37 citations · 91 across the 5 of their papers we have counts for
6 papers
Informed FastICA: Semi-Blind Minimum Variance Distortionless Beamformer
Zbyněk Koldovský, Jiří Málek, Jaroslav Čmejla +1
Non-Gaussianity-based Independent Vector Extraction leads to the famous one-unit FastICA/FastIVA algorithm when the likelihood function is optimized using an approximate Newton-Rap…
Target Speech Extraction: Independent Vector Extraction Guided by Supervised Speaker Identification
Jiri Malek, Jakub Jansky, Zbynek Koldovsky +3
This manuscript proposes a novel robust procedure for the extraction of a speaker of interest (SOI) from a mixture of audio sources. The estimation of the SOI is performed via inde…
Dynamic Independent Component/Vector Analysis: Time-Variant Linear Mixtures Separable by Time-Invariant Beamformers
Zbyněk Koldovský, Václav Kautský, Petr Tichavský
A novel extension of Independent Component and Independent Vector Analysis for blind extraction/separation of one or several sources from time-varying mixtures is proposed. The mix…
Adaptive blind audio source extraction supervised by dominant speaker identification using x-vectors
Jakub Janský, Jiří Málek, Jaroslav Čmejla +3
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 optimizatio…
Block-Online Multi-Channel Speech Enhancement Using DNN-Supported Relative Transfer Function Estimates
Jiri Malek, Zbynek Koldovsky, Marek Bohac
This work addresses the problem of block-online processing for multi-channel speech enhancement. Such processing is vital in scenarios with moving speakers and/or when very short u…
Spatial Source Subtraction Based on Incomplete Measurements of Relative Transfer Function
Zbynek Koldovsky, Jiri Malek, Sharon Gannot
Relative impulse responses between microphones are usually long and dense due to the reverberant acoustic environment. Estimating them from short and noisy recordings poses a long-…