ASMSP-P2: Multichannel and Spatial Audio Processing
Tue, 9 Sep, 16:00 - 17:40 Italy Time (UTC +2)
Location: Poster Area A
Session Type: Poster
Session Co-Chairs: Peter Jax, Rheinisch-Westfälische Technische Hochschule Aachen and Jesper Rindom Jensen, Aalborg University
Track: ASMSP - Acoustic, Speech and Music Signal Processing

ASMSP-P2.1: CHURCHIR: A DATASET OF MULTICHANNEL CHURCH IMPULSE RESPONSES FOR SPATIAL AUDIO APPLICATIONS

Riccardo Giampiccolo, Sofia Parrinelli, Fabio Antonacci, Politecnico di Milano, Italy

ASMSP-P2.2: TARGET SPEAKER SELECTION FOR NEURAL NETWORK BEAMFORMING IN MULTI-SPEAKER SCENARIOS

Luan Vinícius Fiorio, Eindhoven University of Technology, Netherlands; Bruno Defraene, Johan David, Alex Young, Frans Widdershoven, Wim van Houtum, NXP Semiconductors, Belgium; Ronald M. Aarts, Eindhoven University of Technology, Netherlands

ASMSP-P2.3: HIGHER-ORDER AMBISONICS UPSCALING USING GATED RECURRENT UNITS

Egke Chatzimoustafa, Peter Jax, Rheinisch-Westfälische Technische Hochschule Aachen, Germany

ASMSP-P2.4: Array Agnostic Multi-channel Speech Presence Probability Estimation

Shuai Tao, Aalborg University, Denmark; Kaixuan Yang, Stijn Kindt, Ghent University, Belgium; Jesper Rindom Jensen, Mads Græsbøll Christensen, Aalborg University, Denmark; Nilesh Madhu, Ghent University, Belgium

ASMSP-P2.5: ROOM IMPULSE RESPONSE ESTIMATION THROUGH OPTIMAL MASS TRANSPORT BARYCENTERS

Rumeshika Pallewela, Yuyang Liu, Filip Elvander, Aalto University, Finland

ASMSP-P2.6: A Lightweight Cross-Domain Front-End Feature Extractor for Multichannel Voice Activity and Overlapped Speech Detection

Shaojie Li, College of Computer Science/Inner Mongolia University, China; Qintuya Si, College of Electronic and Information Engineering/Inner Mongolia University, China; De Hu, College of Computer Science/Inner Mongolia University, China

ASMSP-P2.7: ROBUST DIFFERENTIAL BEAMFORMERS FOR LINEAR SUPERARRAYS WITH NON-UNIFORMLY ORIENTED DIRECTIONAL MICROPHONES

Weilong Huang, Emanuël Habets, Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany

ASMSP-P2.8: Coding Higher Order Ambisonics in 3GPP IVAS – Scaling Parametric Audio Coding to Higher Bitrates

Christoph Hold, Aalto University, Finland; Dominik Weckbecker, Guillaume Fuchs, Markus Multrus, Fraunhofer IIS, Germany; Rishabh Tyagi, Stefanie Brown, Juan Torres, Stefan Bruhn, Dolby Laboratories, Australia

ASMSP-P2.9: A MACHINE LEARNING APPROACH FOR DENOISING AND UPSAMPLING HRTFS

Xuyi Hu, Jian Li, Lorenzo Picinali, Imperial College London, United Kingdom; Aidan Hogg, Queen Mary University of London, United Kingdom

ASMSP-P2.10: EVALUATING MULTICHANNEL SPEECH ENHANCEMENT ALGORITHMS AT THE PHONEME SCALE ACROSS GENDERS

Nasser-eddine Monir, Paul Magron, Romain Serizel, Université de Lorraine, CNRS, Inria, Loria, France