Conditioned Source Separation for Musical Instrument Performances

  • Authors
  • Slizovskaia O, Haro G, Gomez E
  • UPF authors
  • HARO ORTEGA, GLORIA; GÓMEZ GUTIÉRREZ, EMILIA; SLIZOVSKAIA ., OLGA;
  • Type
  • Scholarly articles
  • Journal títle
  • IEEE-ACM transactions on audio, speech, and language processing
  • Publication year
  • 2021
  • Pages
  • 1-14
  • ISSN
  • 2329-9304
  • Publication State
  • Published
  • Abstract
  • In music source separation, the number of sources may vary for each piece and some of the sources may belong to the same family of instruments, thus sharing timbral characteristics and making the sources more correlated. This leads to additional challenges in the source separation problem. This paper proposes a source separation method for multiple musical instruments sounding simultaneously and explores how much additional information apart from the audio stream can lift the quality of source separation. We explore conditioning techniques at different levels of a primary source separation network and utilize two extra modalities of data, namely presence or absence of instruments in the mixture, and the corresponding video stream data.
  • Complete citation
  • Slizovskaia O, Haro G, Gomez E. Conditioned Source Separation for Musical Instrument Performances. IEEE-ACM transactions on audio, speech, and language processing 2021; ( ): 1-14.
Bibliometric indicators
  • 1 times cited Scopus
  • 1 times cited WOS
  • Índex Scimago de 0.916 (2020)