In this paper, we propose a novel method for analyzing piglet calls that includes an efficient noise reduction technique tailored for noisy pig farming environments. Our approach adopts analysis of the inaudible frequency ranges, where environmental noise levels are low, combined with Non-negative Matrix Factorization (NMF) based noise reduction. We constructed a Random Forest classifier using sixteen acoustic features as an acoustic event detector. The experiment revealed that the three acoustic features, which are F0, ∆MFCC, and SpBandwidth, were particularly important, as they were able to distinguish between the squeals, litter calls, and environmental noise of the three piglet species 98.9% of the time.