Tuesday, Sept. 6

9:00 – 9:30 Opening
Plenary Hall  
9:30 – 10:30 Keynote 1
Plenary Hall Chair: Walter Kellermann

The Evolution of Microphone Array Beamformers
Jens Meyer and Gary W. Elko
mh acoustics
10:30 – 11:00 Coffee Break
Poster Area

11:00 – 12:30 
Poster Session A
Poster Area
Chair: Emanuël A. P. Habets
A-01 Joint Analysis of Acoustic Scenes and Sound Events with Weakly Labeled Data
Shunsuke Tsubaki1, Keisuke Imoto1, and Nobutaka Ono2
1Doshisha University, Japan
2Tokyo Metropolitan University, Japan
A-02 Preservation of Interaural Level Difference Cue in a Deep Learning-Based Speech Separation System for Bilateral and Bimodal Cochlear Implants User
Zicheng Feng1, Yu Tsao2, and Fei Chen1
1Southern University of Science and Technology, China
2Academia Sinica, Taiwan
A-03 Distributed Synchronization for Ad-Hoc Acoustic Sensor Networks using Closed-Loop Double-Cross-Correlation Processing
Aleksej Chinaev and Gerald Enzner
University of Oldenburg, Germany
A-04 Incremental Method of Permutation Alignment for Frequency-Domain Blind Source Separation
Satoru Emura
Kyoto University of Advanced Science, Japan
A-05 Direction of Arrival Estimation for Reverberant Speech based on Neural Networks and the Direct-Path Dominance Test
Orel Ben Zaken1, Boaz Rafaely1, Anurag Kumar2, and Vladimir Tourbabin2
1Ben-Gurion University of the Negev, Israel
2 Reality Labs Research at Meta, USA
A-06 User Preference between Residual Noise and Speech Distortion in Speech Enhancement
Akihiko Sugiyama1, Osamu Shimada2, and Toshiyuki Nomura2
1Yahoo Japan Corporation, Japan
NEC Corporation, Japan
A-07 Enhancement of Hearing Aid Processing via Spatial Spectro-Temporal Post-Filtering with a Prototype Eyeglass-Integrated Array
Marcos Cantu and Volker Hohmann
University of Oldenburg, Germany
A-08 Sector-based Parametric Sound Field Reproduction in the Circular Harmonic Domain using Covariance based Rendering
Carlotta Anemüller, Oliver Thiergart, and Emanuël A. P. Habets
International Audio Laboratories Erlangen, Germany
A-09 Deep Multi-Frame MVDR Filtering for Binaural Noise Reduction
Marvin Tammen and Simon Doclo
University of Oldenburg, Germany
A-10 Model-Based Estimation of In-Car-Communication Feedback Applied to Speech Zone Detection
Kaspar Müller1, Simon Doclo2, Jan Østergaard3, and Tobias Wolff1
1Cerence, Germany,
2University of Oldenburg, Germany
3Aalborg University, Denmark
A-11 Beyond Griffin-Lim: Improved Iterative Phase Retrieval for Speech
Tal Peer, Simon Welker, and Timo Gerkmann
University of Hamburg, Germany
A-12 Mechatronic Generation of Datasets for Acoustics Research
Austin Lu, Kanad Sarkar, Manan Mittal, Ryan Corey, Paris Smaragdis, and Andrew Singer
University of Illinois at Urbana-Champaign, USA
A-13 Polynomial Eigenvalue Decomposition-Based Target Speaker Voice Activity Detection in the Presence of Competing Talkers
Vincent W. Neo1, Stephan Weiss2, Simon W. McKnight1, Aidan O. T. Hogg1, and Patrick A. Naylor1
1Imperial College London, UK
2University of Strathclyde, UK
A-14 Acoustic System Identification with Partially Time-Varying Models Based on Tensor Decompositions
Gongping Huang1, Jacob Benesty2, Jingdong Chen3, Constantin Paleologu4, Silviu Ciochina4, Walter Kellermann1, and Israel Cohen5
1Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany
2University of Quebec, Canada
3Northwestern Polytechnical University, China
4University Politehnica of Bucharest, Romania
5Technion – Israel Institute of Technology, Israel
A-15 Binaural Speech Enhancement using STOI Optimal Masks
Vikas Tokala, Mike Brookes, and Patrick A. Naylor
Imperial College London, UK
12:30 – 14:00 Lunch Break
Lunch Room

