WS-10.4
Eigenbeam-Feature-Based Multi-Order Encoder for Geometry-Agnostic Speech Enhancement
Dongzhe Zhang, Alessandro Ilic Mezza, Federico Miotello, Politecnico di Milano, Italy; Jianfeng Chen, Northwestern Polytechnical University, China; Mou Wang, Chinese Academy of Sciences, China; Fabio Antonacci, Alberto Bernardini, Politecnico di Milano, Italy
Session:
WS-10: The Joint Workshop on HSCMA and CHiME 2026: Speech processing with wearable and multimodal technologies for everyday life Oral
Track:
Satellite Workshops
Location:
Room 120+121
Presentation Time:
Mon, 4 May, 09:00 - 18:00
Presentation
Discussion
Resources
No resources available.
Session WS-10
WS-10.1: On the Role of Spatial Features in Foundation-Model-Based Speaker Diarization
Marc Deegen, Tobias Gburrek, Tobias Cord-Landwehr, Thilo von Neuman, Paderborn University, Germany; Jiangyu Han, Lukáš Burget, Brno University of Technology, Czechia; Reinhold Haeb-Umbach, Paderborn University, Germany
WS-10.2: Optimization of High Directivity Beamforming and WPE Method for Improved Speech Dereverberation
Kang Chen, Hanchen Pei, Gongping Huang, Wuhan University, China
WS-10.3: Blind Direction-Dependent Acoustic Parameter Estimation using Smart Glasses
Philipp Götz, International Audio Laboratories, Germany; Sebastià V. Amengual, Paul Calamia, Ishwarya Ananthabhotla, Andrew Francl, Carl Schissler, Meta Reality Labs, United States of America; Emanuël A. P. Habets, International Audio Laboratories, Germany
WS-10.4: Eigenbeam-Feature-Based Multi-Order Encoder for Geometry-Agnostic Speech Enhancement
Dongzhe Zhang, Alessandro Ilic Mezza, Federico Miotello, Politecnico di Milano, Italy; Jianfeng Chen, Northwestern Polytechnical University, China; Mou Wang, Chinese Academy of Sciences, China; Fabio Antonacci, Alberto Bernardini, Politecnico di Milano, Italy
WS-10.5: DISCRIMINATING REAL AND SYNTHETIC SUPER-RESOLVED AUDIO SAMPLES USING EMBEDDING-BASED CLASSIFIERS
Mikhail Silaev, Tampere University, Finland; Konstantinos Drossos, Nokia Technologies, Finland; Tuomas Virtanen, Tampere University, Finland
WS-10.6: Target-speaker voice activity detection with chunk-level speaker queries
Naohiro Tawara, Shota Horiguchi, NTT, Inc., Japan
WS-10.7: Geneses: Unified Generative Speech Enhancement and Separation
Kohei Asai, Wataru Nakata, Yuki Saito, Hiroshi Saruwatari, The University of Tokyo, Japan
WS-10.8: An Analysis on the Influence of Array Element Directivity on the Performance of Differential Beamformers
Federico Miotello, Politecnico di Milano, Italy; Davide Albertini, STMicroelectronics, Italy; Alberto Bernardini, Politecnico di Milano, Italy
Contacts