Informed FastICA: Semi-Blind Minimum Variance Distortionless Beamformer
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24220%2F24%3A00012440" target="_blank" >RIV/46747885:24220/24:00012440 - isvavai.cz</a>
Result on the web
<a href="https://asap.ite.tul.cz/wp-content/uploads/sites/3/2024/07/IWAENC_2024___Blind_Minimum_Variance_Distortionless_Beamformer__The_Informed_FastICA_algorithm.pdf" target="_blank" >https://asap.ite.tul.cz/wp-content/uploads/sites/3/2024/07/IWAENC_2024___Blind_Minimum_Variance_Distortionless_Beamformer__The_Informed_FastICA_algorithm.pdf</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/IWAENC61483.2024.10694166" target="_blank" >10.1109/IWAENC61483.2024.10694166</a>
Alternative languages
Result language
angličtina
Original language name
Informed FastICA: Semi-Blind Minimum Variance Distortionless Beamformer
Original language description
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-Raphson algorithm under the orthogonality constraint. In this paper, we replace the constraint with the analytic form of the minimum variance distortionless beamformer (MVDR), by which a semi-blind variant of FastICA/FastIVA is obtained. The side information here is provided by a weighted covariance matrix replacing the noise covariance matrix, the estimation of which is a frequent goal of neural beamformers. The algorithm thus provides an intuitive connection between model-based blind extraction and learning-based extraction. The algorithm is tested in simulations and speaker ID-guided speaker extraction, showing fast convergence and promising performance.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10307 - Acoustics
Result continuities
Project
—
Continuities
V - Vyzkumna aktivita podporovana z jinych verejnych zdroju
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
The 18th International Workshop on Acoustic Signal Enhancement (IWAENC 2024)
ISBN
979-835036185-8
ISSN
2639-4316
e-ISSN
—
Number of pages
5
Pages from-to
95-99
Publisher name
IEEE, Eurasip
Place of publication
—
Event location
Aalborg, Denmark
Event date
Jan 1, 2024
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
001337653100020