For the chatter occured frequently in precise hole boring processing and resulted in low quality of finished surface, a chatter monitoring system was established to finish the feature extraction of the chatter to predict the chatter and gain the precious time for chatter suppression. Firstly, according to the characteristics of chatter signals,Empirical Mode Decomposition(EMD) and Hilbert-Huang Transform(HHT) were introduced to extract the chatter feature, and their basic theories were investigated. Then, the vibration of boring bar was picked up online during the process, and the vibration signal was decomposed by EMD and then transformed by HHT. Finally, the feature of chatter symptom was extracted by analyzing the Hilbert spectrum of each Intrinsic Mode Function(IMF). The experimental results show that extracting chatter feature from vibration of boring bar by EMD and HHT can gain the chatter symptom by 0.5 s ahead of the chatter outbreak, which can provide sufficient guarantee for follow-up chatter suppression and can provide the high quality surface for workpieces.