Field Mixed Acoustic identification hybrid Systems Based on ICA and Improved GCA
With independent component analysis (ICA) to realize the blind separation from mixed acoustic objects, an identification method based on improved gray correlation analysis (IGCA) is proposed through extracting linear prediction coefficient (LPC) feature. It is revealed that LPC is consistently better than wavelet energy feature, ICA is efficient algorithm to estimate the unknown signal level and IGCA which gets over the shortcomings of GCA model may reflect the difference and similarity of the influences of factors or characteristics effectively. The validity of the new systems is verified via examples in mixed acoustic objects identification system.
ICA. GCA. LPC. Feature. Identification.
Yaobo Li Zhiliang Ren Gong Chen Shengliang Hu
Dept. Of Weaponry Eng., Naval Univ. Of Engineering,Wuhan 430033,China. Dept. of Electronic Information Eng.. Institute Communications Engineering of PLA University,Nanjing Electronic Eng. College,Naval Univ. Of Engineering,Wuhan 430033,China
国际会议
2006 IEEE International Conference on Information Acquisition
山东威海
英文
117-121
2006-08-20（万方平台首次上网日期，不代表论文的发表时间）