Although a nuclear reactor is a hostile environment for sensing and electrical communications, the reactor core is amenable to acoustic communication. An acoustic measurement infrastructure (AMI) has been installed at the Advanced Test Reactor (ATR) nozzle trench area to record acoustic signals that have the ability to capture different operating regimes of the reactor. This AMI includes ATR in-pile structural components, coolant, acoustic receivers, and primary coolant pumps as signal sources, a data acquisition system, and signal-processing algorithms enabling real-time monitoring. This report will discuss development of a recursive Short Time Fast Fourier Transform (STFFT) approach to process acoustic signals. The recursive STFFT is then applied to the data obtained from the ATR brush experiment to understand the vibration levels and to develop spectrograms for different operating regimes. The combination of primary coolant pumps for normal and power axial locator mechanisms of ATR are different and generate unique signatures. These acoustic signatures were used to develop machine learning approaches to automatically classify different operating regimes. This lays the foundation for a predictive analytic framework that can be leveraged by ATR to optimize their operations and maintenance.