A DTD-free AEC method based on the flexible independent component analysis

Marko Kanadi, Muhammad Tahir Akhtar, Wataru Mitsuhashi

Research output: Contribution to conferencePaperpeer-review

Abstract

In this paper, we propose a double-talk detection (DTD)-free acoustic echo cancellation (AEC) method based on the flexible independent component analysis (ICA). The inflexible score function used in the existing ICA-based AEC system is not always suitable since the probability density function of the source signal (speech in our case) is not always super Gaussian. The flexible ICA, on the other hand, has a parametric score function which is controlled by the Gaussianity of the source signal. Therefore, the proposed method is able to always provide the suitable score-function depending on the present Gaussianity of the speech signal. The experimental results indicate that the proposed method significantly outperforms the existing ICA-based AEC algorithm and the variable step-size (VSS)-NLMS algorithm.

Original languageEnglish
Pages189-193
Number of pages5
Publication statusPublished - Dec 1 2011
Externally publishedYes
Event6th Triangle Symposium on Advanced ICT 2011, TriSAI 2011 - Daejeon, Korea, Republic of
Duration: Aug 25 2011Aug 26 2011

Conference

Conference6th Triangle Symposium on Advanced ICT 2011, TriSAI 2011
CountryKorea, Republic of
CityDaejeon
Period8/25/118/26/11

ASJC Scopus subject areas

  • Information Systems

Fingerprint Dive into the research topics of 'A DTD-free AEC method based on the flexible independent component analysis'. Together they form a unique fingerprint.

Cite this