Fire incidents are responsible for severe damage and thousands of deaths every year all over the world. Extreme temperatures, low visibility, toxic gases, and unknown locations of victims create difficulties and delays in rescue operations, escalating the risk of injury or death. It is time-critical to detect the victims trapped inside the burning sites for facilitating the rescue operations. This research work presents an audio-based automated system for victim detection in fire emergencies, investigating two machine learning (ML) methods: support vector machines (SVM) and long short-term memory (LSTM). The performance of these two ML techniques has been evaluated based on a variety of performance metrics. Our analyses show that both ML methods provide superior scream detection performance, with SVM slightly overperforming LSTM. Because of its lower complexity, SVM is a better candidate for real-time implementation in our autonomous embedded system vehicle (AESV).