Greg, interesting though on speaker dependent fine tuned decoders (I
think that's what you meant ?). Would mean for you buddies you could
store something different and buy them another half dB on their
transmit power bill.
and suitable implementation for some other optimised band/propagation
might not even be OFDM, though that the PAPR 'problem' has been
mitigated, might now be a more generalized implementation (although
there wont be something for nothing).
fascinating . the use of bottleneck algorthmic contraints to control
amplitude distribution...
wondering about embedded implementation...
According to the paper https://arxiv.org/pdf/2505.06671
Vocoder computational workload of about 300MMACS isnt too bad at all.
FARGIN paper and site with FARGIN at 600 FLOPS sounds amazing
https://ahmed-fau.github.io/fargan_demo/
On 16/08/2025 17:12, Greg Maxwell wrote:
There is also non-trivial channel specific DSP development likely
needed too, not just ML training-- as the ML still relies on the
receiver managing to sync and track the signal. Maybe a ML only
adjustment for a different channel would be better than doing nothing,
but it probably won't get particularly close to the results you'd get
with some more direct engineering.
Another fun potential avenue that would avoid more of the human
engineered parts: -- for when you know the speaker, hold the RADE
encoder constant but fine tune the decoder for a particular parties
voice. Might improve the threshold for intelligibility by some
fraction of the channel capacity wasted communicating that info,
entirely unlike the advanced decoding in WSJTX is able to exploit the
assumption that the callsign of the current message you're
receiving is more likely the callsign that you just called.
On Sat, Aug 16, 2025 at 6:58 AM glen english LIST
<glenl...@cortexrf.com.au> wrote:
Hi David
Have just read all the papers.. as i read it ,
(https://arxiv.org/pdf/2505.06671)
we could alternatively train the system for say aurora channel
characteristsics on 2m , or rainscatter characteristics on 10 GHz
and could expand or use different training sets for different
propagation modes on different bands,
....depending on how general they are.
IE this is a workiong deomonstration for AWGN and HF style
multipath channels, but not at all limited it
best regards
-glen
_______________________________________________
Freetel-codec2 mailing list
Freetel-codec2@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/freetel-codec2
