Adaptive blind moving source separation based on intensity vector statistics

This paper presents a novel approach to blind moving source separation by detecting, tracking and separating speakers in real-time using intensity vector direction (IVD) statistics. It updates unmixing system parameters swiftly in order to deal with the time-variant mixing parameters. Denoising is c...

Full description

Saved in:
Bibliographic Details
Main Authors: Areeb Riaz, Xiyu Shi, Ahmet Kondoz
Format: Default Article
Published: 2019
Subjects:
Artificial intelligence not elsewhere classified
Linguistics not elsewhere classified
Blind moving source separation
Convolutive mixtures
Intensity vector direction
Location expectation
Speaker activity detection
Linguistics
Artificial Intelligence and Image Processing
Online Access:https://hdl.handle.net/2134/9536765.v1
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items