Micro-Doppler signatures (μ-DS) are widely used for human activity recognition (HAR) using radar. However, traditional methods for generating μ-DS, such as the Short-Time Fourier Transform (STFT), suffer from limitations, such as the trade-off between time and frequency resolution, noise sensitivity, and parameter calibration. To address these limitations, we propose a novel deep learning-based approach to reconstruct high-resolution μ-DS directly from 1D complex time-domain signal. Our deep learning architecture consists of an autoencoder block to improve signal-to-noise ratio (SNR), an STFT block to learn frequency transformations to generate pseudo spectrograms, and finally, a UNET block to reconstruct high-resolution spectrogram images. We evaluated our proposed architecture on both synthetic and real-world data. For synthetic data, we generated 1D complex time domain signals with multiple time-varying frequencies and evaluated and compared the ability of our network to generate high-resolution μ-DS and perform in different SNR levels. For real-world data, a challenging radar-based American Sign Language (ASL) dataset consisting of 100 words was used to evaluate the classification performance achieved using the μ-DS generated by the proposed approach. The results showed that the proposed approach outperforms the classification accuracy of traditional STFT-based μ-DS by 3.48%. Both synthetic and experimental μ-DS show that the proposed approach learns to reconstruct higher-resolution and sparser spectrograms.