Music/voice separation based on the multi-repeating structure of Mel cepstrum coefficient  

作　　者：ZHANG Tianqi XU Xin WU Wangjun LIU Yu 

机构地区：[1]Chongqing Key Laboratory of Signal and Information Processing,Chongqing University of Posts and Telecommunications

出　　处：《Chinese Journal of Acoustics》2015年第4期424-435,共12页声学学报（英文版）

基　　金：supported by the National Natural Science Foundation of China(61371164,61275099,61102131);the Project of Key Laboratory of Signal and Information Processing of Chongqing(CSTC2009CA2003);the Chongqing Distinguished Youth Fundation(CSTC2011jjjq40002);the Natural Science Foundation of Chongqing(CSTC2012JJA40008);the Research Project of Chongqing Educational Commission(KJ120525,KJ130524);Graduate Research and Innovation Projects of Chongqing(CYS14140)

摘　　要：For the poor adaptability of the original repeating pattern, an improved music separation method of multi-repeating structure of Mel cepstrum coefficient （MFCC） is proposed. Firstly, the MFCC coefficient matrix （39-dimensional data） of the music signal was extracted. Then the cosine characteristic was applied to the count of similarity matrix of MFCC, and the fragments with consistent similarity are putted together. Next different repeating patterns are built for different groups. Thereby the spectrums of the background music and vocal were separated combined with ideal binary masking （IBM）, and the corresponding time domain signals were obtained by inverse Fourier transform. Fnally, the improved method was tested on the music database of different types and length, and the separation results were compared with repeating method of Rafii and the non-negative matrix factorization based on flexible framework method of Ozerov. The experimental results showed that the separation performance of improved method was improved about 3 dB, and the performance of music with melody changed larger was significantly improved. Experiments verified that the improved method was an effective music separation algorithm and more stability.For the poor adaptability of the original repeating pattern, an improved music separation method of multi-repeating structure of Mel cepstrum coefficient （MFCC） is proposed. Firstly, the MFCC coefficient matrix （39-dimensional data） of the music signal was extracted. Then the cosine characteristic was applied to the count of similarity matrix of MFCC, and the fragments with consistent similarity are putted together. Next different repeating patterns are built for different groups. Thereby the spectrums of the background music and vocal were separated combined with ideal binary masking （IBM）, and the corresponding time domain signals were obtained by inverse Fourier transform. Fnally, the improved method was tested on the music database of different types and length, and the separation results were compared with repeating method of Rafii and the non-negative matrix factorization based on flexible framework method of Ozerov. The experimental results showed that the separation performance of improved method was improved about 3 dB, and the performance of music with melody changed larger was significantly improved. Experiments verified that the improved method was an effective music separation algorithm and more stability.

关 键 词：MFCC Music/voice separation based on the multi-repeating structure of Mel cepstrum coefficient Mel 

分 类 号：TN912.3[电子电信—通信与信息系统]