A VQ-based single-channel audio separation for music/speech mixtures

Meysam Asgari, Mahdi Fallah, Elahe Abouie Mehrizi, Ali Mostafavi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations

Abstract

In this paper, we address the problem of audio ource separation with one single sensor, based on estimation of statistical model of the sources. We improve the-state-of-the art Vector Quantization (VQ) by considering apriori histograms of huge training data. This will result in a more accurate codebook for each source in contrast to the commonly used Linde-Buzo-Gray (LBG) algorithm. An optimum estimator is introduced in separation stage based on Discrete Fourier Transform (DFT) amplitudes. Finally, conducting different simulations, it is demonstrated that proposed approach efficiently segregated audio mixtures in terms of Signal to Distortion Ratio (SDR) measures as well as Mean Opinion Score (MOS) criterion.

Original languageEnglish (US)
Title of host publication11th International Conference on Computer Modelling and Simulation, UKSim 2009
Pages223-227
Number of pages5
DOIs
StatePublished - 2009
Externally publishedYes
Event11th International Conference on Computer Modelling and Simulation, UKSim 2009 - Cambridge, United Kingdom
Duration: Mar 25 2009Mar 27 2009

Publication series

Name11th International Conference on Computer Modelling and Simulation, UKSim 2009

Conference

Conference11th International Conference on Computer Modelling and Simulation, UKSim 2009
Country/TerritoryUnited Kingdom
CityCambridge
Period3/25/093/27/09

Keywords

  • Single cahnnel audio sepatation
  • Vector quantization

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Modeling and Simulation

Fingerprint

Dive into the research topics of 'A VQ-based single-channel audio separation for music/speech mixtures'. Together they form a unique fingerprint.

Cite this