|
Robot Audition from the viewpoint of Computational Auditory Scene Analysis| old_uid | 5306 |
|---|
| title | Robot Audition from the viewpoint of Computational Auditory Scene Analysis |
|---|
| start_date | 2008/09/29 |
|---|
| schedule | 14h-16h |
|---|
| online | no |
|---|
| summary | In this talk, I'd like to overview my research towards listening to several things at once.
First, I'll present three issues of robot audition, sound source localization, separation, and recognition of separated speech signals.
Second, I'll present the design of social behaviors of humanoid based on robot audition.
Third, I'll present two different kinds of sound source separation systems, geometric source separation with eight microphones, and independent component analysis with a pair of microphones. The separated sounds are recognized by missing feature theory based ASR. Missing feature masks are generated by estimating leak energy
between separated sounds.
I will also talk about our open source robot audition system called "HARK" (an old English for "listen") which was developed by Kyoto University and Honda Research Institute Japan Co., Inc.
My talk will be accompanied by several demonstration videos. |
|---|
| responsibles | Clady |
|---|
| |
|