It’s been a half century since single sideband (SSB) supplanted amplitude modulation (AM) as the most popular voice mode on HF, due largely to its spectrum efficiency, occupying roughly half the bandwidth of an AM signal. Now, there’s a new digital voice mode from FreeDV called Radio Autoencoder, or RADE, that occupies half the bandwidth of an SSB signal and reportedly provides more natural-sounding speech. According to Amateur Radio Digital Communications (ARDC), which funded research that advanced RADE’s development, “FreeDV RADE combines machine learning with classical digital signal processing (DSP) and can operate at signal-to-noise ratios (SNRs) as low as -2 dB. Its design also addresses spectrum use, speech quality, and power efficiency, all important considerations for voice communications over HF.”

Most significantly, ARDC reports that manufacturers are beginning to integrate the mode directly into their radios, starting with a module that can be downloaded and installed on certain FlexRadio models. Users of other transceivers may run the mode through computers connected to their radios. More details are available from FreeDV and on the ARDC website.