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

Alexey Ozerov (1) , Cédric Févotte (2) , Raphaël Blouet (3) , Jean-Louis Durrieu (4)

1 METISS - Speech and sound data modeling and processing
2 LTCI - Laboratoire Traitement et Communication de l'Information
3 Yacast
4 SP Lab - Laboratoire de Traitement du signal [EPFL] / Signal Processing Laboratories

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.

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

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⟩