{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:34:09Z","timestamp":1763202849926},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10445834","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1096-1100","source":"Crossref","is-referenced-by-count":9,"title":["Performance and Energy Balance: A Comprehensive Study of State-of-the-Art Sound Event Detection Systems"],"prefix":"10.1109","author":[{"given":"Francesca","family":"Ronchini","sequence":"first","affiliation":[{"name":"Politecnico di Milano,Dipartimento di Elettronica, Informazione e Bioingegneria,Milan,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Romain","family":"Serizel","sequence":"additional","affiliation":[{"name":"Université de Lorraine,CNRS, Inria, Loria,Nancy,France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3256088"},{"article-title":"Semi-supervsied learningbased sound event detection using freuqency dynamic convolution with large kernel attention for dcase challenge 2023 task 4","year":"2023","author":"Kim","key":"ref3"},{"article-title":"Musiclm: Generating music from text","year":"2023","author":"Agostinelli","key":"ref4"},{"article-title":"Rave: A variational autoencoder for fast and high-quality neural audio synthesis","year":"2021","author":"Caillon","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9891914"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21428\/bf6fb269.1f033948"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00076"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3381831"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096975"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.sustainlp-1.2"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095938"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2394"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-456"},{"article-title":"Carbontracker: Tracking and predicting the carbon footprint of training deep learning models","year":"2020","author":"Anthony","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"ref17","article-title":"Codecarbon: estimate and track carbon emissions from machine learning computing","author":"Schmidt","year":"2021","journal-title":"Cited on"},{"key":"ref18","article-title":"Thop: Pytorch-opcounter","author":"Zhu","year":"2019","journal-title":"Lyken17\/pytorchOpCounter"},{"article-title":"Training sound event detection on a heterogeneous dataset","year":"2020","author":"Turpault","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747577"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.33682\/006b-jx26"},{"article-title":"Sound event detection from partially annotated data: Trends and challenges","volume-title":"IcE-TRAN conference","author":"Serizel","key":"ref22"},{"article-title":"Post-processing independent evaluation of sound event detection systems","year":"2023","author":"Ebbers","key":"ref23"},{"article-title":"Description and analysis of novelties introduced in dcase task 4 2022 on the baseline system","year":"2022","author":"Ronchini","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052995"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414579"},{"article-title":"Beats: Audio pre-training with acoustic tokenizers","year":"2022","author":"Chen","key":"ref27"},{"key":"ref28","article-title":"Sound event detection system using pre-trained model for dcase 2023 task 4","volume-title":"Tech. Rep., DCASE2023 Challenge","author":"Chen","year":"2023"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10445834.pdf?arnumber=10445834","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:37:22Z","timestamp":1722573442000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10445834\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10445834","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}