This paper presents a deep learning-based approach to noise suppression in speech signals, comparing convolutional neural networks and recurrent architectures. Inspired by the SEGAN model, a fully convolutional network with residual connections is developed and optimized for TFLite deployment. Results demonstrate effective denoising performance with low latency. Additionally, LSTM models are evaluated, confirming their superiority in handling temporal dependencies in variable-length audio sequences.
Abstract: The increasing digitization of critical infrastructure environments has significantly enhanced operational efficiency while simultaneously exposing industrial systems to sophisticated cyber threats. Critical sectors such as oil and gas, energy, transportation, and manuf…
Abstract: The rapid digital transformation of the oil and gas industry has significantly improved operational efficiency through the integration of Information Technology (IT) and Operational Technology (OT) systems. However, this increased connectivity has also expanded the cybe…
This study investigated real-time assessment and modeling of perceived listening effort (LE). The model consists of a binaural front-end, followed by a monaural back-end. As front-end, a novel blind real-time implementation of the binaural speech intelligibility model (BSIM) was…
Abstract: The rapid digital transformation of the oil and gas industry has accelerated the convergence of Information Technology (IT) and Operational Technology (OT), enabling enhanced operational efficiency, predictive maintenance, and remote asset management. While these techno…
Abstract Advances in digital technologies have fundamentally reshaped health communication and education, giving rise to innovative, interactive, and user-centered learning approaches. In this evolving environment, the edutainment paradigm, which integrates educational content wi…
This study aimed to examine the relationships between principal leadership, physical education teacher readiness, and physical education facilities and the implementation of the Deep Learning Approach, both individually and collectively. A quantitative correlational survey was co…