Micro-end-milling is used for the fabrication of complex geometrical features with high precision on a wide variety of materials. One of the main challenges is related to chatter vibrations, which are detrimental to the productivity and overall quality of the manufactured parts. In this article, a novel chatter-detection method based on wavelet coherence functions is proposed to evaluate the stability of the micro-end-milling process. Then, the method is experimentally tested under different cutting conditions. The results show that the wavelet coherence functions of two orthogonal acceleration signals are sensitive enough and applicable for chatter detection. When chatter occurs, the two orthogonal acceleration signals are highly correlated at the chatter frequency, resulting in a sharp increase in the magnitude of the wavelet coherence functions to values approaching unity.