次世代ネットワークにおける超臨場感音響相互通信の実現 -Ultra-realistic acoustic interactive communication on next-generation Internet-

Special Interest Workshop

The Fourth Workshop of A3 Foresight Program

The 4th workshop was held with the following program.

Date: January 28-30, 2016
Workshop Venue: Seoul National University, Korea

January 28:
16:00-18:00 PI meeting
19:00-20:00 Welcome reception

January 29:
09:30-09:35 Opening remarks
09:35-10:55 Lecture session I

・Li WANG (Institute of Acoustics, Chinese Academy of Sciences, China)
Automatic scoring for English spoken question and answer
・Junhyeong PARK (Gwangju Institute of Science and Technology, Korea)
Multichannel speech reinforcement exploiting spatial information
・Gang TANG (Beijing Institute of Technology, China)
Speaking style recognition of pilots in flight
・Jiahe WEI, Takashi NOSE, Akinori ITO (Tohoku University, Japan)
A study on the speech rate and intelligibility of Japanese speech for non-native listener

・Taehoon KIM (Seoul National University, Korea)
Extraction of an acoustic biomarker for predicting the severity of obstructive sleep apnea
・Xuemin ZHAO (Institute of Acoustics, Chinese Academy of Sciences, China)
Grammar induction from spoken dialogue data
・Yukiko KAGEYAMA, Yuya CHIBA, Takashi NOSE, Akinori ITO (Tohoku University, Japan)
Evaluation of selection response for non-task-oriented dialogue using MMDAgent

・Chul Min LEE (Seoul National University, Korea)
DNN-based residual echo suppression
・Harunori KOIKE, Takashi NOSE, Takahiro SHINOZAKI, Akinori ITO (Tohoku University, Japan)
A study on speaker-independent voice conversion using spectral differential filter based on neural network
・Inyoung HWANG (Hanyang University, Korea)
A statistical model-based voice activity detection using multiple DNNs and noise awareness
・Koki HONGO, Takashi NOSE, Yuki SAITO, Shuhei YAMADA, Akinori ITO (Tohoku University, Japan)
A study on singing voice synthesis based on deep neural networks

・Jeunghun KIM (Seoul National University, Korea)
Spatial sound reproduction in virtual hall
・Virgilijus BRACIULIS, Jorge TREVINO, Cesar D. SALVADOR, Shuichi SAKAMOTO, Yo-iti SUZUKI (Tohoku University)
A statistical approach to source separation using ad-hoc microphone arrays robust to positioning errors
・Shukjae CHOI (Seoul National University, Korea)
Reverberation-robust acoustic indoor localization
・Jessada KARNJANA, Masashi UNOKI (Japan Advanced Institute of Science and Technology)
An audio watermarking scheme based on automatic parameterized singular-spectrum analysis using differential evolution