punctuation or other improvments?

	People,

	Some of the default pronunciation by the Fevtival speakers
	leaves a lot to be desired.  The word "essay",
for example.  
	Or the slight slurring of "to" when compared to
one of its
	homonyms, "two" or "2" ...  .  

	I'm running FreeBSD 6.2 and whatever its the latest KDE
port of 
	its text-to-speech suite.  Can anybody point me to any
fixes or
	improvements in the pronunciation/enunciation side of
things?

	thanks much,

	gary kline


-- 
  Gary Kline  klinethought.org   www.thought.org  Public
Service Unix

_______________________________________________
kde-accessibility mailing list
kde-accessibilitykde.org
https://mail.kde.org/mailman/listinfo/kde-accessibility

On 26 Oct, Gary Kline <klinetao2.thought.org>
wrote:

> 	Some of the default pronunciation by the Fevtival
speakers
> 	leaves a lot to be desired.  The word
"essay", for example.  
> 	Or the slight slurring of "to" when compared
to one of its
> 	homonyms, "two" or "2" ...  .  

I tried the sentence "to essay to" with the
"American Male -
(kal_diphone)" voice.  The are definitely problems.

The word "to" should have three different
pronunciations (at least in
my own speech).  An emphatic form, phonetic [tu:], which is
the same
sound as number "two".  This is used at the end of
a sentence or when
the word is spoken alone.  There are a weak forms when [tU]
(the same
vowel as in "foot") when the next word starts with
a vowel, and [t]
(the neutral schwa vowel, as in "the") when the
next word starts with a
consonant.  Your own local version of English may differ.

Festival seems to use the schwa vowel in all cases, even
when it's
spoken as a single word.  That's definitely wrong.

Festival is OK with "his essay", but in "the
essay" or "to essay" it
seems to drop the initial "e", or perhaps merges
it with the previous
word.  

> 	I'm running FreeBSD 6.2 and whatever its the latest
KDE port of 
> 	its text-to-speech suite.  Can anybody point me to any
fixes or
> 	improvements in the pronunciation/enunciation side of
things?

Yes of course, eSpeak at:
http://espeak.sourcefo
rge.net/

It's intonation is less annoying and the enunciation is
clearer. 
If you don't like its mechanical voice, you can use eSpeak
as a front
end to a more natural mbrola diphone voice. Details are at
http://espe
ak.sourceforge.net/mbrola.html

_______________________________________________
kde-accessibility mailing list
kde-accessibilitykde.org
https://mail.kde.org/mailman/listinfo/kde-accessibility

On Sat, 2007-10-27 at 03:49 +0100, Jonathan Duddington
wrote:
> On 26 Oct, Gary Kline <klinetao2.thought.org>
wrote:
> 
> > 	Some of the default pronunciation by the Fevtival
speakers
> > 	leaves a lot to be desired.  The word
"essay", for example.  
> > 	Or the slight slurring of "to" when
compared to one of its
> > 	homonyms, "two" or "2" ...  .
 
> 
> I tried the sentence "to essay to" with the
"American Male -
> (kal_diphone)" voice.  The are definitely
problems.
> 
> The word "to" should have three different
pronunciations (at least in
> my own speech).  An emphatic form, phonetic [tu:],
which is the same
> sound as number "two".  This is used at the
end of a sentence or when
> the word is spoken alone.  There are a weak forms when
[tU] (the same
> vowel as in "foot") when the next word starts
with a vowel, and [t]
> (the neutral schwa vowel, as in "the") when
the next word starts with a
> consonant.  Your own local version of English may
differ.
> 
> Festival seems to use the schwa vowel in all cases,
even when it's
> spoken as a single word.  That's definitely wrong.
> 
> Festival is OK with "his essay", but in
"the essay" or "to essay" it
> seems to drop the initial "e", or perhaps
merges it with the previous
> word.  
> 
> > 	I'm running FreeBSD 6.2 and whatever its the
latest KDE port of 
> > 	its text-to-speech suite.  Can anybody point me
to any fixes or
> > 	improvements in the pronunciation/enunciation
side of things?
> 
> Yes of course, eSpeak at:
> http://espeak.sourcefo
rge.net/
> 
> It's intonation is less annoying and the enunciation is
clearer. 
> If you don't like its mechanical voice, you can use
eSpeak as a front
> end to a more natural mbrola diphone voice. Details are
at
> http://espe
ak.sourceforge.net/mbrola.html
> 

	Thanks for  the URL's.  Do you know if these just install
in
/usr/local/* and are understood automatically?  or if I need
to do some
by-hand configuration?

	Re "essay" and many other words (and
punctuation), I started to
create my own filter(s).  After I signed up to list list I
discovered
there are more phonic dictionaries that I'd hoped for.   The
thing is:
do I want to make my own fixes or get the latest files?  A
lot of the
stuff I'm working with is my own writing and others and
deals with
things not that commonly discussed. 

