voice acting software?

[DGMacphee]

but as DG so kindly [read: sarcastically/fantasizingly] put it

What can I say? I'm a man with very deep desires. 

Also, how does one define the voice of certain male Simpsons characters, like Bart Simpson, Ralph Wiggum, and Jimbo Jones, when they're all performed by the same voice actress, Nancy Cartwright?

What about Brad Bird performing the voice of Edna Mode in The Incredibles?

[Sylpher]

if a human can recognize the distiction between a male and female voice, than so can a turing machine.  if a human can synthesize a sound that can be represented in digital form, than so can a turing machine.  there's nothing theoretically stopping perfect synthesis of words from text by a computer.  if the distinction between male and female can be determined, then the change can also be made...this isn't even debatable!

Hm, is it a common practice for you to form an idea in about 15 secs and solidify it as unquestionable fact? Just curious...

The flaw in your logic is you see being able to distinguish a male and females voice and being able to manipulate it as the same thing. I think you need to do a bit more studying on the complexity of the human vocal chords before making such rash statements. As well reading up on how software audio manipulation works wouldn't hurt.

Which you probobly won't, so... You may want to at least go back and read some of the perfectly acceptable solutions suggested within your range of options in this very thread.

[InCreator]

Eh, actually resyntesizing human voice is really big waste of lifetime.

This is why people invented alternate ways to do it:

Couple of beers and ask some friends - guys/chicks to come over.
When they're there, just give em' hell until they learn to act properly.

Then use microphone.

[Fuzzpilz]

stuh: "Theoretical barrier" doesn't necessarily mean "IMPOSSIBLE! IMPOSSIBLE! IMPOSSIBLE!". It does, however, mean "IMPOSSIBLE! IMPOSSIBLE! At least without insane advances in AI, for example!", in this case. There are, as DarkStalkey mentioned, pitch shifters that can alter the pitch of a sound and its formants independently, so we have something a little better than just speeding things up or slowing them down. They're still not all that useful for your purposes if you don't do your own acting, though, and their range is limited (not even talking about quality - that's a whole different issue).

if the distinction between male and female can be determined, then the change can also be made...

The difference is harder to tell than you think, though I wouldn't necessarily call it impossible with today's technology - and making the change doesn't magically follow from it. It's all the more impossible with emotional content - there are so many things to consider. Little sounds on the edge of speech. Short transitions to, oh, shouting or growling or whispering or wailing or almost doing one of these at fitting points of the text. And there are too many different ways to do each of these, all kinds of little details that make up an individual's voice.

This means that even if we had the technology for all that, you'd most likely still have to keep track of a large amount of parameter and do much of the work yourself by sequencing this or that, adjusting transitions... and on top of that it's a lot harder to do that to a recording than to synthesise it outright. Maybe we'll start seeing software for that in a few years, and perhaps it'll sound almost acceptable after a while.

I don't recommend holding your breath.

[stuh505]

I don't need to be lectured on the difficulties involved.  In my electrical engineering and computer science courses, I've picked up a few things.  I never said it would be an easy task.  And yes, it would be beneficial for me to learn more about the subject of AI and such..which is why I am doing research this summer at TAMU on artifically intelligent systems, as well as doing a thesis on more intelligent chess algorithms...but all that's really beside the point.  You can call me an idiot all you want but anyone who doesn't recognize that what I suggest is entirely possible and plausible simply needs to stop thinking within the boundaries of current technology.  Honestly, a computer is capable of producing bits which represent any sound...and the bit patterns that represent speech must follow certain rules...and no matter how complex those rules may be, if we knew all of those rules, we could do it.  There's no theoretical limitation on what rules we can learn.  But this is really a very separate topic from my original post on this thread so don't get them confused--

I wasn't expecting some magic software, but using current technology, there could be presets set to run certain fourier transforms and pitch adjustments etc, that would produce moderate effects...better than I might be able to do by manually adjusting these things without any knowledge of what pitch range etc different people talk in.

[Fuzzpilz]

If you ask for existing programs, you can't blame people for "thinking within the boundaries of current technology". That's absurd. You specifically asked for software to do your emoting for you. Sorry, but within the boundaries of current technology, that's also absurd.

[stuh505]

Fuzzpilz,

like I said, there are 2 entirely different topics going on here...and people keep mixing them up.  One of them is about the theoretical limits of computation...the other is about current software.

[Sylpher]

The best you are going to get out of current technology is some pitch-shifting and some other minor manipulation. Is that clear enough?

[TheYak]

Agreed.  As far as current or soon-to-come software goes, you're SOL.  Even if decent equivalents exist they would be exorbitantly priced.  However, there are modifications you can make to a recording (whether it's your own falsetto voice or a friend's) to make it at least nearly acceptable. 

Rather that debate the probability of such a thing, why not make it more productive and get some attempts and submissions in this thread?  I, for one, am thinking of giving this a go and seeing how it turns out.

[SSH]

if a human can recognize the distiction between a male and female voice, than so can a turing machine.  if a human can synthesize a sound that can be represented in digital form, than so can a turing machine.  there's nothing theoretically stopping perfect synthesis of words from text by a computer.  if the distinction between male and female can be determined, then the change can also be made...this isn't even debatable!  I'm not saying we have this technology now or that we ever will.

By your logic, if a human can recognise the 'distiction' between fellatio and cunnilingus, then my computer should be giving me free blowjobs as we speak.

technology is nearly there

[Adamski]

Since when were there two discussions going on in here? And if you're going to ask rediculous questions and don't want to grasp the simple 'no' answer then you should expect people to point out exactly why such a thing isn't possible. No need to be an arse about it.