asterisk users - Jul 2003 - Poll - Would you pay $30-$50 for high quality speech synthesis?

Many of you are familiar with how lousy Festival sounds.

AT&T has a product, NaturalVoices, that sounds much better.  There are
male & female voice fonts for US/UK/Indian English, French, Spanish,
and German.

I am considering offering a linux-based text-to-speech engine based on
the NaturalVoices runtime.  An asterisk module would also be provided,
making it easy to add natural sounding synthesis to Asterisk applications.
You could also use it for other purposes, such as home automation.

After discussing royalties with AT&T, I have concluded that I can probably
offer such a product at the following prices:

Runtime - $30 intro price with one voice font & one processor
Extra voices/languages - $15 each
Extra processors - $15 each

Depending on demand, the price may rise to $50 at some point.  The lower
the demand, the higher the price, due to AT&T's royalty structure.

There is a demo of the synthesis engine here:

http://www.naturalvoices.att.com/demos/

If you would be willing to pay for this kind of software, please e-mail
me privately (not to the list).  Please indicate your purchase timeframe
as well as the number of licenses, extra voices, and processors you
would want.

Regards,

Jeff / 'Bicster' on IRC

we would buy it even just for emergency prompts generation but we would need 
different languages, like polish and danish as well :))

On Tuesday 15 July 2003 17:07, Jeff Noxon wrote:
> Many of you are familiar with how lousy Festival sounds.
>
> AT&T has a product, NaturalVoices, that sounds much better.  There are
> male & female voice fonts for US/UK/Indian English, French, Spanish,
> and German.
>
> I am considering offering a linux-based text-to-speech engine based on
> the NaturalVoices runtime.  An asterisk module would also be provided,
> making it easy to add natural sounding synthesis to Asterisk applications.
> You could also use it for other purposes, such as home automation.
>
> After discussing royalties with AT&T, I have concluded that I can
probably
> offer such a product at the following prices:
>
> Runtime - $30 intro price with one voice font & one processor
> Extra voices/languages - $15 each
> Extra processors - $15 each
>
> Depending on demand, the price may rise to $50 at some point.  The lower
> the demand, the higher the price, due to AT&T's royalty structure.
>
> There is a demo of the synthesis engine here:
>
> http://www.naturalvoices.att.com/demos/
>
> If you would be willing to pay for this kind of software, please e-mail
> me privately (not to the list).  Please indicate your purchase timeframe
> as well as the number of licenses, extra voices, and processors you
> would want.
>
> Regards,
>
> Jeff / 'Bicster' on IRC
> _______________________________________________
> Asterisk-Users mailing list
> Asterisk-Users@lists.digium.com
> http://lists.digium.com/mailman/listinfo/asterisk-users
-- 
Michael Bielicki
Managing Director
TAAN Consultants Ltd
http://www.global-gateway.net/

--------------------------------------------------------------------------

This correspondence is for the named person's use only. It may contain
confidential or legally privileged information or both. No confidentiality
or privilege is waived or lost by any mistransmission. If you receive this
correspondence in error, please immediately delete it from your system and
notify the sender. You must not disclose, copy or rely on any part of this
correspondence if you are not the intended recipient.

Any opinions expressed in this message are those of the individual sender.

Wow, I thought they charged for this application on a per-channel basis.

I would spend $50 for this in a heartbeat.  I would need English, Dutch,
German, Spanish, Arabic & Russian...

-GSR

----- Original Message ----- 
From: "Jeff Noxon" <jeff-asterisk@planetfall.com>
To: <asterisk-users@lists.digium.com>
Sent: Tuesday, July 15, 2003 6:07 PM
Subject: [Asterisk-Users] Poll - Would you pay $30-$50 for high quality
speech synthesis?

