{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T12:03:01Z","timestamp":1774872181634,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1109\/icassp.2016.7472176","type":"proceedings-article","created":{"date-parts":[[2016,6,24]],"date-time":"2016-06-24T01:58:30Z","timestamp":1466733510000},"page":"2742-2746","source":"Crossref","is-referenced-by-count":51,"title":["Audio-based multimedia event detection using deep recurrent neural networks"],"prefix":"10.1109","author":[{"given":"Yun","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leonardo","family":"Neves","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian","family":"Metze","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Noisemes: manual annotation of environmental noise in audio streams","author":"burger","year":"2012","journal-title":"technical report CMU-LTI-12–07 Carnegie Mellon University"},{"key":"ref11","first-page":"1482","article-title":"Audio event classification using deep neural networks","author":"kons","year":"2013","journal-title":"Proc of Interspeech"},{"key":"ref12","first-page":"506","article-title":"Recognition of acoustic events using deep neural networks","author":"gencoglu","year":"2014","journal-title":"Proc of the 22nd European Signal Processing Conference"},{"key":"ref13","article-title":"Poly-phonic sound event detection using multi-label deep neural networks","author":"cakir","year":"2015","journal-title":"IEEE International Joint Conference on Neural Networks"},{"key":"ref14","first-page":"606","article-title":"Audio concept classification with hierarchical deep neural networks","author":"ravanelli","year":"2014","journal-title":"Proc of the 22nd European Signal Processing Conference"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1145\/2671188.2749396","article-title":"Audio-based multimedia event detection with DNNs and sparse sampling","author":"ashraf","year":"2015","journal-title":"Proc ACM International Conference on Multimedia Retrieval"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(88)90007-X"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref19","article-title":"Gradient flow in recurrent nets: the difficulty of learning longterm dependencies","author":"hochreiter","year":"2001","journal-title":"A Field Guide to Dynamical Recurrent Neural Networks"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"2089","DOI":"10.21437\/Interspeech.2012-557","article-title":"Compact audio representation for event detection in consumer media","author":"zhuang","year":"2012","journal-title":"Proc of Interspeech"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2413294"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"2105","DOI":"10.21437\/Interspeech.2012-561","article-title":"Bag-of-audio-words approach for multimedia event classification","author":"pancoast","year":"2012","journal-title":"Proc of Interspeech"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2013.27"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"2081","DOI":"10.21437\/Interspeech.2012-555","article-title":"Consumer-level multimedia event detection through unsupervised audio signal modeling","author":"byun","year":"2012","journal-title":"Proc of Interspeech"},{"key":"ref7","first-page":"2929","article-title":"Robust audio-codebooks for large-scale event detection in consumer videos","author":"rawat","year":"2013","journal-title":"Proc of Interspeech"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"2085","DOI":"10.21437\/Interspeech.2012-556","article-title":"Event-based video retrieval using audio","author":"jin","year":"2012","journal-title":"Proc of Interspeech"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"2265","DOI":"10.21437\/Interspeech.2011-602","article-title":"Unsupervised learning of acoustic unit descriptors for audio content representation and classification","author":"chaudhuri","year":"2011","journal-title":"Proc of Interspeech"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2006.870086"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502224"},{"key":"ref21","first-page":"1","article-title":"Theano: a CPU and GPU math expression compiler","author":"bergstra","year":"2010","journal-title":"Proceedings of the Python for Scientific Computing Conference"},{"key":"ref24","first-page":"372","article-title":"A method of solving a convex programming problem with convergence rate O(l\/sqr(k))","volume":"27","author":"nesterov","year":"1983","journal-title":"Soviet Mathematics Doklady"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853819"},{"key":"ref26","article-title":"2011 TRECVID multimedia event detection evaluation plan","year":"0"},{"key":"ref25","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"}],"event":{"name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Shanghai","start":{"date-parts":[[2016,3,20]]},"end":{"date-parts":[[2016,3,25]]}},"container-title":["2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7465907\/7471614\/07472176.pdf?arnumber=7472176","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T21:26:12Z","timestamp":1718659572000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7472176\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp.2016.7472176","relation":{},"subject":[],"published":{"date-parts":[[2016,3]]}}}