Percussive/harmonic sound separation by non-negative matrix factorization with smoothness/sparseness constraints

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 b...

Descripción completa

Detalles Bibliográficos
Autores: Canadas Quesada, Francisco Jesus, Vera Candeas, Pedro, Ruiz Reyes, Nicolas, Carabias Orti, Julio J., Cabanas Molero, Pablo
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2014
País:España
Institución:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Repositorio:Recercat. Dipósit de la Recerca de Catalunya
OAI Identifier:oai:recercat.cat:10230/23259
Acceso en línea:http://hdl.handle.net/10230/23259
http://dx.doi.org/10.1186/s13636-014-0026-5
Access Level:acceso abierto
Palabra clave:So -- Mesurament
Anàlisi harmònica (Música)
Descripción
Sumario: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.