AUD-L5: Classification of Acoustic Scenes and Events |
| Session Type: Lecture |
| Time: Wednesday, 6 May, 16:30 - 18:30 |
| Location: On-Demand |
| Virtual Session: View on Virtual Platform |
| Session Chair: Shinji Watanabe, Waseda University |
| AUD-L5.1: COINCIDENCE, CATEGORIZATION, AND CONSOLIDATION: LEARNING TO RECOGNIZE SOUNDS WITH MINIMAL SUPERVISION |
| Aren Jansen; Google Research |
| Daniel P. W. Ellis; Google Research |
| Shawn Hershey; Google Research |
| R. Channing Moore; Google Research |
| Manoj Plakal; Google Research |
| Ashok Popat; Google Research |
| Rif A. Saurous; Google Research |
| AUD-L5.2: ACOUSTIC SCENE CLASSIFICATION FOR MISMATCHED RECORDING DEVICES USING HEATED-UP SOFTMAX AND SPECTRUM CORRECTION |
| Truc Nguyen; Graz University of Technology |
| Franz Pernkopf; Graz University of Technology |
| Michal Kosmider; Samsung R&D Institute |
| AUD-L5.3: LIMITATIONS OF WEAK LABELS FOR EMBEDDING AND TAGGING |
| Nicolas Turpault; Université de Lorraine, CNRS, Inria, Loria |
| Romain Serizel; Université de Lorraine, CNRS, Inria, Loria |
| Emmanuel Vincent; Université de Lorraine, CNRS, Inria, Loria |
| AUD-L5.4: MT-GCN FOR MULTI-LABEL AUDIO TAGGING WITH NOISY LABELS |
| Harsh Shrivastava; National University of Singapore and MIDAS Lab, IIIT-D |
| Yifang Yin; National University of Singapore |
| Rajiv Ratn Shah; MIDAS Labs, IIIT Delhi |
| Roger Zimmermann; National University of Singapore |
| AUD-L5.5: ACOUSTIC SCENE CLASSIFICATION USING DEEP RESIDUAL NETWORKS WITH LATE FUSION OF SEPARATED HIGH AND LOW FREQUENCY PATHS |
| Mark D. McDonnell; University of South Australia |
| Wei Gao; University of South Australia |
| AUD-L5.6: END-TO-END AUDITORY OBJECT RECOGNITION VIA INCEPTION NUCLEUS |
| Mohammad Ebrahimpour; University of California, Merced |
| Timothy Shea; Accenture Technology Labs |
| Andreea Danielescu; Accenture Technology Labs |
| David Noelle; University of California, Merced |
| Chris Kello; University of California, Merced |