Tue AM1.P.2
A Two-stage CNN with Feature Reduction for Speech-aware Binaural DOA Estimation
Reza Varzandeh, Simon Doclo, Volker Hohmann, University of Oldenburg, Germany
Session:
Tue AM1.P: Acoustic Source and Event Localization Poster
Track:
ASMSP - Acoustic, Speech and Music Signal Processing
Location:
Fennia Foyer
Presentation Time:
Tue, 5 Sep, 11:00 - 13:00 Finland Time (UTC +3)
Session Chair:
Filip Elvander, Aalto University
Presentation
Discussion
Resources
No resources available.
Session Tue AM1.P
Tue AM1.P.1: IMPROVING AUDIO EVENT LOCALIZATION ACCURACY VIA DERIVATIVE PREDICTION
Ruchi Pandey, Shreyas Jaiswal, International Institute of Information Technology, Hyderabad, India; Huy Phan, Amazon Alexa, United States; Santosh Nannuru, International Institute of Information Technology Hyderabad, India
Tue AM1.P.2: A Two-stage CNN with Feature Reduction for Speech-aware Binaural DOA Estimation
Reza Varzandeh, Simon Doclo, Volker Hohmann, University of Oldenburg, Germany
Tue AM1.P.3: DATABASE OF SIMULATED ROOM IMPULSE RESPONSES FOR ACOUSTIC SENSOR NETWORKS DEPLOYED IN COMPLEX MULTI-SOURCE ACOUSTIC ENVIRONMENTS
Rene Glitza, Luca Becker, Alexandru Nelus, Rainer Martin, Ruhr-Universität Bochum, Germany
Tue AM1.P.4: POSITION TRACKING OF A VARYING NUMBER OF SOUND SOURCES WITH SLIDING PERMUTATION INVARIANT TRAINING
David Diaz-Guerra, University of Zaragoza, Spain; Archontis Politis, Tuomas Virtanen, Tampere University, Finland
Tue AM1.P.5: Reactive Intensity Vector Based Direct Path Detection for DoA Estimation on a Single Acoustic Vector Sensor
Wen Zhang, Bing Zhu, Northwestern Polytechnical University, China
Tue AM1.P.6: An Acoustic Simulation Framework to Support Indoor Positioning and Data Driven Signal Processing Assessments
Daan Delabie, Chesney Buyle, Bert Cox, Liesbet Van der Perre, Lieven De Strycker, KU Leuven, Belgium
Tue AM1.P.7: A TWO-STAGE SPEAKER EXTRACTION ALGORITHM UNDER ADVERSE ACOUSTIC CONDITIONS USING A SINGLE-MICROPHONE
Aviad Eisenberg, Sharon Gannot, Shlomo E. Chazan, Bar-Ilan University, Israel