
Special Interest Workshop
- The Third Workshop of A3 Foresight Program "Sound and multimedia representations in the Internet era"
- ・Jorge TREVINO (Tohoku University)
Stereo encoding of spatial sound information for ultra-realistic internet broadcasts -
・Shuichi Sakamoto, Arif Wicaksono, Cesar Salvador, Jorge Trevino and Yôiti Suzuki (Tohoku University)
Compression method of spherical microphone array signals -
・Yukio Iwaya, Shoya Yarimizu, Makoto Otani, Takao Tsuchiya (Tohoku Gakuin University)
System evaluation of cloud auditory display in the Internet between China and Japan -
・Chengxiang Yin, Xiang Xie (Beijing Institute of Technology)
Advertising system based on cloud computing and audio watermarking - ・Yuki IGARASHI, Takashi NOSE, Yusuke YAMADA (Tohoku University)
Speaker-Adapted Realtime Talking Avatar on the Internet Using Kinect and Voice Conversion -
・Yuki SAITO, Takashi NOSE, Takahiro SHINOZAKI, Akinori ITO (Tohoku University)
Conversion of Speaker's Face Image Using PCA and Animation Unit for Video Chatting -
・Jeongsoo Park (Seoul National University)
Harmonic/Percussive Sound Separation Using Non-negative Matrix Factorization based on Anisotripic Characteristics in Spectrogram -
・Dooyong Sung (Seoul National University)
Effects of onset asynchrony on loudness discrimination of concurrent pure tones -
・Kisoo Kwon (Seoul National University)
Discriminative Bases Using Cross-Reconstruction Error with Application to the Target Source Separation -
・Anhao Xing (Institute of Acoustics, Chinese Academy of Sciences)
Redundancy removing on deep neural networks -
・Mengzhe Chen (Institute of Acoustics, Chinese Academy of Sciences)
Improved deep neural networks based on Correlation-Generated Targets for Mandarin LVCSR systems -
・Joun Yeop Lee (Seoul National University)
Relevance vector regression based speaker adaptation for HMM-based expressive TTS -
・Yongwei Li, Yasuhiro Hamada, Masato Akagi (JAIST)
Analysis of glottal source waves for emotional speech using ARX-LF model
June 3-4, 2015, Shiinoki Cultural Complex, Ishikawa Prefecture, Japan


The 3rd workshop was held with the following program.
Date: June 3-4, 2015
Workshop Venue: Shiinoki Cultural Complex, Ishikawa Prefecture, Japan
June 3rd: Special Sessions
19:00-21:00 PI meeting
19:00-20:30 Student meeting session ~Sound and multimedia representations in the Internet era~
June 4th: Special Interest Workshop
9:00-10:40 Session I: Multimedia information exchange over the network
10:40-11:00 Coffee break
11:00-11:50 Session II: Technologies for enhanced communications
11:50-13:30 Lunch
13:30-15:10 Session III: Machine learning and signal processing
15:10-15:30 Coffee break
15:30-16:45 Session IV: Speech processing