{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:18:56Z","timestamp":1792786736694,"version":"4.5.0"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2017,6,1]],"date-time":"2017-06-01T00:00:00Z","timestamp":1496275200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"name":"European Unions H2020 Framework Programme"},{"DOI":"10.13039\/501100000781","name":"ERC","doi-asserted-by":"publisher","award":["637422"],"award-info":[{"award-number":["637422"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"name":"EVERYSOUND"},{"name":"Google's Faculty Research"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2017,6]]},"DOI":"10.1109\/taslp.2017.2690575","type":"journal-article","created":{"date-parts":[[2017,5,23]],"date-time":"2017-05-23T17:03:22Z","timestamp":1495559002000},"page":"1291-1303","source":"Crossref","is-referenced-by-count":487,"title":["Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection"],"prefix":"10.1109","volume":"25","author":[{"given":"Emre","family":"Cakir","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giambattista","family":"Parascandolo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Toni","family":"Heittola","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heikki","family":"Huttunen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tuomas","family":"Virtanen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2015.7336899"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2533858"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952585"},{"key":"ref37","first-page":"1272","article-title":"Audio context recognition using audio event histograms","author":"heittola","year":"0","journal-title":"Proc 18th Eur Signal Process Conf"},{"key":"ref36","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proceedings of the 32nd Intl Conf on Machine Learning"},{"key":"ref35","first-page":"1019","article-title":"A theoretically grounded application of dropout in recurrent neural networks","author":"gal","year":"0","journal-title":"Adv Neural Inform Process Syst"},{"key":"ref34","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"hinton","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref28","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"0","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref29","first-page":"1","article-title":"Learning the speech front-end with raw waveform CLDNNs","author":"sainath","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5626\/JCSE.2012.6.1.40"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2015.06.026"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2013-1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701861"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639360"},{"key":"ref50","article-title":"Theano: A python framework for fast computation of mathematical expressions","author":"team","year":"2016"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref57","first-page":"3320","author":"yosinski","year":"0","journal-title":"Adv Neural Inform Process Syst"},{"key":"ref56","first-page":"17","article-title":"Deep learning of representations for unsupervised and transfer learning","volume":"27","author":"bengio","year":"2012","journal-title":"ICML Unsupervised and Transfer Learning"},{"key":"ref55","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"simonyan","year":"0","journal-title":"Proc Workshop Int Conf Learn Represent"},{"key":"ref54","article-title":"Discriminative training of GMM parameters for audio scene classification","author":"yun","year":"2016"},{"key":"ref53","article-title":"Domestic audio tagging with convolutional neural networks","author":"cakir","year":"2016"},{"key":"ref52","article-title":"CQT-based convolutional neural networks for audio scene classification and domestic audio tagging","author":"lidy","year":"2016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2015.7324337"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"ref40","article-title":"DCASE2016 challenge—Audio tagging","author":"heittola","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.857575"},{"key":"ref13","first-page":"1267","article-title":"Acoustic event detection in real life recordings","author":"mesaros","year":"0","journal-title":"Proc Eur Signal Process Conf"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177950"},{"key":"ref15","first-page":"1","article-title":"Polyphonic sound event detection using multilabel deep neural networks","author":"cakir","year":"0","journal-title":"Proc Int Joint Conf Neural Netw"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727634"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472176"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362478"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.32657\/10356\/59272","article-title":"Sound event recognition in unstructured environments using spectrogram image processing","author":"dennis","year":"2014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2015.7336885"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178031"},{"key":"ref7","first-page":"506","article-title":"Recognition of acoustic events using deep neural networks","author":"gencoglu","year":"0","journal-title":"Proc Eur Signal Process Conf"},{"key":"ref49","article-title":"Keras","author":"chollet","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-123"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref45","first-page":"1319","article-title":"Maxout networks.","volume":"28","author":"goodfellow","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref48","article-title":"librosa: Audio and music signal analysis in Python","author":"mcfee","year":"0","journal-title":"Proc 14th Python Sci Conf"},{"key":"ref47","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Workshop Int Conf Learn Represent"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/1882471.1882479"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref44","article-title":"DCASE2016 baseline system","author":"heittola","year":"2016"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/973264.973282"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7933016\/07933050.pdf?arnumber=7933050","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:15:00Z","timestamp":1641986100000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7933050\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6]]},"references-count":57,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2017.2690575","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,6]]}}}