Adaptive Blind Audio Source Extraction Supervised By Dominant Speaker Identification Using X-Vectors
Jakub Janský, Jirí Málek, Jaroslav Cmejla, Tomás Kounovský, Zbynek Koldovský, Jindrich Zdánský
Abstract
We propose a novel algorithm for adaptive blind audio source extraction. The proposed method is based on independent vector analysis and utilizes the auxiliary function optimization to achieve high convergence speed. The algorithm is partially supervised by a pilot signal related to the source of interest (SOI), which ensures that the method correctly extracts the utterance of the desired speaker. The pilot is based on the identification of a dominant speaker in the mixture using x-vectors. The properties of the x-vectors computed in the presence of cross-talk are experimentally analyzed. The proposed approach is verified in a scenario with a moving SOI, static interfering speaker and environmental noise.
BibTeX
@inproceedings{icassp2020_adaptiveblindaud,
title = {Adaptive Blind Audio Source Extraction Supervised By Dominant Speaker Identification Using X-Vectors},
author = {Jakub Janský and Jirí Málek and Jaroslav Cmejla and Tomás Kounovský and Zbynek Koldovský and Jindrich Zdánský},
booktitle = {ICASSP 2020},
year = {2020}
}