<div class="gmail_quote"><div>Hi,<br> <br></div><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">* How many languages does speech-dispatcher support?<br>
<br><a href="http://www.freebsoft.org/doc/speechd/speech-dispatcher_5.html#SEC8" target="_blank">http://www.freebsoft.org/doc/speechd/speech-dispatcher_5.html#SEC8</a><br><br>SD works with Festival <a href="http://www.cstr.ed.ac.uk/projects/festival/" target="_blank">http://www.cstr.ed.ac.uk/projects/festival/</a><br>
English, Czech, Italian, Spanish, Russian, Polish...<br><br>What is the mechanism for adding additional languages? Phoneset<br>recording, dictionary, and what?</blockquote><div><br>As of now we are planning to use the eSpeak module with Speech Dispatcher. It is already available on the XO, is lightweight and has support for many more languages as compared to Festival, and I quote from the eSpeak website : <br>
<br><blockquote style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;" class="gmail_quote">eSpeak does text to speech synthesis for the following languages, some
better than others. Afrikaans, Cantonese, Croatian, Czech, Dutch,
English, Esperanto, Finnish, French, German, Greek, Hindi, Hungarian,
Icelandic, Italian, Lojban, Macedonian, Mandarin, Norwegian, Polish,
Portuguese, Romanian, Russian, Serbian, Slovak, Spanish, Swahili,
Swedish, Vietnamese, Welsh. See <a href="http://espeak.sourceforge.net/languages.html">Languages</a>.</blockquote><div><br>I did some preliminary research regarding the language support that was needed wrt locations where the OLPC Pilot Projects will be launched or are running.<br>
<br>Austria - German<br>India - Hindi<br>Spain - Spanish<br>and so on..<br><br>For a full list of languages and how Languages can be added to eSpeak please check <a href="http://espeak.sourceforge.net/languages.html">http://espeak.sourceforge.net/languages.html</a>. Jon SD the developer of eSpeak has written a few tutorials about how one can go about adding or improving the existing phoneme data sets. In fact Assim had documented and played around with voice characteristics of eSpeak to improve the voice output. You can check the results on the wiki page i had mentioned previously [<a href="http://wiki.laptop.org/go/Screen_Reader#Voice_Files">http://wiki.laptop.org/go/Screen_Reader#Voice_Files</a>]<br>
<br>I have extensively used eSpeak through the course of this project, and will certainly explore other supported TTS engines, however I am taking one step at a time.<br></div><br></div><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
Now for organization.<br><br>Where should we put TTS projects for language support? Can we create<br><a href="http://dev.laptop.org/tts" target="_blank">http://dev.laptop.org/tts</a>? Who should be in charge? What sort of<br>
process should we have for creating projects? Should we just<br>automatically create a TTS project for every translate project?</blockquote><div><br>Indeed this sounds like a great idea, and I was planning to involve more volunteers, once we have a basic speech synthesis frameworkpresent on the XO. It will be easier to motivate individuals from different countries to add translations/ improve phoneme data once there is "something" for them to use. Again, I am a student and devote whatever time i get after my school hours to this project, and hence the pace has been slow.<br>
<br></div><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">> speech-dispatcher is not packaged as an RPM for Fedora,<br><div class="Ih2E3d">
<br></div>I see Debian packages. Is there a converter?</blockquote><div><br>It is possible to convert .deb packages to .rpm using "Alien". I am afraid that wont be possible, as Fedora has strict packaging guidelines that we must adhere to. I am writing the packaging rules from scratch. So it must be approved by the Fedora community before it is accepted in the OLPC builds. The reason for the strict guidelines is mostly Quality Assurance and proper integration of the package with Fedora.<br>
<br></div><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">Have you looked at Oralux, the Linux distro for the blind and visually-impaired?<br>
<a href="http://oralux.net/" target="_blank">http://oralux.net/</a><br>We should invite them to join our efforts.</blockquote><div><br>I did not know about this, and will surely go through there website. However this is an extremely high-level decision that many developers from OLPC will need to take, as I am sure there will be issues of integration of Oralux technology with Sugar etc.<br>
<br> So again I'll say I am moving one step at a time. Thanks for the points that you put forward, they will help us to better structure our own ideas and vision regarding tts on the XO.<br><br>Warm regards,<br>Hemant<br>
</div></div>