> Many of you are familiar with how lousy Festival sounds.
>
> AT&T has a product, NaturalVoices, that sounds much better.  There are
> male & female voice fonts for US/UK/Indian English, French, Spanish,
> and German.
>
> I am considering offering a linux-based text-to-speech engine based on
> the NaturalVoices runtime.  An asterisk module would also be provided,
> making it easy to add natural sounding synthesis to Asterisk applications.
> You could also use it for other purposes, such as home automation.
>
> After discussing royalties with AT&T, I have concluded that I can
probably
> offer such a product at the following prices:
>
> Runtime - $30 intro price with one voice font & one processor
> Extra voices/languages - $15 each
> Extra processors - $15 each
>
> Depending on demand, the price may rise to $50 at some point.  The lower
> the demand, the higher the price, due to AT&T's royalty structure.
>
> There is a demo of the synthesis engine here:
>
> http://www.naturalvoices.att.com/demos/
>
> If you would be willing to pay for this kind of software, please e-mail
> me privately (not to the list).  Please indicate your purchase timeframe
> as well as the number of licenses, extra voices, and processors you
> would want.
>
> Regards,
>
> Jeff / 'Bicster' on IRC
> _______________________________________________
> Asterisk-Users mailing list
> Asterisk-Users@lists.digium.com
> http://lists.digium.com/mailman/listinfo/asterisk-users
>

At 20:36 15-7-2003 +0200, you wrote:
>Wow, I thought they charged for this application on a per-channel basis.
>
>I would spend $50 for this in a heartbeat.  I would need English, Dutch,
>German, Spanish, Arabic & Russian...
I second that motion, my requirement would be Dutch support...

Florian

Hi Jeff-

You might be interested to know that over the last couple of months I've
conducted (in the Windows world) an informal side-by-side comparison of
AT&T's Natural Voices product, with Lernout and Hauspies' (now
ScanSoft)
RealSpeak.  My small sample consisted of a few news clippings spoken with
the several male and female voices available on both systems.  I had about
25 people call in (mostly from the UK and US), and asked them afterwards
which they preferred in "tone" and which they found the most
understandable.

Most people thought that the AT&T Male voice was the most natural and
pleasant to listen to, while ScanSoft's female voice had the highest
"readability".  I think this was due to the fact that the AT&T
product
occasionally ran words together - if they have fixed this bug, AT&T may come
out fully on top.

However, the L&H (Scansoft) product is already available in many more
languages (19), and so you might also give them a call to talk about
licensing before you proceed, since many of the people in the Linux world
may require languages that AT&T doesn't have.

Anyway, I don't mean to dampen the enthusiasm for this undertaking, as we
all would benefit!  Please clarify if the pricing you mention is per system,
or per-port.

Thanks,
Scott Stingel


Scott M. Stingel 
Emerging Voice Technology Inc.
Palo Alto California & London England

Email:          scott@evtmedia.com   
URL:            www.evtmedia.com  


> -----Original Message-----
> From: asterisk-users-admin@lists.digium.com 
> [mailto:asterisk-users-admin@lists.digium.com] On Behalf Of Jeff Noxon
> Sent: Tuesday, July 15, 2003 5:07 PM
> To: asterisk-users@lists.digium.com
> Subject: [Asterisk-Users] Poll - Would you pay $30-$50 for 
> high quality speech synthesis?
> 
> 
> Many of you are familiar with how lousy Festival sounds.
> 
> AT&T has a product, NaturalVoices, that sounds much better.  There are
> male & female voice fonts for US/UK/Indian English, French, Spanish,
> and German.
> 
> I am considering offering a linux-based text-to-speech engine based on
> the NaturalVoices runtime.  An asterisk module would also be provided,
> making it easy to add natural sounding synthesis to Asterisk 
> applications.
> You could also use it for other purposes, such as home automation.
> 
> After discussing royalties with AT&T, I have concluded that I 
> can probably
> offer such a product at the following prices:
> 
> Runtime - $30 intro price with one voice font & one processor
> Extra voices/languages - $15 each
> Extra processors - $15 each
> 
> Depending on demand, the price may rise to $50 at some point. 
>  The lower
> the demand, the higher the price, due to AT&T's royalty structure.
> 
> There is a demo of the synthesis engine here:
> 
http://www.naturalvoices.att.com/demos/

If you would be willing to pay for this kind of software, please e-mail
me privately (not to the list).  Please indicate your purchase timeframe
as well as the number of licenses, extra voices, and processors you
would want.

Regards,

Jeff / 'Bicster' on IRC
_______________________________________________
Asterisk-Users mailing list
Asterisk-Users@lists.digium.com
http://lists.digium.com/mailman/listinfo/asterisk-users

--- Jeff Noxon <jeff-asterisk@planetfall.com>
wrote:
> Many of you are familiar with how lousy Festival sounds.
> 
> AT&T has a product, NaturalVoices, that sounds much better.  There
> are
> male & female voice fonts for US/UK/Indian English, French, Spanish,
> and German.
Festival only sounds bad because you are using it in a very simple way.
It comes with a "demo" text to speech application that really is no
more then a demo but most people just use the demo app and think
Festival itself sounds bad.  You need to read a bit more.  Also at
the cmu.edu web site are some tools for building your own voices.
These can sound very good and speeak other languages.
If you work at it the sound can be very natural.

