ÿþ<HTML> <HEAD> <TITLE>Gnuspeech links and material main page</TITLE> </HEAD> <BODY> <A NAME="top"> <SCRIPT LANGUAGE="JavaScript"> <!-- if (top == self) self.location.href = "gnuspeech-index.htm"; // --> </SCRIPT> <CENTER> <A HREF="http://www.gnu.org/" TARGET="_blank"><IMG SRC="../gnu-head-sm.jpg" </A> </CENTER> <HR> <CENTER> <H2> Links, manuals and papers relevant to Gnuspeech</H2> <P> <FONT COLOR="red">(Those not on-line&#8212;indicated by links&#8212;may be available as hard copy, <A HREF="mailto:hill@cpsc.ucalgary.ca">by request)</A> </P></FONT> </CENTER> <HR> <H3>Sample sounds from Gnuspeech</H3> <H4>Male-Female-Child &#8220;Hello&#8221;synthesis comparison (sound files all ~3 MB)<BR><SMALL> (Composed by Leonard Manzara as a demonstration)</SMALL></H4> <CENTER> <TABLE BORDER=2> <TH> <TR> <TD><A HREF="../helloComparison/helloComparison.aiff" TARGET="_blank">.aiff file</A><BR> <TD><A HREF="../helloComparison/helloComparison.au" TARGET="_blank">.au file</A><BR> <TD><A HREF="../helloComparison/helloComparison.snd" TARGET="_blank">.snd file</A><BR> <TD><A HREF="../helloComparison/helloComparison.wav" TARGET="_blank">.wav file</A><BR> </TABLE> </CENTER> <H4>Additional examples illustrating full articulatory text-to-speech synthesis for male voice (examples chosen for interest rather than flattery) <CENTER> <TABLE BORDER=2> <TH> <TR> <TH><A HREF="../extra-synthesis-examples/pat-a-pan.html" TARGET="_blank">Pat-a-pan</A> <TH><A HREF="../extra-synthesis-examples/lumberjack.html" TARGET="_blank">Lumberjack</A> <TH><A HREF="../extra-synthesis-examples/the-chaos.html" TARGET="_blank">The Chaos</A> </TABLE> </CENTER> <HR> <H3>Gnuspeech links</H3> <UL> <LI><B>Gnuspeech project savannah site</B> <A HREF="http://savannah.gnu.org/projects/gnuspeech" TARGET="_blank">Gnuspeech project web site</A> <HR> <LI><B>Gnuspeech project overview</B> <A HREF="http://www.gnu.org/software/gnuspeech" TARGET="_blank">Gnuspeech overview</A> </UL> <HR> <H3>Papers and manuals relevant to Gnuspeech</H3> <UL> <LI><B>AVIOS &#8216;95 system theory paper</B> <A HREF = "../papers/avios95/index.htm" TARGET="new2">HILL, D.R., MANZARA, L. & TAUBE-SCHOCK, C-R. (1995) Real-time articulatory speech-synthesis-by-rules. <I>Proc. AVIOS '95 14th Annual International Voice Technologies Conf</I>, San Jose, 12-14 September 1995, 27-44</A> <HR> <LI><B>Monet manual</B> <A HREF = "../papers/monman/index.html" TARGET="new2">HILL DR (1993,2004) MONET speech synthesis editing system manual (TextToSpeech Kit tool).</A> On-line manual relevant to the real-time articulatory-synthesis-based text-to-speech system described in <A HREF = "../papers/avios95/index.htm" TARGET="new2"> the AVIOS 95 paper: "Real-time articulatory speech-synthesis-by-rules"</A> <HR> <LI><B>Synthesizer manual</B> <A HREF = "../papers/synthesizer/index.html" TARGET="new2">HILL DR (2006) Manual for the Synthesizer application -- part of the GnuSpeech text-to-speech toolkit</A> On-line manual relevant to the real-time articulatory-synthesis-based text-to-speech system described in <A HREF = "../papers/avios95/index.htm" TARGET="new2"> the AVIOS 95 paper: "Real-time articulatory speech-synthesis-by-rules"</A> <HR> <LI><B>Pronunciation guide</B> <A HREF = "../papers/pronguid.htm" TARGET="new2">HILL DR, MANZARA L & C-R SCHOCK (1993, 2003) Pronunciation guide for TextToSpeech kit</A> Pronunciation guide for Webster's, Trillium and IPA phonetic transcriptions. <HR> <LI><B>Conceptionary for speech and hearing</B> <A HREF = "../papers/conc/index.htm" TARGET="new2"> HILL DR (2001) A conceptionary for speech and hearing in the context of machines and experimentation</A> (This document is designed as an educational and reference