gnuspeech-contact
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [gnuspeech-contact] Re: Waveform comparison


From: David Hill
Subject: Re: [gnuspeech-contact] Re: Waveform comparison
Date: Sat, 5 Mar 2011 13:03:13 -0800

Hi Felipe,

On Mar 5, 2011, at 5:22 AM, Felipe Castro wrote:

Ok, David. So, no need for waveform visualization, anyway.
And the spectrograph bar in the Synthesizer should be really useful, but it doesn't work for me.

That is strange. I wonder if the grey scale data is actually included in the build code that is compiled under GNUStep. If it isn't, the spectrograph bar would not work. There should be 101 tiff images, each one a line the width of the spectrograph bar, covering the density range from 00 (full white) to 100 (full black). The other possibility is a bug in the density indexing that only shows up in the GNUStep version. Or maybe something to do with the makefile not accessing that data, assuming there is a makefile (or lack of a make file)?

It works just fine in the Mac OS X compilation.

I'll search about that "cepstral" analysis thing and other stuff related to voice recognition.

For what purpose would you be using Cepstral analysis?

Warm regards.

david


Thanks for the clarifications,
Felipe Castro.


2011/3/4 David Hill <address@hidden>
Hi again, Felipe,

In your last, you wrote:

Yes, one or two repetitive cycles should be enough, to compare with real speech. Though it would be useful only for the vowels, and for refinements, optimization, etc, in order to approach specific voices.
My idea is to "mimic" someone's voices, in the future. I could have, for example, Maddona singing in Esperanto? Hehehe...

In fact a comparison of the speech waveform is not very helpful in imitating a particular speaker's voice. This is because it is the spectral content, pitch pulse shape and changing frequency, and the spectral dynamics, that are the main determinants of similarity. The speech waveform can vary significantly without changing the perception of similarity because the speech waveform also depends very much on the phase relations of the harmonic components and the human ear is not really sensitive to phase.

Warm regards.

david

--------


_______________________________________________
gnuspeech-contact mailing list
address@hidden
http://lists.gnu.org/mailman/listinfo/gnuspeech-contact


reply via email to

[Prev in Thread] Current Thread [Next in Thread]