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

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.

Music snippet extraction via melody-based repeated pattern discovery

In this paper, we present a complete set of procedures to automatically extract a music snippet, defined as the most representative or the highlighted excerpt of a music clip. We first generate a modified and compact similarity matrix based on selected features and distance metrics, and then several improved techniques for music repeated pattern discovery are utilized because a music snippet is usually a part of the repeated melody, main theme or chorus. During the process, redundant and wrongly detected patterns are discarded, boundaries are corrected using beat information, and final clusters are also further sorted according to the occurrence frequency and energy information. Subsequently, following our methods, we designed a music snippet extraction system which allows users to detect snippets. Experiments performed on the system show the superiority of our proposed approach.