<html>
<head>
<meta http-equiv="Content-Type" content="text/html;
charset=windows-1252">
</head>
<body text="#000000" bgcolor="#FFFFFF">
Hi Blake,<br>
I didn't know there was a KeyNote voice for SAPI 5. How was this
converted? What does CR stand for?<br>
-Ulysses<br>
<div class="moz-cite-prefix">On 9/7/2017 12:53 PM, Blake Roberts
wrote:<br>
</div>
<blockquote type="cite"
cite="mid:993F8FC1D99A4B1D998BCAE73148992B@Blakethegreat">
<meta http-equiv="Context-Type" content="text/html;
charset=us-ascii">
<meta name="Generator" content="Microsoft Word 11 (filtered
medium)">
<div class="Section1">
<p class="MsoNormal"><span>Yes, some of the Circum Reality
voices sound
good. It's also wonderful that Jake Gross made a SAPI
keynote. I did not know that
I could record myself saying a word for correct intonation.
Is version of Circum
Reality on Jake's site the most recent version? My only
issue with CR on Jake's
site is lack of uninstaller. Removing a installed
CircumReality voice requires editing
the registry. I had to do that when I had CR voice(s) on my
computer some time ago.
Editing the registry scares me because of the damage
incorrectly editing registry
entries can do to a computer. Is there a newer version of CR
available which uninstalls
a voice/ removes voice/CR registry keys?</span></p>
<p class="MsoNormal"><span>Blake</span></p>
<p class="MsoNormal"><span> </span></p>
<div>
<div class="MsoNormal"><span>
<hr tabindex="-1" width="100%">
</span></div>
<p class="MsoNormal"><b><span>From:</span></b><span> Dectalk
[<a class="moz-txt-link-freetext" href="mailto:dectalk-bounces@bluegrasspals.com">mailto:dectalk-bounces@bluegrasspals.com</a>] <b><span>On
Behalf Of </span></b>Brandon Tyson<br>
<b><span>Sent:</span></b> Thursday, September 07, 2017
12:47 PM<br>
<b><span>To:</span></b> DECtalk<br>
<b><span>Subject:</span></b> Re: [DECtalk] voice creation</span><span></span></p>
</div>
<p class="MsoNormal"><span> </span></p>
<p class="MsoNormal"><span>Hello,</span></p>
<p class="MsoNormal"><span> </span></p>
<p class="MsoNormal"><span>I
wanted to touch on one point please:</span></p>
<p class="MsoNormal"><span> </span></p>
<p class="MsoNormal"><span>Even
if they can’t do SAPI, and even though this wouldn’t be the
same, I’m still
quite happy with the now open-sourced CircumReality voice
and think that they
sound pretty good.</span></p>
<p class="MsoNormal"><span>What
I particularly like about those is that even if they do have
a
mispronunciation, it’s giving you the possibility to change
the way a
particular word, or even whole phrases, sound through manual
hand made
recordings, I think, which would theoretically be used in
conjunction with the
synthesizer itself.</span></p>
<p class="MsoNormal"><span> </span></p>
<p class="MsoNormal"><span>Does
this make sense?</span></p>
<p class="MsoNormal"><span> </span></p>
<p class="MsoNormal"><span>E.g.
