Hideki Banno (Meijo Univ.) |
|
15:35-15:45 |
Break ( 10 min. ) |
Tue, Mar 1 PM 15:45 - 16:35 |
(15) |
15:45-16:10 |
|
(16) |
16:10-16:35 |
|
|
16:35-16:45 |
Break ( 10 min. ) |
Tue, Mar 1 PM 16:45 - 17:35 |
(17) |
16:45-17:35 |
Speech Communication Systems beyond Acoustics
Tanja Schultz (University of Bremen) |
Wed, Mar 2 AM 09:20 - 10:10 |
(18) |
09:20-10:10 |
Be robust against outlier, and be stable under high-power Gaussian noise simultaneously
Masahiro Yukawa (Keio University) |
|
10:10-10:20 |
Break ( 10 min. ) |
Wed, Mar 2 AM 10:20 - 12:25 |
(19) SP |
10:20-10:45 |
A Study on Hybrid RNN-T/Attention-based Streaming ASR with Triggered Chunkwise Attention and Dual Internal Language Model Integration |
Takafumi Moriya, Takanori Ashihara, Atsushi Ando, Hiroshi Sato, Tomohiro Tanaka, Kohei Matsuura, Ryo Masumura, Marc Delcroix (NTT), Takahiro Shinozaki (Tokyo Tech) |
(20) SP |
10:45-11:10 |
Evaluation of sentence-level generation in Japanese dialect speech synthesis using accent latent variables |
Kazuya Yufune, Tomoki Koriyama, Shinnosuke Takamichi, Hiroshi Saruwatari (UTokyo) |
(21) SP |
11:10-11:35 |
Study of natural singing-voice synthesis for backing vocals based on DNN |
Tomohiro Kioka, Masanobu Abe, Sunao Hara (Okayama Univ.) |
(22) SP |
11:35-12:00 |
Study of Method for Improving Speech Intelligibility in Glossectomy Patients by Knowledge Distillation via Lip Features |
Kazushi Takashima, Masanobu Abe, Sunao Hara (Okayama Univ.) |
(23) SP |
12:00-12:25 |
Evaluating the robustness of signal processing-based pseudonymization using parameter optimization against inversion attack. |
Hiroto Kai (Tokyo Metro. Univ.), Shinnosuke Takamichi (The Univ. of Tokyo), Sayaka Shiota, Hitoshi Kiya (Tokyo Metro. Univ.) |
|
12:25-13:25 |
Break ( 60 min. ) |
Wed, Mar 2 PM 13:25 - 15:25 |
(24) EA |
13:25-15:25 |
[Poster Presentation]
Comparison of Noise Reduction and Robustness for Virtual Sensing Methods in ANC Systems |
Shota Toyooka, Yoshinobu Kajikawa (Kansai Univ.) |
(25) EA |
13:25-15:25 |
[Poster Presentation]
Filtered-X LMS algorithm based on individual interpolation of primary and secondary sound fields for spatial active noise control |
Kazuyuki Arikawa, Shoichi Koyama, Hiroshi Saruwatari (The Univ. of Tokyo) |
(26) EA |
13:25-15:25 |
[Poster Presentation]
Sound Field Estimation from Small Number of Observations by Deep Learning with Difference-Approximation-Based Helmholtz-Equation Loss Function |
Kazuhide Shigemi, Shoichi Koyama, TomohikoNakamura, Hiroshi Saruwatari (UTokyo) |
(27) EA |
13:25-15:25 |
[Poster Presentation]
Multi-channel missing signals recovery using autoencoder for acoustic scene classification |
Yuki Shiroma, Yuma Kinoshita (Tokyo Metro. Univ.), Keisuke Imoto (Doshisha Univ.), Sayaka Shiota, Nobutaka Ono, Hitoshi Kiya (Tokyo Metro. Univ.) |
(28) SIP |
13:25-15:25 |
[Poster Presentation]
Transformer-based Text Decoding using Electrocorticography |
Shuji Komeiji, Kai Shigemi (TUAT), Takumi Mitsuhashi, Yasushi Iimura, Hiroharu Suzuki, Hidenori Sugano (Juntendo Univ.), Koichi Shinoda (Tokyo Tech), Toshihisa Tanaka (TUAT) |
(29) SIP |
13:25-15:25 |
[Poster Presentation]
Simultaneous control of multiple ANC systems using a common microphone |
Ryosuke Okajima, Yoshinobu Kajikawa (Kansai Univ.), Kohei Oto (Nitto Denko) |
(30) SIP |
13:25-15:25 |
[Poster Presentation]
Verification of the Effectiveness of ANC System Using FPGA in Hearable Devices |
Aoi Yoshikawa, Yoshinobu Kajikawa (Kansai Univ.) |
(31) |
13:25-15:25 |
|
(32) |
13:25-15:25 |
|
|
15:25-15:35 |
Break ( 10 min. ) |
Wed, Mar 2 PM 15:35 - 17:35 |
(33) EA |
15:35-17:35 |
[Poster Presentation]
Interpolation of head-related transfer function from small amount of observation data using deep learning based on spherical wavefunction expansion |
Yuki Ito, Tomohiko Nakamura, Shoichi Koyama, Hiroshi Saruwatari (UTokyo) |
(34) SIP |
15:35-17:35 |
[Poster Presentation]
Suppression of alpha power in the prediction of familiar melodies |
Shuma Ito, Toshihisa Tanaka (TUAT) |
(35) SIP |
15:35-17:35 |
[Poster Presentation]
Detection of individual beats from EEG during rhythm imagination |
Naoki Yoshimura, Toshihisa Tanaka (TUAT) |
(36) SIP |
15:35-17:35 |
[Poster Presentation]
Adaptive audio correction for multiway systems based on FxLMS algorithms |
Sota Oka, Toshihisa Tanaka (TAT) |
(37) SIP |
15:35-17:35 |
[Poster Presentation]
Effective Features for Detecting Abnormal Braking from Electroencephalogram and Electrocardiogram during Automatic Driving |
Erika Sekiguchi, Toshihisa Tanaka (TUAT), Ken Kubota (JATCO Engineering), Shun Nakamura (CorLab), Kenichi Makita (JATCO) |
(38) SIP |
15:35-17:35 |
[Poster Presentation]
Selective attention to music inducing neural entrainment variation and alpha-band spatial modulation |
Kana Mizokuchi, Toshihisa Tanaka (TUAT), Takashi G. Sato, Yoshifumi Shiraki (NTT) |
(39) SIP |
15:35-17:35 |
[Poster Presentation]
Epileptic Seizure Detection Using Active Learning with Riemannian Manifold |
Toshiki Orihara, Toshihisa Tanaka (TUAT) |
(40) SP |
15:35-17:35 |
[Poster Presentation]
A study of shout detection for clipped speech |
Taito Ishida, Kazuhiro Matsuda, Takahiro Fukumori, Yoichi Yamashita (Ritsumeikan Univ.) |
(41) |
15:35-17:35 |
|