An unusual question

2 posts in this topic


I'm a Computer Science student and I have a question to do to you. Is there a way to recreate a voice of a person ? I'll try to explain myself better. I want to recreate a person's voice starting from his voice recording. I think starting from the frequency of her voice. I have no idea where to start and looking on the internet I've found this forum, hoping that any of you can help me at least to know if this is feasible or not. Thank you.

Share this post

Link to post
Share on other sites

Hey Null pointer

this is really a difficult one, but very interesting, one day while i was dreaming in my school i was wondering if i would be able to make words from violin if I played many notes at ones, so in my next music class i took this to my music teacher, he told me to dream on and i might find a solution.

turns out you can, but not with many violin's no. 

Sound are made by combining many different frequencies, you can understand the break up of these if you use a program like reaper. 
than i came across some statical model used data science which can be used to predict with up to 97% accuracy on the next step (problem is you need the frequencies to be converted to numbers) 

the computational power required to do this math will not be available in a mobile now so this tech will not be portable
so that mean it will not have large scale application and companies like yamaha, zoom, roland will not be intreasting in producing it. 

now your only bet is getting into R&D., 


Share this post

Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now