Evaluation of blind signal separation methods

D.W.E. Schobben, K. Torkkola, P. Smaragdis

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

153 Downloads (Pure)

Abstract

Recently many new Blind Signal Separation BSS algorithms have been introduced Authors evaluate the performance of their algorithms in various ways Among these are speech recognition rates plots of separated signals plots of cascaded mixingunmixing impulse responses and signal to noise ratios Clearly not all of these methods give a good reection of the performance of these algorithms.Moreover since the evaluation is done using different measures and different data results cannot be compared As a solution we provide a unified methodology of evaluating BSS algorithms along with providing data online such that researches can compare their results We will focus on acoustical applications but many of the remarks apply to other BSS application areas as well.
Original languageEnglish
Title of host publicationProc. ICA '99, International Workshop on Independent Component Analysis and Blind Signal Separation
Pages261-266
Publication statusPublished - 1999
Eventconference; ICA '99, International Workshop on Independent Component Analysis and Blind Signal Separation, Aussois, France, 11-15 January 1999 -
Duration: 1 Jan 1999 → …

Conference

Conferenceconference; ICA '99, International Workshop on Independent Component Analysis and Blind Signal Separation, Aussois, France, 11-15 January 1999
Period1/01/99 → …
OtherICA '99, International Workshop on Independent Component Analysis and Blind Signal Separation, Aussois, France, 11-15 January 1999

Fingerprint

Dive into the research topics of 'Evaluation of blind signal separation methods'. Together they form a unique fingerprint.

Cite this