From mid-August to mid-September 2024, we conducted a Radio Autoencoder (RADE) test campaign as described in the “Over the Air Demonstration” section of the paper.

Ten Amateur Radio operators joined our test group, with many submitting stored file results. In particular we would like to thank Mooneer K6AQ, Walter K5WH, Rick W7YC, Yuichi JH0VEQ, Lee BX4ACP, and Simon DJ2LS for posting many useful samples, and for collecting samples of voices other than their own to test.

1. It works well with most speakers, with the exception of one voice tested. 
2. Some of the samples suggest acquisition issues on certain very long distance channels, but this issue seems to be an outlier, perhaps an area for further work.
3. RADE works well on high and low SNR channels.  In both cases the speech quality is competitive with SSB.
4. It works on local (groundwave), NVIS, and International DX channels. It works well for (most) males and females, across several languages.

Selected Samples

We collected around 50 samples, here are just a few that we have selected as good examples.

Our stored file test system sent SSB and RADE versions immediately after each other, so the channel is approximately the same. Both SSB and RADE have the same peak power, and the SSB is compressed to around 6dB Peak to Average Power Ratio (PAPR). In each audio sample below, SSB is presented first.

Here is a sample of Joey K5CJ, provided by Rick W7YC. The path is over 13,680km, from Texas, USA to New South Wales, Australia (VK2), on just 25W. Measured SNR was 4dB. Note the fading in the spectrogram, you can hear RADE lose sync then recover through the fade.

Using another sample of Joey, K5CJ (also at 25W), Rick has provided a novel way to compare the samples:

He writes:

RADE is in the (R) channel & analog SSB is in the (L) left channel. Listen using stereo speakers, and slide the balance control L-R to hear the impact. Or, listen to it on your smart phone & alternately remove the L & R earbuds – wow. It demonstrates how very well RADE does over a 13,680 km path!

Here is Lee, BX4ACP, sending signals from Taiwan to Thailand in a mixture of English and Chinese using 100W. The measured SNR was 5dB, and frequency selective “barber pole” fading can be seen on the spectrogram.

Here is Yuriko (wife of Yuichi JH0VEQ) using 100W over a 846 km path from Niigata Prefecture to Oita Prefecture in Japan. The reported SNR was just 2dB. From the spectrogram of the RADE signal, the channel looks quite benign with no obvious fading. However we note the chirp at the start has a few “pieces missing”, which suggests the reported SNR was lower than the SNR experienced by the RADE signal a few seconds later.