TU2.P2.11
THIRD-ORDER TENSOR DECOMPOSITION BASED MULTICHANNEL LINEAR PREDICTION FOR ROBUST DEREVERBERATION
Shekhar Kumar Yadav, Nithin V. George, Indian Institute of Technology Gandhinagar, India
Session:
TU2.P2: Poster Session IV: Microphone array processing, Acoustic sensor networks Poster
Track:
Acoustic echo and feedback suppression
Location:
Indgangsfoyer
Presentation Time:
Tue, 10 Sep, 15:30 - 17:30 Central European Time (UTC +1)
Session Chair:
Simon Doclo, University of Oldenburg
Presentation
Discussion
Resources
No resources available.
Session TU2.P2
TU2.P2.1: JOINT OPTIMIZATION OF MICROPHONE ARRAY GEOMETRY AND REGION-OF-INTEREST BEAMFORMING WITH SPARSE CIRCULAR SECTOR ARRAYS
Gal Itzhak, Technion, Israel; Simon Doclo, University of Oldenburg, Germany; Israel Cohen, Technion, Israel
TU2.P2.2: Joint Audio Source Localization and Separation With Distributed Microphone Arrays Based on Spatially-Regularized Multichannel NMF
Yoshiaki Sumura, Kyoto University/RIKEN, Japan; Diego Di Carlo, Aditya Arie Nugraha, RIKEN, Japan; Yoshiaki Bando, AIST/RIKEN, Japan; Kazuyoshi Yoshii, Kyoto University/RIKEN, Japan
TU2.P2.3: The acoustic velocity vectors of the outgoing sound field
Frank Jiarui Wang, Prasanga Samarasinghe, Thushara Abhayapala, The Australian National University, Australia; Jihui Aimee Zhang, University of Southampton, United Kingdom of Great Britain and Northern Ireland
TU2.P2.4: UTILIZING HEAD ROTATION DATA IN DNN-BASED MULTI-CHANNEL SPEECH ENHANCEMENT FOR HEARING AIDS
Benjamin Lentz, Rainer Martin, Ruhr University Bochum, Germany
TU2.P2.5: GREEDY DESIGN OF CIRCULAR CONCENTRIC ARRAYS FOR BROADBAND MVDR
yaakov buchris, Israel cohen, Alon Amar, technion, Israel
TU2.P2.6: LOW LATENCY TWO STAGE BEAMFORMING WITH DISTRIBUTED MICROPHONE ARRAYS USING A PLANE WAVE DECOMPOSITION
Manan Mittal, Stony Brook University, United States of America; Ryan Corey, University of Illinois Chicago, Discovery Partners Institute, United States of America; Yongjie Zhuang, Andrew Singer, Stony Brook University, United States of America
TU2.P2.7: ITERATIVE AND COMPLEX ORTHOGONAL MATCHING PURSUIT FOR BROADBAND SPARSE SOUND FIELD RECONSTRUCTION
Shaoheng Xu, The Australian National University, Australia; Jihui Aimee Zhang, University of Southampton, United Kingdom of Great Britain and Northern Ireland; Thushara Abhayapala, Amy Bastine, Prasanga Samarasinghe, The Australian National University, Australia
TU2.P2.8: META-LEARNING FOR VARIABLE ARRAY CONFIGURATIONS IN END-TO-END FEW-SHOT MULTICHANNEL SPEECH ENHANCEMENT
Alina Mannanova, Kristina Tesch, Jean-Marie Lemercier, Timo Gerkmann, Universität Hamburg, Germany
TU2.P2.9: A PHYSICS-INFORMED NEURAL NETWORK-BASED APPROACH FOR THE SPATIAL UPSAMPLING OF SPHERICAL MICROPHONE ARRAYS
Federico Miotello, Ferdinando Terminiello, Mirco Pezzoli, Alberto Bernardini, Fabio Antonacci, Augusto Sarti, Politecnico di Milano, Italy
TU2.P2.10: ON LIMITATIONS AND IMPROVEMENT OF DIFFERENTIAL BEAMFORMING VIA QUADRATIC EIGENVALUE OPTIMIZATION
Jingli Xie, Northwestern Polytechnical University, China; Xudong Zhao, King's College London, United Kingdom of Great Britain and Northern Ireland; Junqing Zhang, Northwestern Polytechnical University, China; Jacob Benesty, INRS-EMT, Canada; Jingdong Chen, Northwestern Polytechnical University, China
TU2.P2.11: THIRD-ORDER TENSOR DECOMPOSITION BASED MULTICHANNEL LINEAR PREDICTION FOR ROBUST DEREVERBERATION
Shekhar Kumar Yadav, Nithin V. George, Indian Institute of Technology Gandhinagar, India
TU2.P2.12: Latency-agnostic speech enhancement for wireless acoustic sensor networks using polynomial eigenvalue decomposition
Emilie d'Olne, Vincent W. Neo, Patrick A. Naylor, Imperial College London, United Kingdom of Great Britain and Northern Ireland
TU2.P2.13: EFFICIENT, CLUSTER-INFORMED, DEEP SPEECH SEPARATION WITH CROSS-CLUSTER INFORMATION IN AD-HOC WIRELESS ACOUSTIC SENSOR NETWORKS
Stijn Kindt, Ghent University - imec, Belgium; Jihyun Kim, Hong-Goo Kang, Yonsei University, Korea, Republic of; NIlesh Madhu, Ghent University - imec, Belgium
TU2.P2.14: SOURCE SIGNAL CAPTURE IN ACOUSTIC SENSOR NETWORKS BASED ON ROBUST BEAMFORMING AND SOURCE-RELATED CLUSTER ESTIMATION
Luca Becker, Kamel Naame, Rainer Martin, Ruhr-University Bochum, Germany
TU2.P2.15: ONE-SHOT DISTRIBUTED NODE-SPECIFIC SIGNAL ESTIMATION WITH NON-OVERLAPPING LATENT SUBSPACES IN ACOUSTIC SENSOR NETWORKS
Paul Didier, Pourya Behmandpoor, Toon van Waterschoot, Marc Moonen, KU Leuven University, Belgium