WE1.SC2.6
DIRECT UPDATE OF BACK-PROJECTED DEMIXING MATRICES IN BLIND SOURCE SEPARATION
Yui Kuriki, Taishi Nakashima, Nobutaka Ono, Tokyo Metropolitan University, Japan
Session:
WE1.SC2: Advanced Signal Processing and Machine Learning for Acoustic Scene Analysis and Signal Enhancement Lecture
Track:
Special Sessions
Location:
Saint Clair 2
Presentation Time:
Wed, 28 Aug, 12:10 - 12:30 France Time (UTC +1)
Session Co-Chairs:
Shoji Makino, Waseda University and Nobutaka Ono, Tokyo Metropolitan University
Presentation
Discussion
Resources
No resources available.
Session WE1.SC2
WE1.SC2.1: Concurrent Speaker Detection: A Multi-microphone Transformer-Based Approach
Amit Eliav, Sharon Gannot, Bar-Ilan University, Israel
WE1.SC2.2: From Weak to Strong Sound Event Labels using Adaptive Change-Point Detection and Active Learning
John Martinsson, RISE Research Institutes of Sweden, Lund University, Sweden; Olof Mogren, RISE Research Institutes of Sweden, Sweden; Maria Sandsten, Lund University, Sweden; Tuomas Virtanen, Tampere University, Finland
WE1.SC2.3: SPATIALLY CONSTRAINED VS. UNCONSTRAINED FILTERING IN NEURAL SPATIOSPECTRAL FILTERS FOR MULTICHANNEL SPEECH ENHANCEMENT
Annika Briegleb, Walter Kellermann, Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany
WE1.SC2.4: Low algorithmic delay implementation of convolutional beamformer for online joint source separation and dereverberation
Kaien Mo, Waseda University, Japan; Xianrui Wang, Yichen Yang, Northwestern Polytechnical University, China; Shoji Makino, Waseda University, Japan; Jingdong Chen, Northwestern Polytechnical University, China
WE1.SC2.5: STEERED RESPONSE POWER-BASED DIRECTION-OF-ARRIVAL ESTIMATION EXPLOITING AN AUXILIARY MICROPHONE
Klaus Brümann, Simon Doclo, Carl von Ossietzky Universität, Germany
WE1.SC2.6: DIRECT UPDATE OF BACK-PROJECTED DEMIXING MATRICES IN BLIND SOURCE SEPARATION
Yui Kuriki, Taishi Nakashima, Nobutaka Ono, Tokyo Metropolitan University, Japan