| 9:00 – 10:00 | Keynote 2 |
| Plenary Hall | Chair: Tim Fingscheidt Pushing the Limits of Speech Enhancement Technology Shoko Araki NTT Communication Science Laboratories |
| 10:00 – 10:30 | Coffee Break |
| Poster Area | |
| 10:30 – 12:30 |
Lecture Session: Bester Paper Award Contest |
| Poster Area |
Chairs: Peter Jax and Rainer Martin |
| L-01 | Bilateral-Ambisonic Reproduction by Soundfield Translation Lachlan Birnie1, Zamir Ben-Hur2, Vladimir Tourbabin2, Thushara Abhayapala1, and Prasanga Samarasinghe1 1Australian National University, Australia 2Reality Labs Research at Meta, USA |
| L-02 | Head-Related
Transfer Function Interpolation from Spatially Sparse Measurements
Using Autoencoder with Source Position Conditioning Yuki Ito, Tomohiko Nakamura, Shoichi Koyama, and Hiroshi Saruwatari University of Tokyo, Japan |
| L-03 | Occlusion Effect Reduction Using a Vibration Sensor Christoph Weyer and Peter Jax RWTH Aachen University, Germany |
| L-04 | AmbiSep: Ambisonic-to-Ambisonic Reverberant Speech Separation Using Transformer Networks Adrian Herzog, Srikanth Chetupalli, and Emanuël A. P. Habets International Audio Laboratories Erlangen, Germany |
| L-05 | Distributed Cross-Relation-Based Frequency-Domain Blind System Identification using Online-ADMM Matthias Blochberger1, Filip Elvander1, Randall Ali1, Marc Moonen1, Jan Østergaard2, Jesper Jensen2, and Toon van Waterschoot1 1KU Leuven, Belgium 2Aalborg University, Denmark |
| L-06 | Monaural Source Separation: From Anechoic to Reverberant Environments Tobias Cord-Landwehr1, Christoph Böddeker1, Thilo von Neumann1, Catalin Zorila2, Rama Doddipatla2, and Reinhold Häb-Umbach1 1Paderborn University, Germany 2Toshiba Cambridge Research Laboratory, UK |
| 12:30 – 14:00 | Lunch Break |
| Lunch Room |
|
| 14:00 – 16:00 |
Poster Session D |
| Poster Area | Chair: Timo Gerkmann |
| D-01 | Does a PESQNet (Loss) Require a Clean Reference Input? The Original PESQ Does, But ACR Listening Tests Don’t Ziyi Xu, Maximilian Strake, and Tim Fingscheidt Technische Universität Braunschweig, Germany |
| D-02 | Machine Learning for Parameter Estimation in the MBSTOI Binaural Intelligibility Metric Pierre Guiraud, Alastair H. Moore, Rebecca R. Vos, Patrick A. Naylor, and Mike Brookes Imperial College London, UK |
| D-03 | The SEBASS-DB: A Consolidated Public Data Base of Listening Test Results for Perceptual Evaluation of BSS Quality Measures Thorsten Kastner and Jürgen Herre International Audio Laboratories Erlangen, Germany |
| D-04 | Explainable Acoustic Scene Classification: Making Decisions Audible Hasan Nazim Bicer1, Philipp Goetz1, Cagdas Tuna2, and Emanuël A. P. Habets1 1International Audio Laboratories Erlangen, Germany 2Fraunhofer Institute for Integrated Circuits IIS Erlangen, Germany |
| D-05 | Dictionary-Based Fusion of Contact and Acoustic Microphones for Wind Noise Reduction Marvin Tammen1, Xilin Li2, Simon Doclo1, and Lalin Theverapperuma2 1University of Oldenburg, Germany 2Reality Labs Research at Meta, USA |
| D-06 | Coherence-based Frequency Subset Selection for Binaural RTF-Vector-based Direction of Arrival Estimation for Multiple Speakers Daniel Fejgin and Simon Doclo University of Oldenburg, Germany |
| D-07 | BonsApps Keyword Spotting Challenge: Environment Aware Universal Keyword Encoder for Low Foot Print Devices Moammed Hafsati and Kamil Bentounes Tuito, France |
| D-08 | A Linear MMSE Filter using Delayed Remote Microphone Signals for Speech Enhancement in Hearing Aid Applications Vasudha Sathyapriyan1,2, Michael S. Pedersen2, Jan Østergaard1, Mike Brookes3, Patrick A. Naylor3, and Jesper Jensen1,2 1Aalborg University, Denmark 2Demant A/S, Denmark 3Imperial College London, UK |
| D-09 | Polynomial Multiple Variance Impulse Response Measurement Riccardo Forti1, Alberto Carini1, and Simone Orcioni2 1University of Trieste, Italy 2Università Politecnica delle Marche, Italy |
| D-10 | Robust Feedback Active Noise Control in Headphones Based on a Data-Driven Uncertainty Model Florian Hilgemann and Peter Jax RWTH Aachen University, Germany |
| D-11 | A Deep Learning-based Pressure Matching Approach to Soundfield Synthesis Luca Comanducci, Fabio Antonacci, and Augusto Sarti Politecnico di Milano, Italy |
| D-12 | An EEG-based Study of Auditory Sensitivity in Spatial Hearing Yihan Wang, Zhixing Liu, and Fei Chen Southern University of Science and Technology, China |
| D-13 | Comparison of Position Estimation Methods for the Rotating Equatorial Microphone Jeremy Lawrence1, Jens Ahrens2, and Nils Peters1 1International Audio Laboratories Erlangen, Germany 2Chalmers University of Technology, Sweden |
| D-14 | DNN-Free Low-Latency Adaptive Speech Enhancement Based on Frame-Online Beamforming Powered by Block-Online FastMNMF Aditya Arie Nugraha1, Kouhei Sekiguchi1, Mathieu Fontaine2, Yoshiaki Bando3, and Kazuyoshi Yoshii4 1RIKEN Center for Advanced Intelligence Project, Japan 2Télécom Paris, France 3National Institute of Advanced Industrial Science and Technology, Japan 4Kyoto University, Japan |
| 14:00 – 16:00 | Demonstrations A |
| Chair: Henning Puder |
|
| DA-01 Room K3 |
3PASS – Realistic Testing Matters Natalia Manrique, Jan Reimes, and Christian Schüring HEAD acoustics, Germany |
| DA-02 Room K8 |
Demonstration
of Spatial Spectro-Temporal Filtering with a Prototype
Eyeglass-Integrated Array and the openMHA Real-Time Audio Signal
Processing Platform Marcos A. Cantu and Volker Hohmann University of Oldenburg, Germany |
| DA-03 Hotel Entrance |
In-Car Communication and Karaoke System in Passenger Van Markus Buck, Tim Haulick, and Tobias Wolf Cerence, Germany |
| 16:00-16:10 | Group Photo |
| Hotel Lobby | |
| 16:10-18:00 | Guided City Tours |