Process harmonics often need to be eliminated for accurate regenerative chatter diagnosis. To eliminate the harmonics with many band-stop characteristics, this paper uses a periodic/aperiodic separation filter (PASF) and proposes a chatter detection algorithm based on the PASF. The PASF can design the cutoff frequency and time constant, directly, and the high-order PASF improves the harmonics elimination performance without deteriorating chatter signal extraction performance. The experiments validated the proposed algorithm under several conditions of spindle speeds, cutting types, thresholds, and cutoff frequencies. Their results showed the robustness of the proposed chatter detection algorithm against the threshold selection and change of cutting conditions.