To non-destructively determine the freshness of pork rapidly,near-infrared (NIR) spectroscopy was applied to quantitative the content of total volatile basic nitrogen (TVB-N) in pork which was an important index of pork freshness. The raw spectra of pork was preprocessed by the normaliyation method of standard deviation (SNV). Synergy interval partial least squares (siPLS) algorithm was used to build the precessed spectra of pork and calibration model of TVB-N content and that model was compared with the models respectively built by classical partial least squares (PLS) and interval PLS (iPLS) algorithms. Experimental results showed that the performance of siPLS model was the best in contrast to PLS and iPLS. The optimal calibration model was achieved with correlation coefficient (Rc=0.8332),root mean square error of cross-validation (fRV=3.75) in calibration set and correlation coefficient (Rp=0.8238),root mean squared error of prediction (fRP=4.17) in prediction set. This study demonstrated that NIR spectroscopy with siPLS can be successfully applied as a rapid method to determine the TVB-N of pork rapidly.