Abstract: Concerning the high complexity and low rate in abnormal audio recognition, the abnormal audio recognition system based on the Mel-Frequency Cepstrum Coefficients (MFCC) and short-term energy was proposed. This feature vector made the Gaussian Mixture Model (GMM) classifier outperform MFCC and Differential MFCC features in classification. The classifier can achieve an average recognition rate of more than 90%, and small computational complexity. The steps of system implementation were elaborated. The simulation results prove the effectiveness of the proposed algorithm.

Key words: abnormal audio recognition, Mel-Frequency Cepstrum Coefficient (MFCC), short-term energy, Gaussian Mixture Model (GMM)

摘要： 针对现行异常声音识别算法复杂度高和特征识别率低的问题，将梅尔频率倒谱系数（MFCC）与短时能量混合特征应用到异常声音识别系统中。该混合特征使得高斯混合模型（GMM）分类器可获得比使用MFCC特征及其差分MFCC更好的分类性能。给出了系统实现的具体步骤，并通过仿真实验证明了该算法的有效性,分类器的平均识别率可达到90%以上，并且计算复杂度小。

关键词: 异常声音识别, 梅尔倒谱系数, 短时能量, 高斯混合模型