Supervised speech separation combined with adaptive beamforming

Authors:           Zoran Šarić¹, Miško Subotić¹, Ružica Bilibajkić¹, Marko Barjaktarović², Jasmina Stojanović³

 

¹Laboratory of Acoustics, Life Activities Advancement Center,

Gospodar Jovanova 35, 11000 Belgrade, Serbia

 

²Faculty of electrical engineering University of Belgrade, Bulevar kralja Aleksandra 73, 11120 Belgrade, Serbia

 

³Faculty of medical sciences University of Kragujevac, Svetozara Markovica 69,

34000 Kragujevac, Serbia

 

 

·        How to install supervised speech separation-Adaptive beamforming

·        Download DNN-ABF matlab code

 

 

Test scenario, T60 = 360 ms

Test examples   ratio_1_clean.wav ratio_1_refMic.wav ratio_1_estimated.wav ratio_1_gsc.wav ratio_1_gscPost2.wav

Clean speech of the uterence 1 Noisy speech of the uterence 1 recorded on microphone 4 Speech Processed by supervised speech separation (SSS) Speech processed by S-GSC Speech processed by postfilter