19 September 2025 in IEEE Communications Letters
Frequency modulation (FM) is widely used in broadcasting and IoT audio for its simplicity and low cost, yet remains susceptible to noise. We present DeepFM, a hybrid digital–analog system that supplements FM with a low-rate semantic side channel. A neural encoder compresses audio into quantized features sent alongside the FM signal. A channel-aware decoder fuses semantic bits, noisy analog input, and RSSI to restore high-fidelity audio. Evaluated on our SFR dataset at 0.5–12 kbps, DeepFM outperforms leading neural codecs in mainstream speech-quality metrics, particularly at low–medium bitrates (0.5–3 kbps). DeepFM demonstrates robust, real-time performance compatible with legacy FM infrastructure.