Separation of Instrument Sounds using Non-negative Matrix Factorization with Spectral Envelope Constraints
This work addresses sound source separation for audio processing applications, but it is incremental as it builds on existing NMF techniques with a new constraint.
The paper tackles the problem of separating instrument sounds by introducing spectral envelope constraints into non-negative matrix factorization, and the proposed method outperforms conventional methods in experiments.
Spectral envelope is one of the most important features that characterize the timbre of an instrument sound. However, it is difficult to use spectral information in the framework of conventional spectrogram decomposition methods. We overcome this problem by suggesting a simple way to provide a constraint on the spectral envelope calculated by linear prediction. In the first part of this study, we use a pre-trained spectral envelope of known instruments as the constraint. Then we apply the same idea to a blind scenario in which the instruments are unknown. The experimental results reveal that the proposed method outperforms the conventional methods.