Abstract | ||
---|---|---|
In this paper, we propose a twice-iterated composite Fourier transform (TICFT) technique to detect the singing voice boundaries from acoustical polyphonic music signals. We show that the cumulative TICFT energy in the lower coefficients is capable of differentiating the harmonic structures of vocal and instrumental music in higher octaves. The musical signal is first segmented into frames based on quarter-notes. Then TICFT is used to measure the harmonic structure of each frame. Finally, the vocal and instrumental frames are classified by applying music domain knowledge. Experimental results show over 80% frame level accuracy can be achieved |
Year | DOI | Venue |
---|---|---|
2004 | 10.1109/ICME.2004.1394478 | Multimedia and Expo, 2004. ICME '04. 2004 IEEE International Conference |
Keywords | Field | DocType |
Fourier transforms,audio signal processing,music,acoustical polyphonic music signals,cumulative TICFT energy,instrumental frame classification,quarter-notes,singing voice boundaries,singing voice detection,twice-iterated composite Fourier transform,vocal frame classification | Octave,Music information retrieval,Pattern recognition,Computer science,Harmonic,Speech recognition,Fourier transform,Singing,Artificial intelligence,Polyphony,Audio signal processing,Quarter note | Conference |
Volume | ISBN | Citations |
2 | 0-7803-8603-5 | 11 |
PageRank | References | Authors |
1.93 | 3 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Namunu Chinthaka Maddage | 1 | 108 | 11.28 |
Kongwah Wan | 2 | 423 | 29.55 |
Changsheng Xu | 3 | 4957 | 332.87 |
Ye Wang | 4 | 766 | 68.77 |