A user types in “Wow!” but they find the intonation is
incorrect. It says
“wow.” Instead, making it sound boring. So the user can go
in and manually
correct this to have it say “Wow!” correctly by making an
individual recording
for that.</span></p>
<p class="MsoNormal"><span> </span></p>
<p class="MsoNormal"><span>Thanks,</span></p>
<p class="MsoNormal"><span> </span></p>
<p class="MsoNormal"><span>Brandon</span></p>
<p class="MsoNormal"><span> </span></p>
<div>
<p class="MsoNormal"><b><span>From: </span></b><a
href="mailto:r.d.t.prater@gmail.com"
moz-do-not-send="true">Devin Prater</a><br>
<b><span>Sent: </span></b>Thursday, September 7, 2017
8:56 AM<br>
<b><span>To: </span></b><a
href="mailto:dectalk@bluegrasspals.com"
moz-do-not-send="true">DECtalk</a><br>
<b><span>Subject: </span></b>Re: [DECtalk] voice creation</p>
</div>
<p class="MsoNormal"><span> </span></p>
<p class="MsoNormal"><span>Yuly,
GPU is the Graphics processing unit, and the CPU is the
central processing
unit. </span></p>
<div id="AppleMailSignature">
<p class="MsoNormal"><span>A
neural net is is a way for computers to learn as a human
does, through
artificial intelligence. <br>
<br>
Sent from my iPhone</span></p>
</div>
<div>
<p class="MsoNormal"><span><br>
On Sep 7, 2017, at 7:39 AM, Ulysses Harmony Garcia via
Dectalk <<a href="mailto:dectalk@bluegrasspals.com"
moz-do-not-send="true">dectalk@bluegrasspals.com</a>>
wrote:</span></p>
</div>
<blockquote>
<div>
<p class="MsoNormal"><span>What
is GPU, and how is that different from CPU? Also, how
does neural networking
work? Does the computer map out a brain on a series of
coordinates the way it
does when mapping out an MRI or 3D printing the model of
the brain? I'm
interested in knowing what programming languages,
interpreter scripts, etc they
use so that people in college and university labs who do
neuroscientific work
can build more neural networks to experiment on.<br>
I've read some sci-fi literature on how mind-uploading
could work, but the
problem is that it would be nearly impossible to
calculate the exact number of
neurones, neurotransmitters, synapses, and receptors,
and which memories or
part of identity they link up to. It would require a
huge load of processing
and a really high knowledge of map coordination in three
dimensions to put a
series of binary code in each region of how the brain
would look like.<br>
-Ulysses</span></p>
<div>
<p class="MsoNormal"><span>On
9/7/2017 5:22 AM, Piotr Machacz wrote:</span></p>
</div>
<blockquote>
<p class="MsoNormal"><span>I
don’t think LyreBird will ever be able to make local
voices, SAPI or otherwise.
At least not in the near future. The way I understand
it, their system uses a
massive GPU cluster to run a neural net that gets
trained on people’s voices
(this is why if you make enough recordings it learns
to mimic you so well). It
literally makes connections and figures out patterns
like a human brain. If you
were to run something like this on a single home
computer, even one with a
beefy CPU or preferably a good high end GPU, I imagine
it would take days to
train, and then minutes if not a few hours to generate
1 clip of speech. That
being said, neural nets are getting more and more
common and are started to be
used on a small scale on computers or phones, and some
companies like Microsoft
or Google are developing processor chips designed
specifically for neural nets.
So maybe you’ll see this become an offline technology
in a few years. For now,
we know that lyrebird wants to make an API available
for this technology, so
you can expect apps and websites to make use of it (IE
a chatting website might
let you enter your voice fingerprint and then you can
talk to other people by
typing text and getting your actual voice out, or
perhaps getting news or
weather spoken to you with your own voice)</span></p>
<div>
<p class="MsoNormal"><span> </span></p>
<blockquote>
<div>
<p class="MsoNormal"><span>On
7 Sep 2017, at 11:13, Jayson Smith <<a
href="mailto:jaybird@bluegrasspals.com"
moz-do-not-send="true">jaybird@bluegrasspals.com</a>>
wrote:</span></p>
</div>
<p class="MsoNormal"><span> </span></p>
<div>
<div>
<p class="MsoNormal"><span>Hi,<br>
<br>
I don't know of any other voice creation
program which can make a SAPI voice.
