From jpi@uk.ac.bham.cs Fri Oct 23 10:08:22 1992 Path: cam-eng!uknet!news.cs.bham.ac.uk!fat-controller!jpi From: jpi@uk.ac.bham.cs (Jon Iles) Newsgroups: comp.speech Subject: Speech Synthesis Software - Summary Message-ID: Date: 22 Oct 92 17:57:37 GMT Sender: news@cs.bham.ac.uk Reply-To: jpi@uk.ac.bham.cs Followup-To: comp.speech Organization: University of Birmingham Lines: 69 Nntp-Posting-Host: fattie Hi, as promised, I'm summarising the details I was mailed after I made the following request... > >Just a quick question about software based speech synthesis products. >I'd be very interested to hear from anyone regarding the availability >of commercial / public domain / shareware software such as the Klatt >software based speech synthesizer. I hasten to add I'm mainly >interested in software to perform conversion from parameters to a >speech signal, rather than complete text to speech systems. > The response I got indicated that there is very little Public Domain or Shareware speech synthesis related software available for FTP. However, the ones that are available I've listed below... Text to phoneme program in /pub/linguist/phon.tar.Z from ftp.Hawaii.edu based (I think) on the Naval Research Lab's set of text to phoneme rules. Text to speech program in /pub/speak.tar.Z from wilma.cs.brown.edu - based on concatenation of pre-recorded speech segments - works on Sun Sparc's. The following are commercial systems that replies pointed out, I have included contacts where I was given names / addresses... MacIntalk (Mac) - formant based speech synthesis Narrator (Amiga) - formant based synthesis JSRU software - contact Dr. E.Lewis (eric.lewis@uk.ac.bristol) Klatt Software - contact... Dr. David Williams at Sensimetrics Corporation, 64 Sidney Street, Cambridge, MA 02139. Fax: (617) 225-0470; Tel: (617) 225-2442. Other suggestions were... Bliss by Dr. John Merus (Brown University) Mertus@browncog.bitnet CSRE by Dr. Terry Nearey (Alberta University) Nearey@nova.ling.ualberta.ca I haven't checked out much of the above-mentioned. I have snail-mailed Sensimetrics a few weeks ago, but no details forthcoming (anyone from Sensimetrics listening - mail me 'cos you've got a customer !). Apart from that, I hope this is useful. I'd like to see some more of this sort of info, perhaps added to the FAQ - could be useful ? Thanks to the following who mailed replies, apologies if I have incorrectly credited anyone, or omitted anyone. Ken Stevens (stevens@speech.mit.edu) Henry Rogers (rogers@epas.utoronto.ca) Gyger Markus (mgyger@itr.ch) Mark Huckvale (uclytmh@ucl.ac.uk) Joe Campbell (jpcampb@afterlife.ncsc.mil) Marty (marty@cs.utexas.edu) Terry Baxter (terry@stonyplain.cs.ualberta.ca) Cheers ! Jon From: jpi@uk.ac.bham.cs (Jon Iles) Newsgroups: comp.speech Subject: Re: Speech Synthesis Software - Summary Date: 23 Oct 92 07:55:12 GMT Reply-To: jpi@uk.ac.bham.cs Organization: University of Birmingham Nntp-Posting-Host: fattie Thanks to those who mailed me regarding phon.tar.Z (text to phoneme software) which I said could be found in Hawaii - I was wrong - the particular site I mentioned is no longer operational. Anyway, archie tells me that there is a copy of the relevant s/w at... shark.cse.fau.edu in /pub/src/phon.tar.Z Fingers crossed this will work :) Have fun ! Jon --- ========================================================================== School of Computer Science, | j.p.iles@uk.ac.bham.cs University of Birmingham, | Birmingham, B15 2TT. UK | From nik@tiuk.ti.com Wed Mar 2 07:26:32 1994 Newsgroups: comp.speech Path: pavo.csi.cam.ac.uk!doc.ic.ac.uk!warwick!zaphod.crihan.fr!jussieu.fr!math.ohio-state.edu!cs.utexas.edu!csc.ti.com!tilde.csc.ti.com!cauldron!ra.csc.ti.com!usenet From: nik@tiuk.ti.com Subject: "rsynth" text-to-speech code for Sun, linux, NeXT and SGI Message-ID: Sender: usenet@csc.ti.com Nntp-Posting-Host: pluto.tiuk.ti.com Organization: Texas Instruments Ltd. Date: Fri, 25 Feb 1994 12:42:30 GMT Lines: 29 I have made another release of my "rsynth" package. There are no major functional changes, but I have included drivers for linux, NeXT and SGI machines that have been contributed by a number of people. Thanks to: Rob Hooft. hooft@EMBL-Heidelberg.DE - Linux Axel Belinfante Axel.Belinfante@cs.utwente.nl - mods for WWW integration Ben Stuyts benstn@olivetti.nl - NeXT Frans Van Hoesel hoesel@chem.rug.nl - SGI Various other people who have sent me mail with suggestions. (If your favourite suggestion/enhancement has not made it please re-mail me I have lost one or two!) Only other change of note is that the infinite recusion problem when "spelling out" words WITHOUT the dictionary is fixed. rsynth is available via anonymous ftp from : svr-ftp.eng.cam.ac.uk /comp.speech/sources/rsynth-1.0.tar.Z or /comp.speech/sources/rsynth-1.0.tar.gz Please not that this is a private project and Texas Instruments is not responsible in any manner. Nick Ing-Simmons via nik@tiuk.ti.com or nicki@lobby.ti.com