We introduce a data-driven approach for extracting two-level system (TLS) parameters–frequency (Formula presented.), coupling strength (Formula presented.), dissipation time (Formula presented.), and the pure dephasing time (Formula presented.), labeled as a 4 component vector (Formula presented.), directly from simulated spectroscopy data generated for a single TLS by a form of two-tone spectroscopy. Specifically, we demonstrate that a custom convolutional neural network model(CNN) can simultaneously predict (Formula presented.), (Formula presented.), (Formula presented.) and (Formula presented.) from the spectroscopy data presented in the form of images. Our results show that the model achieves superior performance to perturbation theory methods in successfully extracting the TLS parameters. Although the model, initially trained on noise-free data, exhibits a decline in accuracy when evaluated on noisy images, retraining it on a noisy dataset leads to a substantial performance improvement, achieving results comparable to those obtained under noise-free conditions. Furthermore, the model exhibits higher predictive accuracy for parameters (Formula presented.) and (Formula presented.) in comparison to (Formula presented.) and (Formula presented.).