{"date_created":"2024-11-18T09:29:16Z","publication":"32nd European Signal Processing Conference (EUSIPCO 2024)","ddc":["000"],"department":[{"_id":"54"}],"project":[{"name":"WestAI - AI Service Center West","_id":"512"}],"citation":{"ama":"Werning A, Haeb-Umbach R. Target-Specific Dataset Pruning for Compression of Audio Tagging Models. In: <i>32nd European Signal Processing Conference (EUSIPCO 2024)</i>. ; 2024.","ieee":"A. Werning and R. Haeb-Umbach, “Target-Specific Dataset Pruning for Compression of Audio Tagging Models,” presented at the 32nd European Signal Processing Conference, Lyon, 2024.","apa":"Werning, A., &#38; Haeb-Umbach, R. (2024). Target-Specific Dataset Pruning for Compression of Audio Tagging Models. <i>32nd European Signal Processing Conference (EUSIPCO 2024)</i>. 32nd European Signal Processing Conference, Lyon.","short":"A. Werning, R. Haeb-Umbach, in: 32nd European Signal Processing Conference (EUSIPCO 2024), 2024.","mla":"Werning, Alexander, and Reinhold Haeb-Umbach. “Target-Specific Dataset Pruning for Compression of Audio Tagging Models.” <i>32nd European Signal Processing Conference (EUSIPCO 2024)</i>, 2024.","bibtex":"@inproceedings{Werning_Haeb-Umbach_2024, title={Target-Specific Dataset Pruning for Compression of Audio Tagging Models}, booktitle={32nd European Signal Processing Conference (EUSIPCO 2024)}, author={Werning, Alexander and Haeb-Umbach, Reinhold}, year={2024} }","chicago":"Werning, Alexander, and Reinhold Haeb-Umbach. “Target-Specific Dataset Pruning for Compression of Audio Tagging Models.” In <i>32nd European Signal Processing Conference (EUSIPCO 2024)</i>, 2024."},"author":[{"full_name":"Werning, Alexander","first_name":"Alexander","id":"62152","last_name":"Werning"},{"full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold","id":"242"}],"has_accepted_license":"1","language":[{"iso":"eng"}],"date_updated":"2024-11-18T12:15:50Z","year":"2024","type":"conference","file":[{"relation":"main_file","content_type":"application/pdf","file_size":183539,"creator":"awerning","success":1,"date_created":"2024-11-18T12:10:09Z","file_name":"Eusipco__Target_specific_Dataset_Pruning_for_Compression_of_Audio_Tagging_Models.pdf","access_level":"closed","file_id":"57200","date_updated":"2024-11-18T12:10:09Z"}],"keyword":["data pruning","knowledge distillation","audio tagging"],"conference":{"name":"32nd European Signal Processing Conference","location":"Lyon"},"user_id":"62152","file_date_updated":"2024-11-18T12:10:09Z","title":"Target-Specific Dataset Pruning for Compression of Audio Tagging Models","status":"public","abstract":[{"lang":"eng","text":"Large audio tagging models are usually trained or pre-trained on AudioSet, a dataset that encompasses a large amount of different sound classes and acoustic environments. Knowledge distillation has emerged as a method to compress such models without compromising their effectiveness. There are many different applications for audio tagging, some of which require a specialization to a narrow domain of sounds to be classified. For these scenarios, it is beneficial to distill the large audio tagger with respect to a specific subset of sounds of interest. A method to prune a general dataset with respect to a target dataset is presented. By distilling with such a specialized pruned dataset, we obtain a compressed model with better classification accuracy in the specific target domain than with target-agnostic distillation."}],"_id":"57160"}