{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:57:36Z","timestamp":1780588656393,"version":"3.54.1"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1109\/ijcnn.2018.8489470","type":"proceedings-article","created":{"date-parts":[[2018,10,19]],"date-time":"2018-10-19T18:25:09Z","timestamp":1539973509000},"page":"1-7","source":"Crossref","is-referenced-by-count":18,"title":["End-to-End Polyphonic Sound Event Detection Using Convolutional Recurrent Neural Networks with Learned Time-Frequency Representation Input"],"prefix":"10.1109","author":[{"given":"Emre","family":"Cakir","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tuomas","family":"Virtanen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Learning the speech front-end with raw waveform CLDNNs","author":"sainath","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854950"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727635"},{"key":"ref15","article-title":"Sound event detection in real life audio using multimodel system","author":"hou","year":"2017","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727634"},{"key":"ref17","article-title":"librosa: 0.4.1","author":"mcfee","year":"2015"},{"key":"ref18","author":"o\u2019shaughnessy","year":"1987","journal-title":"Speech Communication Human and Machine"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63450-0_12"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472176"},{"key":"ref6","article-title":"DCASE 2017 challenge setup: Tasks, datasets and baseline system","author":"mesaros","year":"2017","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2017 Workshop (DCASE2017)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2778423"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690575"},{"key":"ref7","article-title":"Rare sound event detection using 1D convolutional recurrent neural networks","author":"lim","year":"2017","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63450-0_13"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2015.06.026"},{"key":"ref9","article-title":"Sound event detection in multichannel audio using spatial and harmonic features","author":"adavanne","year":"2016","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref20","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980 [cs LG]"},{"key":"ref22","article-title":"Dropout: A simple way to prevent neural networks from overfitting","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"ref21","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume":"abs 1502 3167","author":"ioffe","year":"2015","journal-title":"CoRR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref23","article-title":"Keras","author":"chollet","year":"2015","journal-title":"github com\/fchollet\/keras"}],"event":{"name":"2018 International Joint Conference on Neural Networks (IJCNN)","location":"Rio de Janeiro","start":{"date-parts":[[2018,7,8]]},"end":{"date-parts":[[2018,7,13]]}},"container-title":["2018 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8465565\/8488986\/08489470.pdf?arnumber=8489470","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T20:09:52Z","timestamp":1598213392000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8489470\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2018.8489470","relation":{},"subject":[],"published":{"date-parts":[[2018,7]]}}}