14:00 – 15:30 
Poster Session B
Poster Area
Chair: Simon Doclo
B-01 Self-Attention with Restricted Time Context and Resolution in DNN Speech Enhancement
Maximilian Strake, Adrian Behlke, and Tim Fingscheidt
Technische Universität Braunschweig, Germany
B-02 Blind Extraction of Target Speech Source: Three Ways of Guidance Exploiting Supervised Speaker Embeddings
Jiri Malek, Jaroslav Cmejla, and Zbynek Koldovsky
Technical University of Liberec, Czechia
B-03 Spherical Sector Harmonics based Directional Drone Noise Reduction
Hanwen Bi, Fei Ma, Thushara Abhayapala, and Prasanga Samarasinghe
Australian National University, Australia
B-04 Semi-supervised Domain Adaptation for Acoustic Scene Classification by Minimax Entropy and Self-supervision Approaches
Yukiko Takahashi1, Sawa Takamuku1, Keisuke Imoto2, and Naotake Natori1
1AISIN Corporation, Japan
2Doshisha University, Japan
B-05 Joint Localization and Synchronization of Distributed Camera-attached Microphone Arrays for Indoor Scene Analysis
Yoshiaki Sumura1, Kouhei Sekiguchi2, Yoshiaki Bando3, Aditya Arie Nugraha2, and Kazuyoshi Yoshii1
1Kyoto University, Japan
2RIKEN Center for Advanced Intelligence Project, Japan
3National Institute of Advanced Industrial Science and Technology, Japan
B-06 DNN-based Speech Quality Assessment for Binaural Signals
Jan Reimes
HEAD acoustics, Germany
B-07 Simulating Wind Noise with Airflow Speed-Dependent Characteristics
Daniele Mirabilii1, Alexander Lodermeyer1, Felix Czwielong2, Stefan Becker2, and Emanuël A. P. Habets1
1International Audio Laboratories Erlangen, Germany
2Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany
B-08 Frequency-domain MIMO Acoustic Echo Cancellation Based on a Kronecker Product Approximation
Mhd Modar Halimeh and Walter Kellermann
Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany
B-09 On the Importance of Acoustic Reflections in Beamforming
Oren Shmaryahu and Sharon Gannot
Bar-Ilan University, Israel
B-10 Do You Listen with One or Two Microphones? A Unified ASR Model for Single and Multi-Channel Audio
Gokce Keskin, Minhua Wu, Brian King, Harish Mallidi, Yang Gao, Jasha Droppo, Ariya Rastrow, and Roland Maas
Amazon, USA
B-11 Subspace Constrained Independent Vector Extraction
Tongzheng Liu and Zhihua Lu
Ningbo University, China
B-12 Binaural Reproduction using Multi-Driver Headphones
Jiarui Wang, Prasanga Samarasinghe, Thushara Abhayapala, and Jihui Aimee Zhang
Australian National University, Australia
B-13 Utterance Weighted Multi-Dilation Temporal Convolution Networks for Monaural Speech Dereverberation
William Ravenscroft, Stefan Goetze, and Thomas Hain
University of Sheffield, UK
B-14 Meta-Learning for Adaptive Filters with Higher-Order Frequency Dependencies
Junkai Wu1, Jonah Casebeer1, Nicholas Bryan2, and Paris Smaragdis2
1University of Illinois at Urbana-Champaign, USA
2Adobe Research, USA
B-15 Adaptive Crosstalk Cancellation and Spatialization for Dynamic Group Conversation Enhancement Using Mobile and Wearable Devices
Ryan Corey, Manan Mittal, Kanad Sarkar, and Andrew Singer
University of Illinois at Urbana-Champaign, USA
B-16 Streaming Noise Context Aware Enhancement for Automatic Speech Recognition in Multi-Talker Environments
Joseph Caroselli, Arun Narayanan, and Yiteng Huang
Google, USA
15:30 – 16:00
Coffee Break
Poster Area

