Return-Path: Received: from rly-yc01.mail.aol.com (rly-yc01.mail.aol.com [172.18.205.144]) by air-yc02.mail.aol.com (v121.4) with ESMTP id MAILINYC24-1b547b80a2c36a; Sun, 17 Feb 2008 05:19:40 -0500 Received: from post.thorcom.com (post.thorcom.com [193.82.116.20]) by rly-yc01.mail.aol.com (v121.4) with ESMTP id MAILRELAYINYC17-1b547b80a2c36a; Sun, 17 Feb 2008 05:19:26 -0500 Received: from majordom by post.thorcom.com with local (Exim 4.14) id 1JQgbw-0001W0-BF for rs_out_1@blacksheep.org; Sun, 17 Feb 2008 10:19:04 +0000 Received: from [193.82.59.130] (helo=relay2.thorcom.net) by post.thorcom.com with esmtp (Exim 4.14) id 1JQgbv-0001Vr-SZ for rsgb_lf_group@blacksheep.org; Sun, 17 Feb 2008 10:19:03 +0000 Received: from smtp27.orange.fr ([80.12.242.95]) by relay2.thorcom.net with esmtp (Exim 4.63) (envelope-from ) id 1JQgbs-0002wz-0s for rsgb_lf_group@blacksheep.org; Sun, 17 Feb 2008 10:19:03 +0000 Received: from me-wanadoo.net (localhost [127.0.0.1]) by mwinf2712.orange.fr (SMTP Server) with ESMTP id CDFFC1C0009E for ; Sun, 17 Feb 2008 11:18:54 +0100 (CET) Received: from JR (Mix-Dijon-107-2-87.w193-248.abo.wanadoo.fr [193.248.1.87]) by mwinf2712.orange.fr (SMTP Server) with ESMTP id B95661C00097 for ; Sun, 17 Feb 2008 11:18:52 +0100 (CET) X-ME-UUID: 20080217101853759.B95661C00097@mwinf2712.orange.fr Message-ID: <200802171118500509.0A5C9E7E@smtp.wanadoo.fr> In-Reply-To: <007b01c8702f$e7ac1f10$0301a8c0@g3kev> References: <007b01c8702f$e7ac1f10$0301a8c0@g3kev> X-Mailer: Courier 3.50.00.09.1098 (http://www.rosecitysoftware.com) (P) Date: Sun, 17 Feb 2008 11:18:50 +0100 From: "John RABSON" To: rsgb_lf_group@blacksheep.org Mime-Version: 1.0 X-Spam-Score: 0.3 (/) X-Spam-Report: autolearn=disabled,RCVD_IN_NJABL_PROXY=0.327 Subject: Re: LF: CW Skimmer Content-Type: text/plain; charset="ISO-8859-1" Content-Transfer-Encoding: quoted-printable X-Spam-Checker-Version: SpamAssassin 2.63 (2004-01-11) on post.thorcom.com X-Spam-Level: X-Spam-Status: No, hits=0.0 required=5.0 tests=none autolearn=no version=2.63 X-SA-Exim-Scanned: Yes Sender: owner-rsgb_lf_group@blacksheep.org Precedence: bulk Reply-To: rsgb_lf_group@blacksheep.org X-Listname: rsgb_lf_group X-SA-Exim-Rcpt-To: rs_out_1@blacksheep.org X-SA-Exim-Scanned: No; SAEximRunCond expanded to false X-AOL-IP: 193.82.116.20 X-AOL-SCOLL-AUTHENTICATION: listenair ; SPF_helo : n X-AOL-SCOLL-AUTHENTICATION: listenair ; SPF_822_from : n On 16/02/2008 at 00:07 mal wrote: >Take the letter Z for instance sent badly spaced. It could be TD, MI, GE, T= TEE. A proficient cw operator would be able to identify the context in which= it was being sent and read it accordingly. Presently it could not be >read=20= by a machine. If you were doing machine based CW recognition for serious, you would start=20= by collecting data on how people mangle code. This is similar, though with=20= a much more limited language, to the data collection work that was done in o= rder to produce Speaker-Independent recognition of spoken digits for the tel= ephone service.=20 I expect you would find a number of common errors (equivalent to different a= ccents in spoken language), as for example a contester who calls NST when he= means TEST, and of course 5NN for a signal report*. Then there are the bug= key users who speed up their sending by taking the weights off to shorten t= he dots but do not make the corresponding adjustment in the manually-produce= d dashes. Once you have a sufficient quantity of data, you would be in a po= sition to analyse it and establish how many different "accent" you would hav= e to deal with. Do not expect to produce a system that is 100% accurate. The ear plus brain= doesn't provide that. John F5VLF *does anyone use short numerals nowadays?