High-speed rotating machinery such as a turbocharger is always subject to imperfection that causes strong vibrations. The problem is that there is no way of knowing the root causes of these vibrations by just using our five senses. This problem is significant since unattended heavy vibrations on a turbocharger may lead to permanent damage and a high cost to fix them. The purpose of this study is to investigate the vibration characteristics of a running turbocharger using the Digital Signal Processing (DSP) method, hence identifying the sources of such vibration profiles. In this context, DSP is the process of taking vibration signals that have been digitized and then mathematically manipulating them. Usually, it involves converting time domain data into frequency domain using Fast Fourier Transform (FFT). To identify the causes of turbocharger vibrations, a literature review was done by studying past research of the same methodology. An experiment was conducted by running the machine at different speeds and operating conditions across the choke, regular, and surge conditions. Vibrational data was obtained by mounting a piezoelectric accelerometer onto the compressor housing. The data was then later post-processed using MATLAB to execute FFT. The result shows high energy peaks at various frequencies associated with an unbalanced rotor, oil whirl, looseness, misalignment, and surging noise. On this basis, it is concluded that the vibrational data of a turbocharger can be identified using DSP.