{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:31:59Z","timestamp":1774539119656,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683627","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"46-50","source":"Crossref","is-referenced-by-count":11,"title":["Sound Event Detection with Sequentially Labelled Data Based on Connectionist Temporal Classification and Unsupervised Clustering"],"prefix":"10.1109","author":[{"given":"Yuanbo","family":"Hou","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, P. R. China"}]},{"given":"Qiuqiang","family":"Kong","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech and Signal Processing, University of Surrey, UK"}]},{"given":"Shengchen","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, P. R. China"}]},{"given":"Mark D.","family":"Plumbley","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech and Signal Processing, University of Surrey, UK"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc of ICML"},{"key":"ref11","first-page":"78","article-title":"Polyphonic audio tagging with sequentially labelled data using crnn with learnable gated linear units","author":"hou","year":"2018","journal-title":"DCASE 2018 workshop"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952704"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref14","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"Deep Learning and Representation Learning Workshop NIPS"},{"key":"ref15","first-page":"933","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"2017","journal-title":"Proceedings of ICML 2017"},{"key":"ref16","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"ICML"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.2307\/2346830"},{"key":"ref18","article-title":"Performance evaluation of some zero mean classification functions under unequal misclassification cost","author":"asamoah-boaheng","year":"2014","journal-title":"International Conference on Applied Science and Technology"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4020-8880-3"},{"key":"ref4","article-title":"DCASE 2017 challenge setup: Tasks, datasets and baseline system","author":"mesaros","year":"2017","journal-title":"Proc of the DCASE 2017 Workshop"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964310"},{"key":"ref5","article-title":"A report on sound event detection with different binaural features","author":"adavanne","year":"2017","journal-title":"Tech Rep DCASE 2017 Challenge"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952234"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461975"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref9","article-title":"Audio tagging with con-nectionist temporal classification model using sequentially labelled data","author":"hou","year":"2018","journal-title":"2018 International Conference on Communications Signal Processing and Systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2007.4425280"},{"key":"ref20","first-page":"4097","author":"benesty","year":"2009","journal-title":"Noise Reduction in Speech Processing"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"ref21","article-title":"General-purpose tagging of freesound audio with audioset labels: Task description, dataset, and baseline","author":"eduardo","year":"2018","journal-title":"DCASE 2018 workshop"},{"key":"ref24","article-title":"A multi-device dataset for urban acoustic scene classification","author":"mesaros","year":"2018","journal-title":"DCASE 2018 workshop"},{"key":"ref23","article-title":"DCASE 2016 acoustic scene classification using convolutional neural networks","author":"valenti","year":"2016","journal-title":"Workshop on DCASE 2016"},{"key":"ref26","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proceedings of ICL"},{"key":"ref25","article-title":"Sound event detection and time-frequency segmentation from weakly labelled data","author":"kong","year":"2018","journal-title":"IEEE\/ACM Transection on Audio Speech and Language Processing (Early Access)"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, UK","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683627.pdf?arnumber=8683627","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T18:29:28Z","timestamp":1755714568000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683627\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683627","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}