Musical source separation using time-frequency source priors

Abstract : This article deals with the source separation problem for stereo musical mixtures using prior information about the sources (instrument names and localization). After a brief review of existing methods, we design a family of probabilistic mixture generative models combining modified positive Independent Subspace Analysis (ISA), localization models and Segmental Models (SM). We express source separation as a Bayesian estimation problem and we propose efficient resolution algorithms. The resulting separation methods rely on a variable number of cues including harmonicity, spectral envelope, azimuth, note duration and monophony. We compare these methods on two synthetic mixtures with long reverberation. We show that they outperform methods exploiting spatial diversity only and that they are robust against approximate localization of the sources.
Complete list of metadatas

Cited literature [31 references]  Display  Hide  Download

https://hal.inria.fr/inria-00544269
Contributor : Emmanuel Vincent <>
Submitted on : Tuesday, December 7, 2010 - 3:43:31 PM
Last modification on : Thursday, March 21, 2019 - 2:20:03 PM
Long-term archiving on : Tuesday, March 8, 2011 - 4:41:17 AM

File

vincent_TASLP06.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : inria-00544269, version 1

Citation

Emmanuel Vincent. Musical source separation using time-frequency source priors. IEEE Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2006, 14 (1), pp.91--98. ⟨inria-00544269⟩

Share

Metrics

Record views

209

Files downloads

679