EURASIP Journal on Audio Speech and Music Processing · 2014 · 45 citations · 27 references
ComputingMusicologyAcousticsMachine LearningMusic AnalysisHarmonic AnalysisMatrix FactorizationSpeech RecognitionUnsupervised LearningAudio Feature ExtractionHarmonic RecognitionNon-negative Matrix FactorizationSound Source SeparationUnsupervised Feature Learning
In this paper, unsupervised learning is used to separate percussive and harmonic sounds from monaural non-vocal polyphonic signals. Our algorithm is based on a modified non-negative matrix factorization (NMF) procedure that no labeled data is required to distinguish between percussive and harmonic bases because information from percussive and harmonic sounds is integrated into the decomposition process. NMF is performed in this process by assuming that harmonic sounds exhibit spectral sparseness (narrowband sounds) and temporal smoothness (steady sounds), whereas percussive sounds exhibit spectral smoothness (broadband sounds) and temporal sparseness (transient sounds). The evaluation is performed using several real-world excerpts from different musical genres. Comparing the developed approach to three current state-of-the art separation systems produces promising results.
27
Learning the parts of objects by non-negative matrix factorization
Daniel D. Lee, H. Sebastian Seung · Nature · 1999 · 14.1K citations
Algorithms for Non-negative Matrix Factorization
Daniel D. Lee, H. Sebastian Seung · 2000 · 5.5K citations
Non-negative Matrix Factorization with Sparseness Constraints
Patrik O. Hoyer · 2004 · 2.6K citations