CAJ | 학술논문

为解决噪声环境下瞬态声自动识别系统性能下降的问题，在自动识别系统前端采用Teager能量算子（TEO）和离散余弦变换（DCT）相结合的方法进行降噪处理，同时采取基于高斯混合模型（GMM）的缺失特征边缘化算法进行自动分类。实验结果表明，此方法可以显著地提高噪声环境下系统的识别性能。
위해결조성배경하순태성자동식별계통성능하강적문제，재자동식별계통전단채용Teager능량산자（TEO）화리산여현변환（DCT）상결합적방법진행강조처리，동시채취기우고사혼합모형（GMM）적결실특정변연화산법진행자동분류。실험결과표명，차방법가이현저지제고조성배경하계통적식별성능。
To solve the problem of performance degradation of the automatic recognition system applied to the transient sounds in the noisy environment,a method combining Teager energy operator(TEO)with discrete cosine transform(DCT)is adopted at front?end of the automatic recognition system to suppress the noise. At the same time,the missing feature marginaliza?tion algorithm based on the Gaussian mixture model(GMM)is used to achieve automatic classification. The experimental results show that the method can obviously improve the recognition performance of the system in noisy environment.