Performance of an automatic speech recognition (ASR) system tends to be dramatically degraded in the presence of impulsive noise. In the previous work [1], we proposed flooring the observation probability (FOP) to compensate the adverse effect of impulsive noise on sensitive dimensions of Mel-frequency cepstral coefficient (MFCC) features. Linear prediction cepstral coefficient (LPCC) is another kind of widely used acoustic feature, and in this paper we study the performance of the FOP method when applied to LPCC features, including feature vector partition based upon noise sensitivity analysis of each feature dimension and flooring threshold calculation. Evaluation results confirm the efficiency of FOP method on LPCC feature. For example, the highest averaged error reduction rate (ERR) of 38.9% and 46.8% versus the baseline is obtained, respectively in simulated substitutive impulsive noise and machinegun noise environment. Keywords: Robust Speech Recognition, Impulsive Noise, Observation Probability, Flooring Threshold, LPCC acoustic feature