{"date_updated":"2023-11-22T08:36:18Z","file":[{"success":1,"file_id":"49114","content_type":"application/pdf","access_level":"closed","date_created":"2023-11-22T08:35:23Z","date_updated":"2023-11-22T08:35:23Z","file_name":"dcase2022_tech_report_ebbers.pdf","relation":"main_file","file_size":491650,"creator":"ebbers"}],"language":[{"iso":"eng"}],"abstract":[{"text":"In this report we present our system for the Detection and Classification of Acoustic Scenes and Events (DCASE) 2022 Challenge Task 4: Sound Event Detection in Domestic Environments 1 . As in previous editions of the Challenge, we use forward-backward convolutional recurrent neural networks (FBCRNNs) [1, 2] for weakly labeled and semi-supervised sound event detection (SED) and eventually generate strong pseudo labels for weakly labeled and unlabeled data. Then, (tag-conditioned) bidirectional CRNNs (Bi-CRNNs) [1, 2] are trained in a strongly supervised manner as our final SED models. In each of the training stages we use multiple iterations of self-training. Compared to previous editions, we improved our system performance by 1) some tweaks regarding data augmentation, pseudo labeling and inference 2) using weakly labeled AudioSet data [3] for pretraining larger networks and 3) augmenting the DESED data [4] with strongly labeled AudioSet data [5] for finetuning of the networks. Source code is publicly available at https://github.com/fgnt/pb_sed.","lang":"eng"}],"title":"Pre-Training And Self-Training For Sound Event Detection In Domestic Environments","user_id":"34851","author":[{"first_name":"Janek","full_name":"Ebbers, Janek","last_name":"Ebbers"},{"full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"year":"2022","status":"public","file_date_updated":"2023-11-22T08:35:23Z","_id":"49113","date_created":"2023-11-22T08:34:23Z","department":[{"_id":"54"}],"has_accepted_license":"1","ddc":["000"],"project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"citation":{"ieee":"J. Ebbers and R. Haeb-Umbach, <i>Pre-Training And Self-Training For Sound Event Detection In Domestic Environments</i>. 2022.","bibtex":"@book{Ebbers_Haeb-Umbach_2022, title={Pre-Training And Self-Training For Sound Event Detection In Domestic Environments}, author={Ebbers, Janek and Haeb-Umbach, Reinhold}, year={2022} }","ama":"Ebbers J, Haeb-Umbach R. <i>Pre-Training And Self-Training For Sound Event Detection In Domestic Environments</i>.; 2022.","short":"J. Ebbers, R. Haeb-Umbach, Pre-Training And Self-Training For Sound Event Detection In Domestic Environments, 2022.","apa":"Ebbers, J., &#38; Haeb-Umbach, R. (2022). <i>Pre-Training And Self-Training For Sound Event Detection In Domestic Environments</i>.","chicago":"Ebbers, Janek, and Reinhold Haeb-Umbach. <i>Pre-Training And Self-Training For Sound Event Detection In Domestic Environments</i>, 2022.","mla":"Ebbers, Janek, and Reinhold Haeb-Umbach. <i>Pre-Training And Self-Training For Sound Event Detection In Domestic Environments</i>. 2022."},"type":"report"}