Do you know if there is one central place that has the
newest voices, or
is it pretty much look and see?

thanks again,

gary

> _______________________________________________
> kde-accessibility mailing list
> kde-accessibilitykde.org
> https://mail.kde.org/mailman/listinfo/kde-accessibility
-- 
Gary Kline     
klineethos.thought.org         
www.thought.org       
Thought Unlimited

_______________________________________________
kde-accessibility mailing list
kde-accessibilitykde.org
https://mail.kde.org/mailman/listinfo/kde-accessibility

On 27 Oct, Gary Kline <klineethos.thought.org>
wrote:

> 	Thanks for  the URL's.  Do you know if these just
install in
> /usr/local/* and are understood automatically?  or if I
need to do
> some by-hand configuration?

Packages for eSpeak are available for various Linux
distributions.  If
you are installing manually, instructions are in:
  http://espeak.sf.n
et/commands.html

It includes how to set up eSpeak as a "talker" in
the KDE speech
manager.

> 	Re "essay" and many other words (and
punctuation), I started to
> create my own filter(s).  After I signed up to list
list I discovered
> there are more phonic dictionaries that I'd hoped for. 
 The thing is:
> do I want to make my own fixes or get the latest files?
 A lot of the
> stuff I'm working with is my own writing and others and
deals with
> things not that commonly discussed. 

> Do you know if there is one central place that has the
newest voices,
> or is it pretty much look and see?

I don't know anything about dictionary or voice updates for
Festival.

For eSpeak if you find pronunciation errors, you can email
them to me
and I'll fix them.  Alternatively you can make your own
pronunciation
exceptions list in  dictsource/en_extra  and then re-compile
the
pronunciation dictionary with:
  espeak --compile=en

Details are in  http://espeak.sf
.net/dictionary.html  in the section
Pronunciation Dictionary List, or see  dictsource/en_list 
as an
example.

_______________________________________________
kde-accessibility mailing list
kde-accessibilitykde.org
https://mail.kde.org/mailman/listinfo/kde-accessibility

On Sat, 2007-10-27 at 12:14 +0100, Jonathan Duddington
wrote:
> On 27 Oct, Gary Kline <klineethos.thought.org>
wrote:
> 
> > 	Thanks for  the URL's.  Do you know if these just
install in
> > /usr/local/* and are understood automatically?  or
if I need to do
> > some by-hand configuration?
> 
> Packages for eSpeak are available for various Linux
distributions.  If
> you are installing manually, instructions are in:
>   http://espeak.sf.n
et/commands.html
> 
> It includes how to set up eSpeak as a
"talker" in the KDE speech
> manager.
> 
> > 	Re "essay" and many other words (and
punctuation), I started to
> > create my own filter(s).  After I signed up to
list list I discovered
> > there are more phonic dictionaries that I'd hoped
for.   The thing is:
> > do I want to make my own fixes or get the latest
files?  A lot of the
> > stuff I'm working with is my own writing and
others and deals with
> > things not that commonly discussed. 
> 
> > Do you know if there is one central place that has
the newest voices,
> > or is it pretty much look and see?
> 
> I don't know anything about dictionary or voice updates
for Festival.

	Then perhaps you can tell me the relationship between Alan
Black's
"Festival" and "espeak"; there is a
suite of three speech utilities
named "*mbrola" that have not up updated on my
version of BSD for two
years.   I would like to use the leading synthsizer--the one
most
actively being developed.  

> 
> For eSpeak if you find pronunciation errors, you can
email them to me
> and I'll fix them.  Alternatively you can make your own
pronunciation
> exceptions list in  dictsource/en_extra  and then
re-compile the
> pronunciation dictionary with:
>   espeak --compile=en
> 
	I'll do both; or try!  My background is as a systems
analyst,
in porting code, and in operating system test.   I know
nearly 0.0 about
the audio or video side of computers.  At any rate, I'm back
in schhool
studying ethics  [[philosophy]]; it is in this area where
some of the
default "talkers" mispronunciations stem.  Not
all; some of the words
are more common.  (I don't mean "read" [reed] and
"read" [red]; this is
an AI/syntactical/linguistics problem.  --I'll send you some
words,
off-list.

> Details are in  http://espeak.sf
.net/dictionary.html  in the section
> Pronunciation Dictionary List, or see 
dictsource/en_list  as an
> example.
> 
	Thanks for your pointers.  


