Thu AM1.L1.1
Uncertainty in Semi-supervised Audio Classification -- A Novel Extension for FixMatch
Sascha Grollmisch, Fraunhofer IDMT, Germany; Estefanía Cano, Songquito UG, Germany; Hanna Lukashevich, Jakob Abeßer, Fraunhofer IDMT, Germany
Session:
Thu AM1.L1: Acoustic scene classification and event detection Lecture
Track:
ASMSP - Acoustic, Speech and Music Signal Processing
Location:
EUROPAEA
Presentation Time:
Thu, 7 Sep, 10:30 - 10:50 Finland Time (UTC +3)
Session Chair:
Sharon Gannot, Bar-Ilan University
Presentation
Discussion
Resources
No resources available.
Session Thu AM1.L1
Thu AM1.L1.1: Uncertainty in Semi-supervised Audio Classification -- A Novel Extension for FixMatch
Sascha Grollmisch, Fraunhofer IDMT, Germany; Estefanía Cano, Songquito UG, Germany; Hanna Lukashevich, Jakob Abeßer, Fraunhofer IDMT, Germany
Thu AM1.L1.3: AUTOMATIC TV GENRE CLASSIFICATION BASED ON VISUALLY-CONDITIONED DEEP AUDIO FEATURES
Alessandro Ilic Mezza, Paolo Sani, Augusto Sarti, Politecnico di Milano, Italy
Thu AM1.L1.4: ANOMALOUS SOUND EVENT DETECTION BASED ON ONE-CLASS CLASSIFICATION USING VARIATIONAL AUTOENCODERS AND INTERVAL TYPE-2 FUZZY SETS
Zied Mnasri, University Tunis El Manar, Tunisia; Stefano Rovetta, Francesco Masulli, Università degli studi di Genova, Italy
Thu AM1.L1.5: DEVICE-ROBUST ACOUSTIC SCENE CLASSIFICATION VIA IMPULSE RESPONSE AUGMENTATION
Tobias Morocutti, Florian Schmid, Khaled Koutini, Gerhard Widmer, Johannes Kepler University Linz, Austria
Thu AM1.L1.6: DOMAIN INFORMATION CONTROL AT INFERENCE TIME FOR ACOUSTIC SCENE CLASSIFICATION
Shahed Masoudian, Khaled Koutini, Markus Schedl, Gerhard Widmer, Navid Rekabsaz, Johannes Kepler University, Linz, Austria