Seminar Program
- The 6th seminar of A3 foresight program "Ultra-realistic Acoustic Interactive Communication on Next-generation Internet"
February 23-24, 2014, Ishikawa, Japan
Date: February 23-24, 2014,
Seminar Venue: Ishikawa, Japan
Feb. 23 (Sunday)
10:40-12:00
Session 1-1
• Yongwei Li & Masato Akagi (JAIST, Japan)
Analysis of emotional speech based on ARX-LF model for emotional speech conversion
• Yuxuan Du & Masato Akagi (JAIST, Japan)
A study on Speech Recognition in noise conditions using non-negative matrix factorization
• Keisuke Kobayashi, Daisuke Morikawa & Masato Akagi (JAIST, Japan)
Study on Analyzing Individuality of Piano Sounds Using Non-negative Matrix Factorization
• Cesar D. Salvador, Shuichi Sakamoto, Jorge Trevino & Yôiti Suzuki(Tohoku University, Japan)
Editing distance information in binaural renderings of far field recordings
13:00-14:00
Session 1-2
• Kisoo Kwon (Seoul National University, Korea)
NMF-based speech enhancement using bases update.
• Hoon Heo (Seoul National University, Korea)
Transcription of vocal melodies using harmonic structure regularity.
• Bong-Ki Lee(Seoul National University, Korea)
An Enhanced Muting Method in Packet Loss Concealment of ITU-T G.722 Using an Sigmoid Function
14:15-15:15
Session 1-3
• Yanmeng Guo (Chinese Academy of Sciences, Chaina)
Acoustic Scene Aware Dereverberation Using 2-channel Spectral Enhancement for REVERB Challenge.
• Ta Li (Chinese Academy of Sciences, Chaina)
Improved Mandarin Spoken Term Detection by Using Deep Neural Network for Keyword Verification.
15:30-16:30
Session 1-4
• Elbarougy Reda Elsaid & Masato Akagi (JAIST, Japan)
A study on constructing an automatic speech emotion recognition system based on a three-layer model for human perception
• Jorge Trevino (Tohoku University, Japan), Takuma Okamoto (NICT, Japan), Shoichi Koyama (NTT Media Laboratory, Japan), Yukio Iwaya (Tohoku Gakuin University, Japan), Shuichi Sakamoto & Yôiti Suzuki (Tohoku University, Japan)
Sound field recording and reproduction: an overview of present and upcoming technologies
16:45-18:00 Student meeting Session
20:00-22:30 Special (PI meeting) Session
Feb. 24 (Monday)
10:00-11:00
Session 2-1
• Minoru Otake, Takeshi Saito & Masato Miyoshi (Kanazawa University, Japan)
Changes in acoustic characteristics of native Mikawa-ben living in KANAZAWA
• Yasukazu Teramura, Takeshi Saito & Masato Miyoshi (Kanazawa University, Japan)
High quality operatic singing synthesis by controlling acoustic features unique to operatic singing voices
• Hiroshi Nakagawa & Masato Akagi (JAIST, Japan)
Study of Recommendation System Based on Acoustic Features
11:15-12:15
Session 2-2
• Kingo Minami, Takeshi Saito & Masato Miyoshi (Kanazawa University, Japan)
Binaural sound reproduction using the amplitude control of adjacent virtual loudspeakers
• Hiroaki Kurabayashi, Makoto Otani, Masami Hashimoto, & Mizue Kayama (Shinshu University, Japan)
Development and evaluation of dynamic transaural reproduction system
• Yoshiki Sato, Shuichi Sakamoto, Jorge Trevino & Yôiti Suzuki (Tohoku University, Japan)
A method to apply listener’s head rotation to 3D sound-space representation by the SENZI system.
13:15-14:15
Session 2-3
• Masaru Ando, Daisuke Morikawa & Masashi Unoki (JAIST, Japan)
Study on DOA estimation method based on human ability of sound localization
• Kohei Yamazaki, Makoto Otani (Shinshu University, Japan), Masahiro Toyoda (Kansai University, Japan), Masami Hashimoto, & Mizue Kayama (Shinshu University, Japan)
Perception of sound image size in anechoic environment: Effects of frequency bandwidth
• Yuji Kondo, Wataru Teramoto (Muroran Institute of Technology, Japan), Maori Kobayashi (Meiji University, Japan), Makoto Otani (Shinshu University, Japan)
Auditory-somatosensory interactions in auditory distance perception
14:30-15:30
Session 2-4
• Naoya Suzuki, Wataru Teramoto (Muroran Institute of Technology, Japan)
Influence of remote partner's movements on a sense of being together in a shared virtual environment
• Hiroyuki Yagyu, Shuichi Sakamoto, Emi Takahashi, Tomoko Ohtani & Yôiti Suzuki (Tohoku University, Japan)
Temporal characteristics of perceived reality with multimodal media
• Emi Takahashi. Shuichi Sakamoto, Yôiti Suzuki & Jiro Gyoba (Tohoku University, Japan)
Effects of body vibration characteristics on the perceived reality in 3D multi-modal contents
15:45-16:45
Session 2-5
• Gen Hasegawa, Shuichi Sakamoto, Toru Abe, Tomoko Ohtani, Yôiti Suzuki & Tetsuro Kawase (Tohoku University, Japan)
The study on the contribution of the detailed parts around talker's mouth for speech intelligibility
• Akikazu Miyazaki & Masashi Unoki (JAIST, Japan)
Study on Blind Method of Estimating Speech Transmission Index from Noisy Reverberant Speech Signals
• Yasutaka Nishino, Ryota Miyauchi & Masashi Unoki (JAIST, Japan)
Study on redundancy contained in temporal amplitude envelope of Japanese speech