====Chris Albertson
  Home:   310-376-1029  chrisalbertson90278@yahoo.com
  Cell:   310-990-7550
  Office: 310-336-5189  Christopher.J.Albertson@aero.org
  KG6OMK

__________________________________
Do you Yahoo!?
SBC Yahoo! DSL - Now only $29.95 per month!
http://sbc.yahoo.com

Would you mind giving us a few examples on how we can make festival
sound better?  (Some sample festival configs would be nice!)

Jared

On Tue, 2003-07-15 at 14:41, Chris Albertson wrote:
> --- Jeff Noxon <jeff-asterisk@planetfall.com> wrote:
> > Many of you are familiar with how lousy Festival sounds.
> > 
> > AT&T has a product, NaturalVoices, that sounds much better.  There
> > are
> > male & female voice fonts for US/UK/Indian English, French,
Spanish,
> > and German.
> 
> Festival only sounds bad because you are using it in a very simple way.
> It comes with a "demo" text to speech application that really is
no
> more then a demo but most people just use the demo app and think
> Festival itself sounds bad.  You need to read a bit more.  Also at
> the cmu.edu web site are some tools for building your own voices.
> These can sound very good and speeak other languages.
> If you work at it the sound can be very natural.
> 
> ====> Chris Albertson
>   Home:   310-376-1029  chrisalbertson90278@yahoo.com
>   Cell:   310-990-7550
>   Office: 310-336-5189  Christopher.J.Albertson@aero.org
>   KG6OMK
> 
> __________________________________
> Do you Yahoo!?
> SBC Yahoo! DSL - Now only $29.95 per month!
> http://sbc.yahoo.com
> _______________________________________________
> Asterisk-Users mailing list
> Asterisk-Users@lists.digium.com
> http://lists.digium.com/mailman/listinfo/asterisk-users

Sorry, I left out the URL.  Here it is

  http://fife.speech.cs.cmu.edu/festival/

If interrested look at "demos" on the top menu bar.
You see what is involved in building new databases
for new languages or speaker voices for Festival.

When you complain about the sound you are really complaining
about the database quality or the quality of in mark-up 
embedded in the input text.

In building a new database first you will need to find a
human with a nice sounding voice who speaks the language
with the "correct" regional accent.  That may be the hardest
part but after that it seems to take about a day or two



--- Chris Albertson <chrisalbertson90278@yahoo.com>
wrote:
> 
> --- Jeff Noxon <jeff-asterisk@planetfall.com> wrote:
> > Many of you are familiar with how lousy Festival sounds.
> > 
> > AT&T has a product, NaturalVoices, that sounds much better.  There
> > are
> > male & female voice fonts for US/UK/Indian English, French,
> Spanish,
> > and German.
> 
> Festival only sounds bad because you are using it in a very simple
> way.
> It comes with a "demo" text to speech application that really is
no
> more then a demo but most people just use the demo app and think
> Festival itself sounds bad.  You need to read a bit more.  Also at
> the cmu.edu web site are some tools for building your own voices.
> These can sound very good and speeak other languages.
> If you work at it the sound can be very natural.
====Chris Albertson
  Home:   310-376-1029  chrisalbertson90278@yahoo.com
  Cell:   310-990-7550
  Office: 310-336-5189  Christopher.J.Albertson@aero.org
  KG6OMK

__________________________________
Do you Yahoo!?
SBC Yahoo! DSL - Now only $29.95 per month!
http://sbc.yahoo.com

> If you would be willing to pay for this kind of software, please e-mail
> me privately (not to the list).  Please indicate your purchase timeframe
> as well as the number of licenses, extra voices, and processors you
> would want.
It should be simple, call an executable, with two parameters, the file where
the text is and what to name the output sound file.

I would pay for that.  We could sell at least 10-15 per month.

