End to End Deep Neural Network Frequency Demodulation of Speech Signals
This addresses improved speech signal recovery in FM broadcasting for communication systems, but appears incremental as it applies deep learning to a known problem.
The paper tackles FM demodulation of speech signals by proposing an end-to-end deep learning-based SDR receiver that uses prior speech information, achieving high performance in noisy conditions and outperforming established methods at low SNR in MSE and perceptual quality scores.
Frequency modulation (FM) is a form of radio broadcasting which is widely used nowadays and has been for almost a century. We suggest a software-defined-radio (SDR) receiver for FM demodulation that adopts an end-to-end learning based approach and utilizes the prior information of transmitted speech message in the demodulation process. The receiver detects and enhances speech from the in-phase and quadrature components of its base band version. The new system yields high performance detection for both acoustical disturbances, and communication channel noise and is foreseen to out-perform the established methods for low signal to noise ratio (SNR) conditions in both mean square error and in perceptual evaluation of speech quality score.