Re: just a newbi problem, want to use festival, not flite with emacspeak

["T. V. Raman" <raman@xxxxxxxxxxx>]

so why do yu ned the  Viavoice sdk - the waa the emacspeak server
is implemented, all  you need is the runtime.

>>>>> "tcross" == tcross  <tcross@xxxxxxxxxxx> writes:
    tcross> Just a few points which may be of interest in this
    tcross> thread.
    tcross> 
    tcross> Festival is a very powerful and configurable TTS. It
    tcross> can support quite a few different voices and has a
    tcross> lot of parameters which can be tweaked to improve
    tcross> synthesis. The "out of the box" configuration is a
    tcross> general default that is likely to meet most users
    tcross> requirements.  However, I found (quite some time ago)
    tcross> when playing with festival, I could get better
    tcross> performance tweaking some of the settings associated
    tcross> with festival and the voice tools. Unfortunately, it
    tcross> was a while ago and I dont actually remember what all
    tcross> the tweaks were.
    tcross> 
    tcross> Festival supports voices from other sources and in
    tcross> many distributions, you will get different quality
    tcross> voices - for example, in Debian, there are both 8k
    tcross> and 16k voices for US/UK english. The 8k voices don't
    tcross> have the same quality, but will probably give better
    tcross> performance on slower machines with less memory.
    tcross> 
    tcross> Although I've never got around to it, mbrola voices
    tcross> are supposed to provide very good quality voices with
    tcross> festival. Voices from http://www.cepstral.com can
    tcross> also be used with festival - they had a perl script
    tcross> on their website that would allow you to import a
    tcross> cepstral voice into festival. Cepstral voices are
    tcross> good quality, but they lose quality significantly at
    tcross> higher voice speaking rates. They are commercial
    tcross> voices which you have to pay for, but they do have a
    tcross> number of different languages available.
    tcross> 
    tcross> IMO by far the best software TTS for emacspeak is
    tcross> ViaVoice, which you can purchase from
    tcross> http://www.wizzardsoftware.com. However, you have to
    tcross> purchase the SDK and it costs over $300US.
    tcross> 
    tcross> Second best for quality of speech is the software
    tcross> dectalk. However, this TTS engine does crash
    tcross> regularly under emacspeak (it works reliably under
    tcross> speech dispatcher, but speech dispatcher is using it
    tcross> in its most basic way and does not try to use the
    tcross> in-line voice control codes emacspeak uses for voice
    tcross> locking etc). The software dectalk is available from
    tcross> http://www.fonix.com for about $100US.
    tcross> 
    tcross> I used the softwar dectalk for quite some time and
    tcross> managed to live with the regular crashes - all you
    tcross> need to do is a C-e C-s when the TTS stops working
    tcross> and verything is restarted. Although a bit annoying,
    tcross> it provides good voice quality at high speaking
    tcross> rates, which I think is important. I now use it as my
    tcross> emergency backup TTS if I don't have a hardware
    tcross> synthesiser for backup.
    tcross> 
    tcross> HTH
    tcross> 
    tcross> Tim
    tcross> 
    tcross> 
    tcross> 
    tcross> 
    tcross> 
    tcross> 
    tcross> Lukas Loehrer writes:
    >> 
    >> Some observations:
    >> 
    >> I just tried speech dispatcher with festival again. I am
    >> using fspeech dispatcher via speechd-el this time. I am
    >> using the packages from Debian unstable.
    >> 
    >> When using the flite output module of speech dispatcher,
    >> responsiveness is the same as with eflite in
    >> emacspeak. When using the festival output module in speech
    >> dispatcher, some of the problems seen in espeakf go
    >> away. Speech stops immediately when it should. However,
    >> there is a noticeable pause between the moment a command
    >> is issued and the corresponding speech starts. I cannot
    >> tell if the pause is silence generated by the tts or if it
    >> takes that long for the speech to be synthesized. In the
    >> latter case, a faster machine might in fact help.
    >> 
    >> Thus, it seems that if one is looking for good
    >> responsiveness, festival used through either espeakf or
    >> speech-dispatcher should not be one's first choice. things
    >> look differently if priorities lie with support for
    >> multiple voices or languages.
    >> 
    >> Best regards, Lukas
    >> 
    >> -----------------------------------------------------------------------------
    >> To unsubscribe from the emacspeak list or change your
    >> address on the emacspeak list send mail to
    >> "emacspeak-request@xxxxxxxxxxx" with a subject of
    >> "unsubscribe" or "help"
    >> 
    tcross> 
-- 
Tim Cross tcross@xxxxxxxxxxx
    tcross> 
    tcross> There are two types of people in IT - those who do
    tcross> not manage what they understand and those who do not
    tcross> understand what they manage.
    tcross> 
    tcross> -----------------------------------------------------------------------------
    tcross> To unsubscribe from the emacspeak list or change your
    tcross> address on the emacspeak list send mail to
    tcross> "emacspeak-request@xxxxxxxxxxx" with a subject of
    tcross> "unsubscribe" or "help"

-- 
Best Regards,
--raman

      
Email:  raman@xxxxxxxxxxx
WWW:    http://emacspeak.sf.net/raman/
AIM:    emacspeak       GTalk: tv.raman.tv@xxxxxxxxxxx
PGP:    http://emacspeak.sf.net/raman/raman-almaden.asc
Google: tv+raman 
IRC:    irc://irc.freenode.net/#emacs

-----------------------------------------------------------------------------
To unsubscribe from the emacspeak list or change your address on the
emacspeak list send mail to "emacspeak-request@xxxxxxxxxxx" with a
subject of "unsubscribe" or "help"