-Matt

Jeff Noxon wrote:
>Many of you are familiar with how lousy Festival sounds.
>
>AT&T has a product, NaturalVoices, that sounds much better.  There are
>male & female voice fonts for US/UK/Indian English, French, Spanish,
>and German.
>
>I am considering offering a linux-based text-to-speech engine based on
>the NaturalVoices runtime.  An asterisk module would also be provided,
>making it easy to add natural sounding synthesis to Asterisk applications.
>You could also use it for other purposes, such as home automation.
>
>After discussing royalties with AT&T, I have concluded that I can
probably
>offer such a product at the following prices:
>
>Runtime - $30 intro price with one voice font & one processor
>Extra voices/languages - $15 each
>Extra processors - $15 each
>
>Depending on demand, the price may rise to $50 at some point.  The lower
>the demand, the higher the price, due to AT&T's royalty structure.
>
Maybe you are right, but take great care with this.

You can get packaged versions of Natural Voices cheaply for desktop 
applications. However, when you want to use it for telephony systems it 
usually costs more like $600-$700 per port. There are also big 
differences in the way ports are counted by different vendors. For 
example, the per port pricing for RealSpeak (which is not realated to 
Naturally Speaking) and Speechify (Speechworks derivative of Naturally 
Speaking) is not too different, but the final bill may be. With 
Realspeak, if you have 1000 ports, and only use TTS a little you still 
pay for 1000 ports. With Speechify you pay for the maximum current 
channels you will have speaking at any instant. Unless your system is 
very TTS heavy, this makes a huge difference.

I last worked heavily with these TTS engines about two years ago. They 
have improved, but I don't think by that much. Speechify was a lot more 
functional then Naturally Speaking, as its front end language processing 
was more complete. Naturally Speaking read too many things in the wrong 
way (a lot of other TTSs did too). The various Naturally Speaking 
derivatives are not all equal. Naturally Speaking is itself a derivative 
of Festival. Look in the directories, and you still see lots of Festival 
files. Cepstral and Rhetorical Systems both have impressive sounding TTS 
based on Festival. Festival seems to be the root of most things other 
than RealSpeak and Eloquence. Eloquence seems pretty much the only 
mainstream package which does things differently, and actually 
synthesizes voice from basic principals.

Two years ago we deployed systems using RealSpeak, Speechify and 
Eloquence. People hated the robotic quality of Eloquence, but could 
understand it clearly (at least the English one - the Mandarin version 
sounded terrible). People liked the natural sound of RealSpeak, but 
couldn't understand it very well - they could follow paragraphs of text 
OK, but ask them about a specific thing that was said, like a street 
name, and their accuarcy was very poor. Speechify was somewhere in 
between, but tending towards RealSpeak. In the end, adverse user 
reaction made us rip out all the TTS and abandon attempts to use it.

Some pointers from working with this stuff:

- First impressions are a bad indicator of true quality, due to the next 
point. You need to play with these things for a while, and see how they 
behave in real world use, before you can really evaluate their usefulness.

- In current TTS systems (all of them), natural sounding tned to equate 
with hard to understand. Most TTS systems basically use a database of 
recorded snippets, and blend them to form speech. The longer the 
snippets, the smoother and more natural the sound, but the worse is its 
accuracy. Short snippets allow more flexibility in sculpting the result. 
giving better intelligibility, but making the sound more robotic.

- If your application is reading long tracts of text, the natural 
sounding TTSs do fairly well. The words you don't hear clearly are 
naturally filled in by your brain from the context. If your application 
is reading out addresses, the more robotic systems do better - I found 
Eloquence does the best for this.

- Don't underestimate the importance of the front end language 
processor. Most offerings deal with this part poorly. They all have 
demos that show how well the sysem will read things like currency and 
dates. Try feeding those texts to other vendor's TTS engines. The 
results can be quite interestings. The demos only contain examples of 
things the particular engine does well, and they have all focussed on 
getting different things right.

- You put together a system you think is really neat. Users initially 
think it pretty neat too. Then those same users gradually abandon the 
system as they find its limitations.

- Watch our for resource usage. You might expect these things to hog the 
CPU. They don't. However, they take hundreds of megs of disk (OK), and 
some (like Naturally Speak and Speechify) needed it all in RAM at once 
to work well (not so OK). So, you had to allow more than 200MB of RAM 
per voice. This may have been improved in newer versions of Speechify, 
but I don' t think Naturally Speaking has changed much in that time.

Regards,
Steve