16:00 – 17:30  Poster Session C
Poster Area
Chair:Thushara Abhayapala
C-01 Joint Acoustic Echo Cancellation and Blind Source Extraction based on Independent Vector Extraction
Thomas Haubner1, Zbynek Koldovsky2, and Walter Kellermann1
1Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany
2Technical University of Liberec, Czechia
C-02 GMM based Multi-stage Wiener Filtering for Low SNR Speech Enhancement
Wageesha Manamperi, Prasanga Samarasinghe, Thushara Abhayapala, and Jihui Zhang
Australian National University, Australia
C-03 Learnable Acoustic Frontends in Bird Activity Detection
Mark Anderson and Naomi Harte
Trinity College Dublin, Ireland
C-04 Bias Analysis of Spatial Coherence-Based RTF Vector Estimation for Acoustic Sensor Networks in a Diffuse Sound Field
Wiebke Middelberg and Simon Doclo
University of Oldenburg, Germany
C-05 Deep Complex-Valued Convolutional-Recurrent Networks for Single Source DOA Estimation
Eric Grinstein and Patrick A. Naylor
Imperial College London, UK
C-06 Statistical Analysis of Randomness in Training of Small-Scale Neural Networks for Speech Enhancement
Annika Briegleb and Walter Kellermann
Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany
C-07 Acoustic Room Compensation using Local PCA-based Room Average PSD Estimation
Wenyu Jin, Patrick McPherson, Chris Pike, and Adib Mehrabi
Sonos, USA/UK
C-08 Differential and Constant-Beamwidth Beamforming with Uniform Rectangular Arrays
Gal Itzhak and Israel Cohen
Technion – Israel Institute of Technology, Israel
C-09 Frame-based Space-Time Covariance Matrix Estimation for Polynomial Eigenvalue Decomposition-based Speech Enhancement
Emilie d’Olne, Vincent W. Neo, and Patrick A. Naylor
Imperial College London, UK
C-10 A Distributed Steered Response Power Approach to Source Localization in Wireless Sensor Networks
Bilgesu Çakmak1, Thomas Dietzen1, Randall Ali1, Patrick A. Naylor2, and Toon van Waterschoot1
1KU Leuven, Belgium
2Imperial College London, UK
C-11 Robust Acoustic Contrast Control with Positive Semidefinite Constraint using Iterative POTDC Algorithm
Junqing Zhang1, Liming Shi2, Mads G. Christensen2, Wen Zhang1, Lijun Zhang1, and Jingdong Chen1
1Northwestern Polytechnical University, China
2Aalborg University, Denmark
C-12 Pareto Optimal Binaural MVDR Beamformer with Controllable Interference Suppression
1Elior Hadad, Simon Doclo2, Sven Nordholm3, and Sharon Gannot1
1Bar-Ilan University, Israel
2University of Oldenburg, Germany
3Curtin University, Australia
C-13 Speaker-Conditioning Single-Channel Target Speaker Extraction using Conformer-based Architectures
Ragini Sinha1, Marvin Tammen2, Christian Rollwage1, and Simon Doclo2
1Fraunhofer Institute for Digital Media Technology IDMT
2University of Oldenburg, Germany
C-14 Analysis of Impact of Emotions on Target Speech Extraction and Speech Separation
Ján Švec1, Kateřina Žmolíková1, Martin Kocour1, Marc Delcroix2, Tsubasa Ochiai2, Ladislav Mošner1, and Jan Černocký1
1Brno University of Technology, Czechia
2NTT Communications Science Laboratories, Japan
C-15 Blind Directional Room Impulse Response Parameterization from Relative Transfer Functions
Nils Meyer-Kahlen and Sebastian J. Schlecht
Aalto University, Finland
18:00 – 23:00
Banquet at Schloss Weissenstein