voice morph

[MadMax_911]

Is there a software that can take a clean voice recording of one person, compare it to another by me where I say the exact same phrase and calculate how my voice should be "morphed" to sound like the first one?

[Supreme2k]

Sounds like someone is in the market to fake some evidence

I think Goldwave will do that

[MadMax_911]

Actually I'm fixing the auio to an old film for my sister where she did a voice over as a child. in one place I need to replace her voice due to very loud annoying background sounds. It wouldn't be the same if the voice is different for just this part.

I'll try out goldwave what function should I use?

[guns1inger]

Have you watched the restored version of The Good, The Bad and The Ugly ? An 80 year old Eli Wallach just doesn't sound like the 30 year old Tuco, no matter how much processing they applied.

[MadMax_911]

I'm just hoping that I can create something that will sound close to the original and blend in well with the voice before and after. It will anyway be better than to record another voice for this part.

[anubis13]

Cleaning up the noise might be easier than recreating the voice

[Marvingj]

Try Besweet ......

[MadMax_911]

How can I do that with besweet isn't that just for transcoding??
Cleanup is impossible atleast for me. The background sounds are as her voice in mono and loud in the same frequencies as the voice. So I can't remove it by any kind of vocal removal/isolation software. So replacing the audio completely for that part seems to be the best solution.

[Marvingj]

NO, Besweet can do alot of differents but I don't have a guide for but I've somethings in the past with it. But here something thats a little easy.....Audacity has a great built-in noise reduction tool. To get it to do its job properly, you need to get your hands a bit dirty. So, first you need to get a noise profile. A noise profile lets Audacity recognize what noise actually is. The profile also gives Audacity a baseline from which to work.

To get a good noise profile, you need to find a section of the audio file in which there's no talking. You can recognize this because it appears as a flat line in Audacity. Several seconds worth of dead air is best. If you don't have that much, use what you can.

By clicking and dragging with your mouse, Thats it!

[gadgetguy]

As long as you're in Audacity you can play with the "Change Pitch" filter and try your new recording. You may be able to make it sound like a little girl, but I doubt you can make it sound like your sister. What might get better results is if you start with a clean recording from your sister and adjust the pitch from that to try to match her "young" voice.

[MadMax_911]

The "noise" is music and other persons talking loud and cheering in the background. Somehow these "background" sounds are louder than the person holding the microphone and they are drowning her voice. I've used every type of noise reduction and voice isolation software I can think of but the results are not acceptable.
I'm getting a new clean recording of both my sister and her daughter in a couple of weeks. (This time They'll also send a reference recording where they "match" a 7 second clean recording.)
Last try I made with my sister's voice I found that just pitch won't work I tried a trial of a voice changer but there were like 4 or 5 settings I didn't understand what they actually did. I'm trying to find a software that can roughly adjust these other settings to match a reference clip.

[JerryB]

hi,
my 2 cents worth....
1. first... your talking about morphin... however that is a very broad term and encompacesa big field, so need something more specific..... the kind or morphin your looking for is ie; voice transformations, voice imitation, voice translation ... type morphin...

2. now you can, like some one mentioned previously use a program like audacity and adjust manually the pitch, tonal quality, tempo.....

3. however... there is a fair amount voice morphin software out there..... some of it can be pricy..... so what you want is something like a imitation morphine software..... what they do... is they first analyze the orginal voice segment .. (in your case you would take a good clean voice segment from the tape) and it will analyze the characteristics of the orginal and thena person would make a new clip and the the software will convert/morph the new person into the target person voice....
i don't have no recommendations on which software to use.. but this search results has a few software that does what I mentioned.... and you may want to use different search criterias to find better pricess....
http://search.yahoo.com/search;_ylt=A0geu6AMEL5GlSAABllXNyoA?p=voice+imitation+software&fr=yfp-t-471

4. note: in my research.. i noticed several papers where research was being done to incorpoate into kararoki... basically a person sings into the mike and the output is in the voice of thier favorite singer.. smile.....

any way those are my thoughts hope there helpfull good luck and have fun..

Is there a software that can take a clean voice recording of one person, compare it to another by me where I say the exact same phrase and calculate how my voice should be "morphed" to sound like the first one?