This is basically what the speech recognition programs do. That is, I
think they're based on transformed signals --- the earliest ones were.
The programs that are moderately effective depend on training to learn
to recognize the voice of one person (because we're so variable from
person to person) and do a lot of data sorting and matching as well as
basic signal analysis.
There are some free software packages available that you can experiment
with, but I haven't tried any and couldn't recommend one.
Michael Dalton wrote:
>
>
> To all recordists,
>
> Recent discussion concerning spectrograms prompts the following: I've
> been making spectrograms of speech, does anyone in the group have the
> ability to transcribe into English what was said directly from a
> spectrogram of the phrase or sentence?
>
> Mike
>
>
>
>
> ------------------------------------------------------------------------
>
> No virus found in this incoming message.
> Checked by AVG Free Edition.
> Version: 7.1.394 / Virus Database: 268.8.4/363 - Release Date: 6/13/2006
|