![](/i/fill.gif) |
![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
http://www.youtube.com/watch?v=_12b6Om758Q&feature=related
The accent is kind of cute.
--
Tim Cook
http://empyrean.freesitespace.net
Post a reply to this message
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
Tim Cook wrote:
> http://www.youtube.com/watch?v=_12b6Om758Q&feature=related
> The accent is kind of cute.
It was interesting going through the "director's commentary" version. Lots
of interesting insight into what goes into video games.
For the voice, they had a speech synthesizer say the lines, then asked the
voice actress to speak the lines the same way, then post-processed the real
voice to sound like a computer. Kind of a round-about way of doing it.
--
Darren New, San Diego CA, USA (PST)
Forget "focus follows mouse." When do
I get "focus follows gaze"?
Post a reply to this message
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
Darren New <dne### [at] san rr com> wrote:
> For the voice, they had a speech synthesizer say the lines, then asked the
> voice actress to speak the lines the same way, then post-processed the real
> voice to sound like a computer. Kind of a round-about way of doing it.
I would be surprised if they would have been able to do it purely with
software. I don't think text-to-speech is that advanced yet.
--
- Warp
Post a reply to this message
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
Warp wrote:
> Darren New <dne### [at] san rr com> wrote:
>> For the voice, they had a speech synthesizer say the lines, then asked the
>> voice actress to speak the lines the same way, then post-processed the real
>> voice to sound like a computer. Kind of a round-about way of doing it.
>
> I would be surprised if they would have been able to do it purely with
> software. I don't think text-to-speech is that advanced yet.
In case you hadn't noticed or weren't aware of it, Vocaloid is a program
that takes a library of sounds made by a person and lets you string them
together arbitrarily to create a synthetic version of that person. It's
a ways off from sounding truly accurate, but it's a step up from MS Sam.
http://en.wikipedia.org/wiki/Vocaloid
Whole load of youtube videos with it.
--
Tim Cook
http://empyrean.freesitespace.net
Post a reply to this message
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
Tim Cook <z99### [at] gmail com> wrote:
> Warp wrote:
> > Darren New <dne### [at] san rr com> wrote:
> >> For the voice, they had a speech synthesizer say the lines, then asked the
> >> voice actress to speak the lines the same way, then post-processed the real
> >> voice to sound like a computer. Kind of a round-about way of doing it.
> >
> > I would be surprised if they would have been able to do it purely with
> > software. I don't think text-to-speech is that advanced yet.
> In case you hadn't noticed or weren't aware of it, Vocaloid is a program
> that takes a library of sounds made by a person and lets you string them
> together arbitrarily to create a synthetic version of that person. It's
> a ways off from sounding truly accurate, but it's a step up from MS Sam.
Which proves the point I made.
--
- Warp
Post a reply to this message
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
Warp wrote:
> Which proves the point I made.
Amusingly, the voices that are more synthetic-sounding are more
appealing than the 'realistic' ones. Sort of an uncanny valley thing, I
suppose?
--
Tim Cook
http://empyrean.freesitespace.net
Post a reply to this message
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
Warp wrote:
> I would be surprised if they would have been able to do it purely with
> software. I don't think text-to-speech is that advanced yet.
No no. It's definitely worth getting a voice actor. I was just amused that
they *first* used text-to-speech to tell the voice actor what they wanted it
to sound like. :)
--
Darren New, San Diego CA, USA (PST)
Forget "focus follows mouse." When do
I get "focus follows gaze"?
Post a reply to this message
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
Tim Cook wrote:
> http://en.wikipedia.org/wiki/Vocaloid
That makes your link *much* more amusing. :-)
--
Darren New, San Diego CA, USA (PST)
Forget "focus follows mouse." When do
I get "focus follows gaze"?
Post a reply to this message
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
Tim Cook wrote:
> Warp wrote:
>> Darren New <dne### [at] san rr com> wrote:
>>> For the voice, they had a speech synthesizer say the lines, then
>>> asked the voice actress to speak the lines the same way, then
>>> post-processed the real voice to sound like a computer. Kind of a
>>> round-about way of doing it.
>>
>> I would be surprised if they would have been able to do it purely with
>> software. I don't think text-to-speech is that advanced yet.
>
> In case you hadn't noticed or weren't aware of it, Vocaloid is a program
> that takes a library of sounds made by a person and lets you string them
> together arbitrarily to create a synthetic version of that person. It's
> a ways off from sounding truly accurate, but it's a step up from MS Sam.
>
> http://en.wikipedia.org/wiki/Vocaloid
>
> Whole load of youtube videos with it.
Vocaloid works great with the limited phonetic set of Japanese. I have
not heard any of them sing in English convincingly.
Post a reply to this message
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |
| ![](/i/fill.gif) |
|
![](/i/fill.gif) |
|
![](/i/fill.gif) |
| ![](/i/fill.gif) |