{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T12:32:18Z","timestamp":1745843538959,"version":"3.28.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414254","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"865-869","source":"Crossref","is-referenced-by-count":4,"title":["A New DCASE 2017 Rare Sound Event Detection Benchmark Under Equal Training Data: CRNN With Multi-Width Kernels"],"prefix":"10.1109","author":[{"given":"Jan","family":"Baumann","sequence":"first","affiliation":[{"name":"Technische Universität Braunschweig,Institute for Communications Technology,Braunschweig,Germany,38106"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick","family":"Meyer","sequence":"additional","affiliation":[{"name":"Technische Universität Braunschweig,Institute for Communications Technology,Braunschweig,Germany,38106"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Timo","family":"Lohrenz","sequence":"additional","affiliation":[{"name":"Technische Universität Braunschweig,Institute for Communications Technology,Braunschweig,Germany,38106"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Roy","sequence":"additional","affiliation":[{"name":"IAV GmbH,Gifhorn,Germany,38518"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Papendieck","sequence":"additional","affiliation":[{"name":"IAV GmbH,Gifhorn,Germany,38518"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tim","family":"Fingscheidt","sequence":"additional","affiliation":[{"name":"Technische Universität Braunschweig,Institute for Communications Technology,Braunschweig,Germany,38106"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937143"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952655"},{"key":"ref31","first-page":"1745","article-title":"Sound Event Detection Using Multiple Op-timized Kernels","volume":"28","author":"xia","year":"2020","journal-title":"IEEE\/ACM Trans on ASLP"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052950"},{"key":"ref37","first-page":"1929","article-title":"Dropout: A Simple Way to Prevent Neural Networks from Overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"article-title":"Adam: A Method for Stochastic Optimization","year":"2014","author":"kingma","key":"ref36"},{"key":"ref35","first-page":"265","article-title":"Tensorflow: A System for Large-Scale Machine Learning","author":"abadi","year":"2016","journal-title":"Proc of OSDI"},{"article-title":"Keras","year":"2015","author":"chollet","key":"ref34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2389618"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280624"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690575"},{"key":"ref15","first-page":"80","article-title":"Rare Sound Event Detection Using 1D Convolutional Recurrent Neural Networks","author":"lim","year":"2017","journal-title":"Proc of DCASE2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ITAIC.2019.8785647"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003946"},{"article-title":"Characterizing Types of Convolution in Deep Convolutional Recurrent Neural Networks for Robust Speech Emotion Recognition","year":"2018","author":"huang","key":"ref19"},{"key":"ref28","article-title":"A Report on Sound Event Detection with Different Binaural Features","author":"adavanne","year":"2017","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref4","first-page":"1","article-title":"Towards Acoustic Event Detection for Surveillance in Cars","author":"transfeld","year":"2014","journal-title":"Proc of 11th ITG Conference on Speech Communication"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref3","article-title":"Convolutional Recurrent Neural Networks for Rare Sound Event Detection","author":"cakir","year":"2017","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178447"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.33682\/9f2t-ab23"},{"key":"ref5","first-page":"36","article-title":"Sound Event Detection in Multisource Environments Using Source Separation","author":"heittola","year":"2011","journal-title":"Proc of CHiME"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.23919\/FRUCT.2019.8711906"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICOT.2017.8336092"},{"key":"ref2","first-page":"85","article-title":"DCASE 2017 Challenge Setup: Tasks, Datasets and Baseline System","author":"mesaros","year":"2017","journal-title":"Proc of DCASE2017"},{"key":"ref9","first-page":"506","article-title":"Recognition of Acoustic Events Using Deep Neural Networks","author":"gencoglu","year":"2014","journal-title":"Proc of eusipco"},{"key":"ref1","first-page":"2927","article-title":"An Acoustic Event Detection Framework and Evaluation Metric for Surveillance in Cars","author":"transfeld","year":"2015","journal-title":"Proc of Interspeech"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2860246"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2858559"},{"key":"ref21","first-page":"1","article-title":"A New Benchmark CNN for Log-Mel Spectrogram Speech Emotion Recognition","author":"meyer","year":"2021","journal-title":"Proc of SLT"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690563"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952234"},{"article-title":"Freesound","year":"2005","author":"jong","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2907016"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414254.pdf?arnumber=9414254","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:19:39Z","timestamp":1659485979000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414254\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414254","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}