Seismic signal recognition can serve as a powerful auxiliary tool for analyzing and processing ever-larger volumes of seismic data. It can facilitate many subsequent procedures such as first-break picking, statics correction, denoising, signal detection, events tracking, structural interpretation, inversion and imaging. In this study, we propose an automatic technique of seismic signal recognition taking advantages of unsupervised machine learning. In the proposed technique, seismic signal recognition is considered as a problem of clustering data points. All the seismic sampling points in time domain are clustered into two clusters, that is, signal or non-signal. The K-Means clustering algorithm is used to group these sampling points. Four attributes, that is, two STA/LTA ratios, variance and envelope are investigated in the clustering process. The performances of the method are tested on synthetic data and results are presented.