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。
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.
出处
《计算机应用》
CSCD
北大核心
2010年第3期796-798,共3页
journal of Computer Applications
基金
国家自然科学基金资助项目(60702025)
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
abnormal audio recognition
Mel-Frequency Cepstrum Coefficient（MFCC）
short-term energy
Gaussian Mixture Model（GMM）