If you still have the original recordings, and
you still own the copyright in
and to them I.E. you didn't sign some sort of
agreement giving all your rights
to Innoetics, you should in theory be able to
use such a service if one were to
exist at some point in the future. You might
try contacting Lyrebird and
explaining your situation, see what they say.<br>
<br>
Sorry I can't be of more help,<br>
<br>
Jayson<br>
<br>
On 9/6/2017 3:03 PM, Blake Roberts wrote:<br>
> Lyrebird sounds interesting. I notice
that in FAQ Lyrebird says they</span></p>
<p class="MsoNormal"><span>>
can create a higher-quality voice if I have a
lot of recordings but</span></p>
<p class="MsoNormal"><span>>
this is not available in the current beta. On
a related topic, let me</span></p>
<p class="MsoNormal"><span>>
put all my cards on the table. Before
Innoetics was acquired by</span></p>
<p class="MsoNormal"><span>>
Samsung, I was creating a SAPI of myself with
help from a innoetics</span></p>
<p class="MsoNormal"><span>>
founder. In July 2017 around the time of
Samsung's acquisition of the</span></p>
<p class="MsoNormal"><span>>
company, the Innoetics founder told me he
would send me a SAPI of my</span></p>
<p class="MsoNormal"><span>>
voice using the thousands of sentences I
recorded. Due to no SAPI</span></p>
<p class="MsoNormal"><span>>
received after almost 2 months from that
promise, I'm thinking the</span></p>
<p class="MsoNormal"><span>>
Innoetics founder whom I won't specify
on-list might not be able to</span></p>
<p class="MsoNormal"><span>>
create Blake Sapi. I'm not trying to sound
critical of the indivudal.</span></p>
<p class="MsoNormal"><span>>
I'm just accepting the possibility that
aforementioned promise might</span></p>
<p class="MsoNormal"><span>>
not be fulfilled. Does anyone know of a voice
creation program which</span></p>
<p class="MsoNormal"><span>>
can create a SAPI from already recorded
sentence wave files? I spent</span></p>
<p class="MsoNormal"><span>>
many hours and months recording over a
thousand sentences for the</span></p>
<p class="MsoNormal"><span>>
aforementioned Innoetics Blake Sapi. I did the
recording at no</span></p>
<p class="MsoNormal"><span>>
financial cost for personal/friends use. I
don't want my time/effort</span></p>
<p class="MsoNormal"><span>>
to be wasted. Blake</span></p>
<p class="MsoNormal"><span>>
</span></p>
<p class="MsoNormal"><span>>
-----Original Message----- From: Dectalk</span></p>
<p class="MsoNormal"><span>>
[<a
href="mailto:dectalk-bounces@bluegrasspals.com"
moz-do-not-send="true">mailto:dectalk-bounces@bluegrasspals.com</a>]
On Behalf Of Jayson Smith </span></p>
<p class="MsoNormal"><span>>
Sent: Wednesday, September 06, 2017 12:20 PM
To: DECtalk
Discussions </span></p>
<p class="MsoNormal"><span>>
Subject: [DECtalk] Lyrebird TTS, a
demo is finally here!</span></p>
<p class="MsoNormal"><span>>
</span></p>
<p class="MsoNormal"><span>>
Hi all,</span></p>
<p class="MsoNormal"><span>>
</span></p>
<p class="MsoNormal"><span>>
</span></p>
<p class="MsoNormal"><span>>
A few months ago, I heard about Lyrebird, a
future project which</span></p>
<p class="MsoNormal"><span>>
would allow anyone to create a synthetic clone
of their own voice.</span></p>
<p class="MsoNormal"><span>>
Last night I found out that it's finally here,
in an early beta form.</span></p>
<p class="MsoNormal"><span>>
If you go to <a href="http://lyrebird.ai/"
moz-do-not-send="true">http://lyrebird.ai</a>
and create an
account, you can then</span></p>
