{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:17:56Z","timestamp":1776885476669,"version":"3.51.2"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61901265"],"award-info":[{"award-number":["61901265"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Pujiang Program","award":["19PJ1406300"],"award-info":[{"award-number":["19PJ1406300"]}]},{"DOI":"10.13039\/501100004921","name":"Shanghai Jiao Tong University","doi-asserted-by":"publisher","award":["19X100040009"],"award-info":[{"award-number":["19X100040009"]}],"id":[{"id":"10.13039\/501100004921","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3054313","type":"journal-article","created":{"date-parts":[[2021,1,25]],"date-time":"2021-01-25T22:51:23Z","timestamp":1611615083000},"page":"887-900","source":"Crossref","is-referenced-by-count":41,"title":["Towards Duration Robust Weakly Supervised Sound Event Detection"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4330-8980","authenticated-orcid":false,"given":"Heinrich","family":"Dinkel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengyue","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7102-9826","authenticated-orcid":false,"given":"Kai","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052995"},{"key":"ref38","article-title":"Ustc-nelslip system for dcase 2018 challenge task 4,” DCASE2018 challenge","author":"liu","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553198"},{"key":"ref36","article-title":"Surrey-CVSSP system for DCASE2017 challenge task4,” DCASE2017 challenge","author":"xu","year":"2017"},{"key":"ref35","first-page":"12","article-title":"Sound event detection using weakly labeled dataset with stacked convolutional and recurrent neural network","author":"adavanne","year":"0","journal-title":"Proc Detection Classification Acoust Scenes Events Workshop"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682858"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682772"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682847"},{"key":"ref12","first-page":"316","article-title":"A comparison of pooling methods on LSTM models for rare acoustic event classification","author":"kao","year":"0","journal-title":"Proc ICASSP IEEE Int Conf Acoust Speech Signal"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2895254"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852143"},{"key":"ref16","article-title":"Large-margin softmax loss for convolutional neural networks","volume":"2","author":"liu","year":"2016","journal-title":"” ICML"},{"key":"ref17","article-title":"Mean teacher convolution system for dcase 2018 task 4,” DCASE2018 challenge","author":"jiakai","year":"2018"},{"key":"ref18","first-page":"74","article-title":"Ensemble of convolutional neural networks for weakly-supervised sound event detection using multiple scale input","author":"lee","year":"0","journal-title":"Proc Detection Classification Acoust Scenes Events Workshop"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(96)00034-3"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170052"},{"key":"ref4","first-page":"3665","article-title":"Voice activity detection in the wild via weakly supervised sound event detection","author":"chen","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref27","first-page":"145","article-title":"On the stratification of multi-label data,” Mach. Learn. Know. Discov. Databases","author":"sechidis","year":"2011"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63450-0_12"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2989575"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053459"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2858559"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63450-0_13"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2930913"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63450-0_10"},{"key":"ref20","first-page":"3365","article-title":"Neural models for sequence chunking","author":"zhai","year":"0","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref22","article-title":"librosa\/librosa in place of -: 0.7.2","author":"mcfee","year":"2020"},{"key":"ref21","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume":"32","author":"paszke","year":"2019"},{"key":"ref24","first-page":"1","article-title":"End-to-end polyphonic sound event detection using convolutional recurrent neural networks with learned time-frequency representation input","author":"\u00e7akir","year":"0","journal-title":"Proc Int Joint Conf Neural Netw (IJCNN)"},{"key":"ref23","first-page":"42","article-title":"Gnu parallel: - The command-line power tool","volume":"36","author":"tange","year":"2011","journal-title":"USENIX Mag"},{"key":"ref26","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref25","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"0","journal-title":"Proc 7th Int Conf Learn Representations"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09335265.pdf?arnumber=9335265","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:01Z","timestamp":1652194441000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9335265\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3054313","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}