> _______________________________________________
> kde-accessibility mailing list
> kde-accessibilitykde.org
> https://mail.kde.org/mailman/listinfo/kde-accessibility
-- 
Gary Kline     
klineethos.thought.org         
www.thought.org       
Thought Unlimited

_______________________________________________
kde-accessibility mailing list
kde-accessibilitykde.org
https://mail.kde.org/mailman/listinfo/kde-accessibility

On 28 Oct, Gary Kline <klineethos.thought.org>
wrote:

> 	Then perhaps you can tell me the relationship between
Alan Black's
> "Festival" and "espeak";

There is none.  
eSpeak is a different open-source text to speech
synthesizer.  It uses
a different method, "formant synthesis".  This
makes it faster (more
responsive) and much smaller (which allows several languages
in a small
package), but less natural in speech quality.  However I
believe its
enunciation is clearer, which was your main problem.

> there is a suite of three speech utilities named
"*mbrola" that have
> not up updated on my version of BSD for two years.   I
would like to
> use the leading synthsizer--the one most actively being
developed.  

The mbrola diphone voices are only the back-end part of a
synthesizer. 
They need a front-end to do spelling to phoneme conversion
and
intonation.  eSpeak can be used for this and may be useful
to avoid the
Festival errors which you mentioned, while avoiding the
mechanical
sound of eSpeak's own formant synthesis.  

Basically I'm suggesting that you try alternatives to find
which sounds
best for you.  Different people have different preferences.

> I'll send you some words, off-list.

Thanks.  It's easy enough for me to find words which are
pronounced
wrongly, by speaking a lexicon.  But many are uncommon
words, or are
only slightly wrong, or both.  Many may not be a problem in
practice. 
But if you find errors which are annoying or confusing, then
please
tell me.

_______________________________________________
kde-accessibility mailing list
kde-accessibilitykde.org
https://mail.kde.org/mailman/listinfo/kde-accessibility

On Sunday 28 October 2007 02:24:18 Jonathan Duddington
wrote:
> On 28 Oct, Gary Kline <klineethos.thought.org>
wrote:
> > 	Then perhaps you can tell me the relationship
between Alan Black's
> > "Festival" and "espeak";
>
> There is none.
> eSpeak is a different open-source text to speech
synthesizer.  It uses
> a different method, "formant synthesis". 
This makes it faster (more
> responsive) and much smaller (which allows several
languages in a small
> package), but less natural in speech quality.  However
I believe its
> enunciation is clearer, which was your main problem.
>
> > there is a suite of three speech utilities named
"*mbrola" that have
> > not up updated on my version of BSD for two years.
  I would like to
> > use the leading synthsizer--the one most actively
being developed.
>
> The mbrola diphone voices are only the back-end part of
a synthesizer.
> They need a front-end to do spelling to phoneme
conversion and
> intonation.  eSpeak can be used for this and may be
useful to avoid the
> Festival errors which you mentioned, while avoiding the
mechanical
> sound of eSpeak's own formant synthesis.
>
> Basically I'm suggesting that you try alternatives to
find which sounds
> best for you.  Different people have different
preferences.
>
> > I'll send you some words, off-list.
>
> Thanks.  It's easy enough for me to find words which
are pronounced
> wrongly, by speaking a lexicon.  But many are uncommon
words, or are
> only slightly wrong, or both.  Many may not be a
problem in practice.
> But if you find errors which are annoying or confusing,
then please
> tell me.
>
> _______________________________________________
> kde-accessibility mailing list
> kde-accessibilitykde.org
> https://mail.kde.org/mailman/listinfo/kde-accessibility

with the festival based voices you will find that theres a
dictionary file for 
it in  /usr/share/festival/dicts/<the name of the
voice>/
although it mybe a bit involved you can define how each word
is spoken by 
defaut there as well as add new words 

quite often you have to trick it into pronouncing the word
correctly 
for example  for "email"  put  "he mail"
as the text you want it to speak

theres one or two quirks in the standard festival
dictionaries that i find 
annoiying and have corrected in the dictionary files  like
DEC is spoken 
as "december" rather than decriment, short for
digital equipment corp 
or many other abreviations also 

unfortunalty form thepoint of view of kdeaccessibilaty and
kttsd its not realy 
posible to have patches for festival in the install package
both from the 
licencing point of view and the software side of installing
files inot 
another package 

what may be a solution is to use the kttsd filters section
and create your own 
filters for the words you want it to speak diferently to
standard 

realy you should be using festival 1.95 beta and one of the
arctic database 
based voices http://fes
tvox.org/cmu_arctic/dbs_slt.html
for best results use the multisyn versions of the voice

or if your realy brave you can rebuild the voice form the
original source 
audio files to get better audio quality also (if you have a
few months to 
spare that is )

the festival mailing list is  
festival-talkfestvox.org 


David (aka achiestdragon)
personal website http://www.achiestdragon
.org
artwork http://achiestdr
agon.deviantart.com/




_______________________________________________
kde-accessibility mailing list
kde-accessibilitykde.org
https://mail.kde.org/mailman/listinfo/kde-accessibility