English / Japanese

RYU, Takeda


Our goal is to achieve a speech interacton between human and robot(system) at anywhere and any situations.
The sound source separation technique is very important technique for it
because it can separate many sources and robot only recognize the proper separated sound source.
Now, I focus on the Independent Component Analysis (ICA) as a sound source separation method.
Since ICA have few assumptions about sound source,
it is suitable for robot audition or hands-free automatic speech recognition.
The main problems are there are many noises compared with the Spoken dialogue system
which requires a head-set microphone (it captures almost no noises).
Our target problems
My interests Blind Source Separation Recognition of 3 simultaneous speakers Experiment about frog
Now, I am trying to realize BSS, BD, and EC using Independent Component Analysis (ICA) framework.



Copyright (C) 2009-2010 Ryu Takeda All Rights Reserved.