With the proliferation of drones, conventional radar-based detection systems face challenges in accurately distinguishing between drones and birds. Radar requires line of sight to objects. In response, this paper presents a novel approach utilizing acoustic signals for simultaneous detection of drones, humans, and animals. Drones are categorized based on their propulsion systems where each exhibiting unique acoustic signatures. Leveraging machine learning algorithms, this project aims to analyze these signals comprehensively. A robust system capable of distinguishing between drones, animals, and humans with high accuracy is developed by integrating acoustic data with advanced machine learning techniques,. Mean, Variance, Pitch, and Sampling Frequency features are used in this work. To classify the drones Decision Tree based Machine Learning algorithm is explored. This innovative solution promises to enhance security measures by providing reliable drone detection capabilities while mitigating false alarms caused by bird detections and human voice signals. MATLAB is primarily used for simulation purposes. In contrast, NI LabVIEW allows for seamless integration and deployment of code on hardware platforms. These abilities are the motivation for this work. A decision tree model is constructed using the training data in MATLAB. The decision tree logic is then implemented in NI LabVIEW using If-else blocks. This logic is saved in a virtual instrument file, which serves as the operational model for the system. The system is tested with both pre-recorded audio files and real-time data from a microphone. Its performance is evaluated using a confusion matrix. This integrated approach demonstrates the effectiveness of combining MATLAB and NI LabVIEW for real-time acoustic signal classification. Performance of the proposed methods is assessed using accuracy, precision, recall, and F1 score.