Signal Processing and Machine Learning for Spatially Distributed Microphones
A joint workshop of DFG Research Unit FOR 2457 “Acoustic Sensor Networks (ASN)” and the Marie Sklodowska-Curie Actions European Training Network “Service-Oriented, Ubiquitous, Network-Driven Sound (SOUNDS)” is offered as satellite event to IWAENC 2022 on Sept. 5, 2022.
The ubiquity of mobile and wearable devices in our everyday environments offers great opportunities for capturing, processing, interpreting and reproducing speech and, more generally, audio. Network-enabled acoustic sensor nodes overcome the limitations of a single device and promise great advances in user experience and novel applications.
This workshop gives an overview of the state of the art in this exciting field of research. The topics include, but are not limited to
- Networking: Dynamic task allocation for optimal trade-off between signal processing and networking constraints
- Synchronization: Clock synchronization and geometry calibration of distributed sensor nodes in dynamic acoustic environments
- Speech enhancement: Dereverberation, source separation, noise reduction and acoustic beamforming with spatially distributed microphones
- Sound recognition: Acoustic scene and event classification, information fusion and use of spatial information for classification
- Privacy: Signal Processing and Machine Learning to ensure privacy in acoustic sensor networks.
The workshop features a keynote, survey talks, posters, and demonstrations, together with pointers to software and hardware to probe further and gain hands-on experience with acoustic sensor networks.
Tuomas Virtanen, Tampere University
Reinhold Häb-Umbach, University Paderborn
Toon van Waterschoot, KU Leuven
|15:30||Demo and Poster Session
Further details will be announced in due time. There are no registration fees for this workshop, but please indicate your participation by ticking the corresponding box in the registration form for IWAENC 2022.