tool). <HR> <LI><B>Detailed information on the facilities in Gnuspeech</B> <A HREF = "../papers/Developer_TextToSpeech_Manual.pdf" TARGET="new2">HILL DR, MANZARA L & C-R SCHOCK (1995) Manual for the original NeXT Developer TextToSpeech kit</A> The manual supplied for developers who wished to use the TextToSpeech Kit in their software offerings. A useful explanation of the facilities and how to use them as a <I>developer</I>&#8212;as opposed to the free-standing services offered as an extension to the operating system. Relevant to understanding the ported versions. <HR> <LI><B>Models for rhythm and intonation</B> <A HREF = "../papers/icslp92-rhythm-n-intonation.pdf" TARGET="new1">HILL, D.R., SCHOCK, C-R & MANZARA, L. (1992) Unrestricted text-to-speech revisited: rhythm and intonation. <I>Proc. 2nd. Int. Conf. on Spoken Language Processing</I>, Banff, Alberta, Canada, October 12th.-16th., 1219-1222</A> (This paper just barely predates the articulatory synthesis system&#8212;targetting the earlier formant-synthesizer-based system&#8212;but the account of our rhythm and intonation work is relevant to the articulatory system.) <HR> <LI><B>Models for rhythm and intonation</B> HILL, D.R. (1975b) Computer models for synthesising British English rhythm and intonation. <I>Proc. 8th. Int. Cong. of Phonetic Sciences</I>, Leeds, UK, Aug 17-23, paper 129 (This is an early paper as the rhythm and intonation work really got under way.) <HR> <LI><B>Initial paper on investigation of isochrony in rhythm</B> <A HREF = "../papers/stat-app-isoch-79.pdf" TARGET="new1"> HILL, D.R., JASSEM, W. & WITTEN, I.H. (1979) A statistical approach to the problem of isochrony in spoken British English. <I>Current Issues in Linguistic Theory</I> <B>9</B> (eds. H. & P. Hollien), 285-294, Amsterdam: John Benjamins B.V. </A> (An initial interpretation of our major rhythm study of British English rhythm.) <HR> <LI><B>Investigation of isochrony in rhythm</B> <A HREF = "../papers/isochrony-in-english-speech.pdf" TARGET="new2">JASSEM, W., HILL, D.R. & WITTEN, I.H. (1984) Isochrony in English speech: its statistical validity and linguistic relevance. <I>Pattern, Process and Function in Discourse Phonology</I> (collection ed. Davydd Gibbon), Berlin: de Gruyter, 203-225</A> (The comprhensive paper digesting the results of our major study of British English rhythm.) <HR> <LI><B>British English rhythm data and statistical analysis</B> HILL, D.R. (1977) Some results from a preliminary study of British English speech rhythm. <I>94th. Meeting of the Acoustical Society of America</I>, Miami, Dec 12-16 (Full text available as U of Calgary Computer Science Dept. Report 78/26/5) (The original data and statistical analysis from our major study of British English rhythm.) <HR> <!-- <LI>HILL, D.R. (1978) A program structure for event-based speech synthesis by rules within a flexible segmental framework. <I>Int. J. Man-Machine Studies</I> <B>10</B> (3), 285-294, May (J) <LI>HILL, D.R. & REID, N.A. (1977a) An experiment on the perception of intonational features. <I>Int. J. Man-Machine Studies</I> <B>9</B> (2), 337-347 (J) <LI>HILL, D.R. (1975a) Avoiding segmentation in speech analysis: problems and benefits. <I>Proc. 8th. Int. Cong. of Phonetic Sciences</I>, Leeds, UK, Aug 17-23, paper 128 (C) <LI>HILL, D.R., JASSEM, W. & WITTEN, I.H. (1979) A statistical approach to the problem of isochrony in spoken British English. <I>Int. Phonetics Society Congress</I>, Miami, Dec (I) --> <HR> <P><B> Please email any comments or questions about this web site, especially corrections and additions to <A HREF="mailto:hill@cpsc.ucalgary.ca"> Professor David Hill</A> </B> </P> <P>Page last updated 09-11-22</P> </BODY> </HTML>