[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: CASA problems and solutions


Pierre Divenyi wrote:

> To put my 10-cents worth of wisdom into the discussion of CASA vs. ASA,
> with due respect to DeLiang I must say that the most striking difference
> between ASA performed by humans and CASA is that the former works and the
> latter, with few notable exceptions, does not (or at least not well
> enough).

That's a pretty generous assessment. But just imagine what if CASA did work...
We are talking about something magnitudes more important than the Deep Blue
chess program.  Certainly the auditory system does great engineering, as far
as I am concerned, so eumulating ASA makes perfect engineering sense.

To me, the singular reason for slow-paced progress in CASA is the lack of
sustained research efforts; so few are actually systematically working on
this very important problem.  Perhaps it'll take a DARPA program to rectify
this situation.  But to those who are pondering about CASA, I'll say from my
own experience that it is a great problem waiting to be solved, a problem no
less significant or interesting than visual scene analysis.


Dr. DeLiang Wang
Department of Computer and Information Science
The Ohio State University
2015 Neil Ave.
Columbus, OH 43210-1277, U.S.A.

Email: dwang@cis.ohio-state.edu
Phone: 614-292-6827 (OFFICE); 614-292-7402 (LAB)
Fax: 614-292-2911
URL: http://www.cis.ohio-state.edu/~dwang