Negatif olmayan matris ayriştirmaya dayali tek-kanaldan ses ayriştirma için uyarlamali zaman-siklik çözü nürluǧü

Translated title of the contribution: Adaptive time-frequency resolution for single channel sound source separation based on non-negative matrix factorization

Serap Kirbiz, Paris Smaragdis

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

Abstract

This paper proposes an adaptive time-frequency resolution approach for the single channel source separation problem. Our aim is to improve the quality and intelligibility of the separated sources by adapting the time-frequency resolution of the analysis window to the characteristic of the signal under consideration. The results evaluated on a large test set show the improvements obtained by the proposed algorithm.

Translated title of the contributionAdaptive time-frequency resolution for single channel sound source separation based on non-negative matrix factorization
Original languageTurkish
Title of host publication2011 IEEE 19th Signal Processing and Communications Applications Conference, SIU 2011
Pages964-967
Number of pages4
DOIs
StatePublished - Jul 21 2011
Event2011 IEEE 19th Signal Processing and Communications Applications Conference, SIU 2011 - Antalya, Turkey
Duration: Apr 20 2011Apr 22 2011

Publication series

Name2011 IEEE 19th Signal Processing and Communications Applications Conference, SIU 2011

Conference

Conference
CountryTurkey
CityAntalya
Period4/20/114/22/11

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing

Fingerprint Dive into the research topics of 'Adaptive time-frequency resolution for single channel sound source separation based on non-negative matrix factorization'. Together they form a unique fingerprint.

Cite this