<p class="MsoNormal"><span>>
record a minimum of thirty sentences they
specify, the more you</span></p>
<p class="MsoNormal"><span>>
record the better, and then create your
digital voice. Then you can</span></p>
<p class="MsoNormal"><span>>
have it speak any text you choose. I've played
with it, and while the</span></p>
<p class="MsoNormal"><span>>
quality isn't the best, it does pretty
accurately capture my voice,</span></p>
<p class="MsoNormal"><span>>
as well as most of the other people I know of
who have created</span></p>
<p class="MsoNormal"><span>>
voices. Check it out!</span></p>
<p class="MsoNormal"><span>>
</span></p>
<p class="MsoNormal"><span>>
</span></p>
<p class="MsoNormal"><span>>
Jayson</span></p>
<p class="MsoNormal"><span>>
</span></p>
<p class="MsoNormal"><span>>
</span></p>
<p class="MsoNormal"><span>>
_______________________________________________ Dectalk mailing list </span></p>
<p class="MsoNormal"><span>>
<a href="mailto:Dectalk@bluegrasspals.com"
moz-do-not-send="true">Dectalk@bluegrasspals.com</a>
</span></p>
<p class="MsoNormal"><span>>
<a
href="http://bluegrasspals.com/mailman/listinfo/dectalk"
moz-do-not-send="true">http://bluegrasspals.com/mailman/listinfo/dectalk</a></span></p>
<p class="MsoNormal"><span>>
</span></p>
<p class="MsoNormal"><span>>
_______________________________________________ Dectalk mailing list </span></p>
<p class="MsoNormal"><span>>
<a href="mailto:Dectalk@bluegrasspals.com"
moz-do-not-send="true">Dectalk@bluegrasspals.com</a>
</span></p>
<p class="MsoNormal"><span>>
<a
href="http://bluegrasspals.com/mailman/listinfo/dectalk"
moz-do-not-send="true">http://bluegrasspals.com/mailman/listinfo/dectalk</a></span></p>
<p class="MsoNormal"><span>>
</span></p>
<p class="MsoNormal"><span>> </span></p>
</div>
<p class="MsoNormal"><span>_______________________________________________<br>
Dectalk mailing list<br>
<a href="mailto:Dectalk@bluegrasspals.com"
moz-do-not-send="true">Dectalk@bluegrasspals.com</a><br>
<a
href="http://bluegrasspals.com/mailman/listinfo/dectalk"
moz-do-not-send="true">http://bluegrasspals.com/mailman/listinfo/dectalk</a></span></p>
</div>
</blockquote>
</div>
<p class="MsoNormal"><span><br>
<br>
<br>
</span></p>
<pre><span>_______________________________________________</span></pre>
<pre><span>Dectalk mailing list</span></pre>
<pre><span><a href="mailto:Dectalk@bluegrasspals.com" moz-do-not-send="true">Dectalk@bluegrasspals.com</a></span></pre>
<pre><span><a href="http://bluegrasspals.com/mailman/listinfo/dectalk" moz-do-not-send="true">http://bluegrasspals.com/mailman/listinfo/dectalk</a></span></pre>
</blockquote>
<p class="MsoNormal"><span> </span></p>
</div>
</blockquote>
<p class="MsoNormal"><span>_______________________________________________<br>
Dectalk mailing list<br>
<a href="mailto:Dectalk@bluegrasspals.com"
moz-do-not-send="true">Dectalk@bluegrasspals.com</a><br>
<a href="http://bluegrasspals.com/mailman/listinfo/dectalk"
moz-do-not-send="true">http://bluegrasspals.com/mailman/listinfo/dectalk</a></span></p>
<p class="MsoNormal"><span> </span></p>
</div>
<br>
<fieldset class="mimeAttachmentHeader"></fieldset>
<br>
<pre wrap="">_______________________________________________
Dectalk mailing list
<a class="moz-txt-link-abbreviated" href="mailto:Dectalk@bluegrasspals.com">Dectalk@bluegrasspals.com</a>
<a class="moz-txt-link-freetext" href="http://bluegrasspals.com/mailman/listinfo/dectalk">http://bluegrasspals.com/mailman/listinfo/dectalk</a>
</pre>
</blockquote>
<br>
</body>
</html>