[Speex-dev] Digital speech within 100 Hz bandwidth

[LWATCDR]

I just read your paper and this would be close to trivial to do but
almost useless.  If you really want you could cobble together a
prototype with off the self software.
http://cmusphinx.sourceforge.net/html/cmusphinx.php is a FOSS speech
recognition program. That will effectively convert the audio into
phenoms. Most voice synthesizers have a text to phoneme translator so
that code is available.
Just use any number of voice synthesizers to provide play back.

The real issue is why? You could just read the text if you wanted and
not use the synthesizer at all. Buy just transmitting the phonemes you
will loose inflection.
I actually thought about the same thing about ten or fifteen years ago.



On Tue, Aug 12, 2008 at 6:30 PM, Mike Lebo <mike.lebo at gmail.com> wrote:
> Dear Sir,
>
> Could you please forward this e-mail to your  engineering department. I am a
> ham radio person who wants to transmit from the Earth to the moon and back
> to the Earth by phone not by Morris code. This will be a very weak signal. I
> need an extra 13.8 dB of gain. Could you please help me distribute the
> attached paper to someone who could take this project into the next level?
>
> Please reply to this e-mail.
>
> 73's
>
> Mike    n6ief
> _______________________________________________
> Speex-dev mailing list
> Speex-dev at xiph.org
> http://lists.xiph.org/mailman/listinfo/speex-dev
>
>