Skip to Main content Skip to Navigation
Conference papers

Multichannel nonnegative tensor factorization with structured constraints for user-guided audio source separation

Abstract : Separating multiple tracks from professionally produced music recordings (PPMRs) is still a challenging problem. We address this task with a user-guided approach in which the separation system is provided segmental information indicating the time activations of the particular instruments to separate. This information may typically be retrieved from manual annotation. We use a so-called multichannel nonnegative tensor factorization (NTF) model, in which the original sources are observed through a multichannel convolutive mixture and in which the source power spectrograms are jointly modeled by a 3-valence (time/frequency/source) tensor. Our user-guided separation method produced competitive results at the 2010 Signal Separation Evaluation Campaign, with sufficient quality for real-world music editing applications.
Complete list of metadata

Cited literature [13 references]  Display  Hide  Download

https://hal.inria.fr/inria-00564851
Contributor : Alexey Ozerov <>
Submitted on : Thursday, February 10, 2011 - 11:37:23 AM
Last modification on : Tuesday, June 15, 2021 - 4:23:07 PM
Long-term archiving on: : Wednesday, May 11, 2011 - 2:52:35 AM

File

Ozerov_et_al_icassp11.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00564851, version 1

Citation

Alexey Ozerov, Cédric Févotte, Raphaël Blouet, Jean-Louis Durrieu. Multichannel nonnegative tensor factorization with structured constraints for user-guided audio source separation. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP'11), May 2011, Prague, Czech Republic. ⟨inria-00564851⟩

Share

Metrics

Record views

697

Files downloads

942