The Short Time Fourier Transform (STFT) constructs the instantaneous spectrum of an observed dataset after applying a temporal taper for the sake of micro-Doppler feature extraction. Here, the temporal window applied to the STFT is adjusted proportionally to the instantaneous periodicity of the dataset as to establish more consistent UAV micro-Doppler signatures and improve the separability of relevant features. The outlined approach is developed in the context of UAV rotor blade analysis. Techniques for estimating the periodicity of the radar returns and examining the temporal correlation of the signal are presented. To demonstrate the efficacy of the proposed data-driven STFT algorithm, simulated and experimentally measured results of UAV rotor blades are analyzed.