Re: Need to hire a software developer for a voice processing app!
Re: Need to hire a software developer for a voice processing app!
- Subject: Re: Need to hire a software developer for a voice processing app!
- From: Richard Dobson <email@hidden>
- Date: Sat, 20 Feb 2010 14:28:03 +0000
On 20/02/2010 12:45, contact wrote:
..
The free dspdimension code is expensive on CPU, and a wonderful
misdirection on how to do pitch shifting (but that's another story!).
Optimised implementations (not least of the FFT itself) are ~very much~
faster, and of course that technique is targetted at arbitrary sounds
(polyphonic, inharmonic sounds, whole orchestras etc), maybe OTT for use
on monophonic pitched sounds and speech, where techniques such as PSOLA
can shine; but so can other f/d techniques such as Ceptstral analysis.
A PSOLA algorithm is probably going to be the answer, especially as the
fundamental frequency is going to be needed in the future.
It also solves the issue of formant preserving, which I presume is
automatically needed - and can be an expensive step for vocoders.
So a demonstation of real-time pitch marking would be the first task for
the
phone app, me thinks.
Indeed. And of course there are already numerous examples in published
apps implementing tuning meters, etc. Such decisions can often hang not
only on the efficiency of a given technique, but on what other
analytical features (such as spectral envelope, formant analysis etc)
may be required later on.
Richard Dobson
_______________________________________________
Do not post admin requests to the list. They will be ignored.
Coreaudio-api mailing list (email@hidden)
Help/Unsubscribe/Update your Subscription:
This email sent to email@hidden