{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:10:43Z","timestamp":1779379843700,"version":"3.53.1"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2017,11,1]],"date-time":"2017-11-01T00:00:00Z","timestamp":1509494400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2017,11]]},"DOI":"10.1109\/taslp.2017.2740002","type":"journal-article","created":{"date-parts":[[2017,8,14]],"date-time":"2017-08-14T18:10:53Z","timestamp":1502734253000},"page":"2059-2070","source":"Crossref","is-referenced-by-count":82,"title":["Duration-Controlled LSTM for Polyphonic Sound Event Detection"],"prefix":"10.1109","volume":"25","author":[{"given":"Tomoki","family":"Hayashi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takaaki","family":"Hori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Le Roux","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazuya","family":"Takeda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"HTK speech recognition toolkit","year":"2006"},{"key":"ref38","first-page":"825","article-title":"A hidden semi-Markov model-based speech synthesis system","volume":"90","author":"heiga","year":"2007","journal-title":"IEICE Trans Inf Syst"},{"key":"ref33","first-page":"4441","article-title":"A voice activity detection based on the adaptive integration of multiple speech features and a signal decision scheme","author":"fujimoto","year":"2008","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2003.10.002"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/97.736233"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2009.11.011"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015015"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref10","article-title":"TREC Video Retrieval Evaluation: TRECVID","year":"2011"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"ref11","article-title":"Detection and Classification of Acoustic Scenes and Events 2013—DCASE 2013","year":"2013"},{"key":"ref12","article-title":"Detection and Classification of Acoustic Scenes and Events 2016—DCASE 2016","year":"2016"},{"key":"ref13","article-title":"Acoustic event detection using signal enhancement and spectro-temporal feature extraction","author":"schr\u00f6der","year":"2013","journal-title":"Proc IEEE Workshop Appl Signal Process Audio Acoust"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2013-1"},{"key":"ref15","first-page":"36","article-title":"Sound event detection in multisource environments using source separation","author":"heittola","year":"2011","journal-title":"Proc CHiME Workshop on Mach Listen Multisource Environ"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.camwa.2012.03.077"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-30232-9_14"},{"key":"ref18","first-page":"45","article-title":"Acoustic event detection method using semi-supervised non-negative matrix factorization with mixtures of local dictionaries","author":"komatsu","year":"2016","journal-title":"Proc Workshop Detection Classif Acoust Scenes Events"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280624"},{"key":"ref28","first-page":"338","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521503"},{"key":"ref27","first-page":"338","article-title":"Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition","author":"sak","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref3","first-page":"1218","article-title":"Healthcare audio event classification using hidden Markov models and hierarchical hidden Markov models","author":"peng","year":"2009","journal-title":"Proc IEEE Int Conf Multimedia Expo"},{"key":"ref6","first-page":"1272","article-title":"Audio context recognition using audio event histograms","author":"heittola","year":"2010","journal-title":"Proc Eur Signal Process Conf"},{"key":"ref29","first-page":"3274","article-title":"Integration of speech enhancement and recognition using long-short term memory recurrent neural network","author":"chen","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362796"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1098\/rsos.150690"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/35.995862"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2012.6343802"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-540-68585-2_1","article-title":"The CLEAR 2007 evaluation","author":"stiefelhagen","year":"2008","journal-title":"Multimodal Technologies for Perception of Humans"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1352012.1352015"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"ref48","doi-asserted-by":"crossref","first-page":"2345","DOI":"10.21437\/Interspeech.2013-548","article-title":"Sequence-discriminative training of deep neural networks","author":"vesel\u00fd","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472176"},{"key":"ref47","article-title":"TensorFlow—An open source software library for machine intelligence","year":"2015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-015-0069-2"},{"key":"ref42","article-title":"Improving neural networks by preventing co-adaptation of feature detectors","author":"hinton","year":"2012"},{"key":"ref24","first-page":"16","article-title":"DNN-based sound event detection with exemplar-based approach for noise reduction","author":"choi","year":"2016","journal-title":"Proc Workshop Detection Classif Acoust Scenes Events"},{"key":"ref41","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref23","first-page":"589","article-title":"Universal onset detection with bidirectional long short-term memory neural networks","author":"eyben","year":"2010","journal-title":"Proc Int Conf Music Inf Retr"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639012"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_5"},{"key":"ref25","first-page":"6","article-title":"Sound event detection in multichannel audio using spatial and harmonic features","author":"adavanne","year":"2016","journal-title":"Proc Workshop Detection Classif Acoust Scenes Events"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8047434\/08010445.pdf?arnumber=8010445","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,26]],"date-time":"2024-06-26T08:07:07Z","timestamp":1719389227000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8010445\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11]]},"references-count":48,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2017.2740002","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,11]]}}}