Drum Extraction In Single Channel Audio Signals Using Multi-Layer Non Negative Matrix Factor Deconvolution

In this paper, we propose a supervised multilayer factorization method designed for harmonic/percussive Source separation and drum extraction. Our method decomposes the audio signals in sparse orthogonal components whieh capture the harmonie content, while the drum is represented by an extension of non negative matrix factorization which is able to exploit time-frequency dictionaries to take into account non stationary drum sounds. The drum dictionaries represent various real drum hits and the decomposition has more physieal sense and allows for a better interpretation of the results. Experiments on real musie data for a harmonie/percussive source separation task show that our method outperforms other state of the art algorithms. Finally, OUT method is very robust to non stationary harmonic sources that are usually poorly decomposed by existing methods.