From jspickes@etrademail.com Thu Jan 03 17:53:37 2002 Return-Path: X-Sender: jspickes@cc96364-a.hwrd1.md.home.com X-Apparently-To: lojban@yahoogroups.com Received: (EGP: mail-8_0_1_3); 4 Jan 2002 01:53:37 -0000 Received: (qmail 2740 invoked from network); 4 Jan 2002 01:53:36 -0000 Received: from unknown (216.115.97.167) by m4.grp.snv.yahoo.com with QMQP; 4 Jan 2002 01:53:36 -0000 Received: from unknown (HELO cc96364-a.hwrd1.md.home.com) (24.23.49.116) by mta1.grp.snv.yahoo.com with SMTP; 4 Jan 2002 01:53:35 -0000 Received: from jspickes by cc96364-a.hwrd1.md.home.com with local (Exim 3.32 #1 (Debian)) id 16MJWl-0007NY-00 for ; Thu, 03 Jan 2002 20:52:11 -0500 Date: Thu, 3 Jan 2002 20:52:06 -0500 To: lojban@yahoogroups.com Subject: Re: [lojban] Lojban Text to Speech Message-ID: <20020103205206.B23288@cc96364-a.hwrd1.md.home.com> Mail-Followup-To: lojban@yahoogroups.com References: Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.3.23i X-eGroups-From: jspickes@cc96364-a.hwrd1.md.home.com From: jspickes@etrademail.com Reply-To: jspickes@etrademail.com X-Yahoo-Group-Post: member; u=41916889 la tinkit. cusku di'e > > Could you paste a URL to the samples you're discussing? All I found was > > http://jcrossco.home.mindspring.com/dialog8k.wav, which is a computer > > croaking out unintelligible noises that I assume is Lojban. Speech synth > > has a way to go yet! > > > > Perhaps I should clarify my implicit question: did you think that, because > he is from the South, that he crafted the computerized lojban sample with > a Southern accent? I believe the dialog8k.wav you've discovered is the file to which I'm referring. Yes, I'll agree that it could stand some improvement, but I'm impressed with its intelligibility at this early stage. Even with my (extremely limited) lojban vocabulary, I was able to pick out parts of what it was saying. With regards to the accent, the methods that had been previously discussed required that someone record their lojban speech in order for the TTS software to imitate them. My assumption is that the TTS software in this case is constructing the speech from a sequence of sound bytes that someone recorded. It appears that the person who recorded these snippets had a notable southern accent. While this in no way diminishes the accomplishment, I did find it amusing. mu'omi'e djan