Sponsored by JST CREST "Human-Harmonized Information Technology"
Co-sponsored by IEEE SPS Japan Chapter, Kansai Chapter and IEEE Kansai Section

The symposium features invited talks on frontier topics in speech, music, and signal processing. Sessions are organized by principal investigators of four different CREST projects together with IEEE SPS DL program.

The symposium is free of charge and prior registration is not required.

Photos of the symposium is now available HERE

April 1 (Sunday) DAY1: Music and User-Generated Content

13:00-15:00 Session 1 organized by Tokuda's project

Steve Renals (University of Edinburgh)
Natural Speech Technology
Alan Black (Carnegie Mellon University)
Making Computers Really Talk like People
Keiichi Tokuda, Akinobu Lee, Daisuke Yamamoto (Nagoya Institute of Technology), Junichi Ymagishi (University of Edinburgh)
Spoken dialogue system framework based on user-generated content
Coffee Break

15:30-17:30 Session 2 organized by Goto's project

Mark D. Plumbley (Queen Mary University of London)
Making Sense of Sound and Music
Meinard Mueller (Saarland University and MPI Informatik)
Informed Feature Representations for Music and Motion
Masataka Goto (AIST)
Music Technologies for Enhancing Music Appreciation and Creation

April 2 (Monday) DAY2: Human Behavior and Interaction

Coffee Break / Demonstration

15:30-16:30 Session 5 IEEE SPS Distinguished Lecturer Program

Tulay Adali (University of Maryland, Baltimore County)
ICA and IVA: Theory, Connections, and Applications

16:30-17:15 Session 6 organized by IEEE Kansai Section

Mike Schuster (Google)
Voice Search at Google
Attendees: 132 (students: 49, IEEE members: 70, CREST project members: 52)