AUD-35.3
MULTIMODAL EVALUATION METHOD FOR SOUND EVENT DETECTION
Seyed Mohammad Reza Modaresi, Aomar Osmani, Sorbonne Paris Nord University, France; Mohammadreza Razzazi, Amirkabir University of Technology, Iran (Islamic Republic of); Abdelghani Chibani, Université Paris-Est Créteil, France
Session:
Detection and Classification of Acoustic Scenes and Events VII: Evaluation
Track:
Audio and Acoustic Signal Processing
Location:
Gather Area K
Presentation Time:
Fri, 13 May, 22:00 - 22:45 China Time (UTC +8)
Fri, 13 May, 14:00 - 14:45 UTC
Fri, 13 May, 14:00 - 14:45 UTC
Session Chair:
Francesca Ronchini, Inria
Session AUD-35
AUD-35.1: MAXIMIZING AUDIO EVENT DETECTION MODEL PERFORMANCE ON SMALL DATASETS THROUGH KNOWLEDGE TRANSFER, DATA AUGMENTATION, AND PRETRAINING: AN ABLATION STUDY
Daniel Tompkins, Kshitiz Kumar, Jian Wu, Microsoft, United States of America
AUD-35.2: Threshold Independent Evaluation of Sound Event Detection Scores
Janek Ebbers, Reinhold Haeb-Umbach, Paderborn University, Germany; Romain Serizel, Université de Lorraine, France
AUD-35.3: MULTIMODAL EVALUATION METHOD FOR SOUND EVENT DETECTION
Seyed Mohammad Reza Modaresi, Aomar Osmani, Sorbonne Paris Nord University, France; Mohammadreza Razzazi, Amirkabir University of Technology, Iran (Islamic Republic of); Abdelghani Chibani, Université Paris-Est Créteil, France
AUD-35.4: A BENCHMARK OF STATE-OF-THE-ART SOUND EVENT DETECTION SYSTEMS EVALUATED ON SYNTHETIC SOUNDSCAPES
Francesca Ronchini, Romain Serizel, INRIA Grand Est, France
AUD-35.5: GENERALIZING AUC OPTIMIZATION TO MULTICLASS CLASSIFICATION FOR AUDIO SEGMENTATION WITH LIMITED TRAINING DATA
Pablo Gimeno, Victoria Mingote, Alfonso Ortega, Antonio Miguel, Eduardo Lleida, ViVoLab, Aragón Institute for Engineering Research (I3A), University of Zaragoza, Spain