On linear and mixmax interaction models for single channel source separation

Robert Peharz, Franz Pernkopf

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

4 Citations (Scopus)

Abstract

For model-based single channel source separation, one typically assumes a linear interaction model, i.e. that the mixture magnitude spectrogram is the sum of the individual source magnitude spectrograms. In the log-domain, the MIXMAX interaction model is the corresponding approximation for the linear model. Hence, one would expect similar performance for both approaches. However, in this paper we empirically show that this is not the case for vector-quantizer-based (VQ) single channel source separation. We propose factorial linear-VQ, the linear counterpart to factorial max-VQ, and compare the two methods in systematic source separation experiments. Linear-VQ performs significantly better than max-VQ for comparable code-book sizes and behaves more robustly in the presence of additive white noise. Furthermore, we compare resynthesis properties of binary and continuous time-frequency masks. While binary masks achieve a higher interference suppression, the use of continuous masks results in a consistently better signal quality.

Original languageEnglish
Title of host publication2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings
PublisherIEEE Press
Pages249-252
Number of pages4
ISBN (Print)9781467300469
DOIs
Publication statusPublished - 23 Oct 2012
Externally publishedYes
Event2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Kyoto, Japan
Duration: 25 Mar 201230 Mar 2012

Conference

Conference2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012
CountryJapan
CityKyoto
Period25/03/1230/03/12

Keywords

  • single channel
  • source separation
  • time-frequency masking
  • VQ

Fingerprint Dive into the research topics of 'On linear and mixmax interaction models for single channel source separation'. Together they form a unique fingerprint.

Cite this