计算机与数字工程2016，Vol.44Issue(10)：1875-1879,1894,6.DOI:10.3969/j.issn.1672-9722.2016.10.002
基于 EEMD 的异常声音特征提取
Abnormal Sound Feature Extraction Based on EEMD
摘要
Abstract
Aiming at solving the low recognition rate of abnormal sound recognition caused by using M FCC ,LPCC as feature ,the project proposes a feature extraction method for abnormal sound based on Ensemble Empirical Mode Decomposi‐tion (EEMD) combining the high nonlinearity and non‐stationary .First the abnormal sounds are segmented into frames and every frame of the sound is decomposed into IMFS ,then features including energy ,cross rate ,energy ratio ,and M FCC are extracted for every IMF .Finally the feature vectors are segmented and the means of every segment are computed as the final features .Using these features as input ,then the project adopts SVM as classifier to recognize seven kinds of abnormal sounds ,and the recognition rate is tested in railway background .Experiment results show that these features can improve the recognition rate comparing with M FCC .关键词
异常声音识别/经验模态分解/特征提取/支持向量机Key words
abnormal sound recognition/empirical mode decomposition/feature extraction/support vector machine分类
信息技术与安全科学引用本文复制引用
陈志全,杨骏,乔树山..基于 EEMD 的异常声音特征提取[J].计算机与数字工程,2016,44(10):1875-1879,1894,6.基金项目
中科院战略性先导科技专项极低功耗智能感知技术（编号XDA06020401）资助。 （）
