2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

Click on the icon to view the manuscript on IEEE XPlore in the IEEE ICASSP 2021 Open Preview.

AUD-13: Detection and Classification of Acoustic Scenes and Events 2: Weak supervision

Session Type: Poster
Time: Wednesday, 9 June, 15:30 - 16:15
Location: Gather.Town
Virtual Session: View on Virtual Platform
Session Chair: Romain Serizel, Université de Lorraine, LORIA
 
 AUD-13.1: A GLOBAL-LOCAL ATTENTION FRAMEWORK FOR WEAKLY LABELLED AUDIO TAGGING
         Helin Wang; Peking University
         Yuexian Zou; Peking University
         Wenwu Wang; University of Surrey
 
 AUD-13.2: AN IMPROVED MEAN TEACHER BASED METHOD FOR LARGE SCALE WEAKLY LABELED SEMI-SUPERVISED SOUND EVENT DETECTION
         Xu Zheng; National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China
         Yan Song; National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China
         Ian McLoughlin; ICT Cluster, Singapore Institute of Technology
         Lin Liu; iFLYTEK Research, iFLYTEK CO., LTD.
         Li-Rong Dai; National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China
 
 AUD-13.3: COMPARISON OF DEEP CO-TRAINING AND MEAN-TEACHER APPROACHES FOR SEMI-SUPERVISED AUDIO TAGGING
         Léo Cances; Institut de Recherche en Informatique de Toulouse
         Thomas Pellegrini; Institut de Recherche en Informatique de Toulouse
 
 AUD-13.4: THE BENEFIT OF TEMPORALLY-STRONG LABELS IN AUDIO EVENT CLASSIFICATION
         Shawn Hershey; Google
         Daniel P. W. Ellis; Google
         Eduardo Fonseca; Google
         Aren Jansen; Google
         Caroline Liu; Google
         R Channing Moore; Google
         Manoj Plakal; Google
 
 AUD-13.5: UNSUPERVISED CONTRASTIVE LEARNING OF SOUND EVENT REPRESENTATIONS
         Eduardo Fonseca; Universitat Pompeu Fabra
         Diego Ortego; Dublin City University
         Kevin McGuinness; Dublin City University
         Noel E. O'Connor; Dublin City University
         Xavier Serra; Universitat Pompeu Fabra
 
 AUD-13.6: SOUND EVENT DETECTION BY CONSISTENCY TRAINING AND PSEUDO-LABELING WITH FEATURE-PYRAMID CONVOLUTIONAL RECURRENT NEURAL NETWORKS
         Chih-Yuan Koh; National Tsing Hua University
         You-Siang Chen; National Tsing Hua University
         Yi-Wen Liu; National Tsing Hua University
         Mingsian Bai; National Tsing Hua University