Chatter is a common state in the end milling, which has major influence on machining quality. Early chatter detection is a prerequisite for taking adequate measures to avoid chatter. Nevertheless, there are still numerous challenges and difficulties in the feature extraction of chatter detection. In this paper, effective chatter detection in the milling process of a vibration signal is investigated using time frequency analysis. Firstly, the measured vibration signal in the machining process was preprocessed by Wavelet Transform decomposition. Different sub-bands were obtained and the portion with high chatter information was reconstructed for further analysis. Since measured signals from sensors usually constitute of background noise and other disturbances, the wavelet decomposition serves as a preprocessor to denoise the measured signals and enhance the performance of the Wavelet Synchro Squeezing Transform (WSST) which was applied on the reconstructed signal for chatter Identification. The techniques were used to detect the chatter in different operating condition of the machining process. Finally, some milling tests were conducted and the experiment results prove that the proposed method indeed succeed in effectively chatter identification.