home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.speech
- Path: sparky!uunet!utcsri!newsflash.concordia.ca!IRO.UMontreal.CA!kovic.IRO.UMontreal.CA.IRO.UMontreal.CA!cholette
- From: cholette@IRO.UMontreal.CA (Martin Cholette)
- Subject: Re: Could S.Blaster recognize sounds??HELP
- Message-ID: <1992Nov15.203718.15388@IRO.UMontreal.CA>
- Sender: news@IRO.UMontreal.CA
- Reply-To: cholette@IRO.UMontreal.CA (Martin Cholette)
- Organization: Universite de Montreal
- References: <1992Nov10.154616.6281@gw.wmich.edu>
- Date: Sun, 15 Nov 1992 20:37:18 GMT
- Lines: 11
-
-
- The answer to your question is !!!! NO !!!! . What you are asking
- for is extremely complicated, the problem is with the word recognition
- part, it is not a simple lookup in a table to see if a word matches.
- The theory involved is incredibly complicated and boring, Fast Fourrier
- Transforms are involved, heuristic time warp technology may also be used...
- If you plan on doing this, you must be prepared to work on this FULL TIME
- for at least a year! Many PhD's work on this for years and still get nowhere!
-
- Martin Cholette.
-
-