Speaker localization and speech separationin two echoic mixtures / Kalbėtojo aptikimas ir šnekos išskyrimas dviejų signalų mišiniuose su aidu

Speaker localization and speech separationin two echoic mixtures / Kalbėtojo aptikimas ir šnekos išskyrimas dviejų signalų mišiniuose su aidu

We are developing two crucial improvements on the time-frequency masking approach to the blind speech separation of underdetermined mixtures when processing anechoic and echoic mixtures. First, the proposed method copes with the usually large amount of delay estimation error that appears in a low f...

Full description

Bibliographic Details
Main Authors: Włodzimierz Kasprzak, Ning Ding, Nozomu Hamada
Format: Article
Language:English
Published: Vilnius Gediminas Technical University 2011-08-01
Series:Mokslas: Lietuvos Ateitis
Subjects:
blind source separation
histogram clustering
spectrogram analysis
speech reconstruction
time-frequency masking
Online Access:https://www.jbem.vgtu.lt/index.php/MLA/article/view/4995

Internet

https://www.jbem.vgtu.lt/index.php/MLA/article/view/4995

Similar Items