{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T23:20:49Z","timestamp":1778628049075,"version":"3.51.4"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1736210"],"award-info":[{"award-number":["U1736210"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61471145"],"award-info":[{"award-number":["61471145"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/taslp.2020.2966868","type":"journal-article","created":{"date-parts":[[2020,1,15]],"date-time":"2020-01-15T21:42:12Z","timestamp":1579124532000},"page":"770-784","source":"Crossref","is-referenced-by-count":17,"title":["Pyramidal Temporal Pooling With Discriminative Mapping for Audio Classification"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8457-2943","authenticated-orcid":false,"given":"Liwen","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3105-6213","authenticated-orcid":false,"given":"Ziqiang","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4297-4300","authenticated-orcid":false,"given":"Jiqing","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"A multi-device dataset for urban acoustic scene classification","author":"mesaros","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521242"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2389618"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2671188.2749396"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288864"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1243"},{"key":"ref37","article-title":"Efficient convolutional neural network for audio event detection","author":"meyer","year":"0"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751969"},{"key":"ref35","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Computational and Biological Learning Society"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966035"},{"key":"ref60","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-2836-1","article-title":"Nonconvex optimization and its applications","author":"bard","year":"1998","journal-title":"Practical Bilevel Optimization"},{"key":"ref62","first-page":"39","article-title":"Continuous hyper-parameter learning for support vector machines","author":"klatzer","year":"2015","journal-title":"Proc Comput Vision Winter Workshop"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-18461-6_52"},{"key":"ref63","first-page":"377","article-title":"Efficient multiple hyperparameter learning for log-linear models","author":"foo","year":"2007","journal-title":"Proc 21st Annu Conf Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1661377"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2118753"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-8853-9_3"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206774"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1121\/1.4790351"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502245"},{"key":"ref68","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref69","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Comput Sci"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2002.806626"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/79.888862"},{"key":"ref20","first-page":"2105","article-title":"Bag-of-audio-words approach for multimedia event classification","author":"pancoast","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2375575"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2778423"},{"key":"ref24","first-page":"1","article-title":"Improved audio features for largescale multimedia event detection","author":"metze","year":"2014","journal-title":"Proc IEEE Int Conf Multimedia Expo"},{"key":"ref23","first-page":"3325","article-title":"Robust sound event classification using LBP-HOG based bag-of-audio-words feature representation","author":"lim","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref26","article-title":"Non-negative matrix factorization applied to auditory scenes classification","author":"cauchi","year":"2011"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854807"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.153"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-007-0176-2"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.171"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248018"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSP.2017.8096153"},{"key":"ref54","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0"},{"key":"ref53","article-title":"Improving neural networks by preventing co-adaptation of feature detectors","author":"hinton","year":"0"},{"key":"ref52","article-title":"Multi-layered temporal pooling based on CNN for acoustic scene classification","author":"zhang","year":"2018"},{"key":"ref10","first-page":"1216","article-title":"Scream and gunshot detection in noisy environments","author":"gerosa","year":"2007","journal-title":"Proc 15th Eur Signal Process Conf"},{"key":"ref11","first-page":"2279","article-title":"Detecting semantic concepts in consumer videos using audio","author":"liang","year":"2015","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref40","article-title":"Acoustic scene classification by ensemble of spectrograms based on adaptive temporal divisions","author":"sakashita","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2012.2226575"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298789"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.854103"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68585-2_32"},{"key":"ref18","first-page":"505","article-title":"Classification of meeting-room acoustic events with support vector machines and confusion-based clustering","author":"temko","year":"2005","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1121\/1.2750160"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICGTSPICC.2016.7955371"},{"key":"ref3","first-page":"606","article-title":"Audio concept classification with hierarchical deep neural networks","author":"ravanelli","year":"2014","journal-title":"Proc 22nd Eur Signal Process Conf"},{"key":"ref6","article-title":"Computational auditory scene analysis and automatic speech recognition","author":"arun","year":"2012","journal-title":"Techniques for Noise Robustness in Automatic Speech Recognition"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2008.03.004"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521503"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/EEEI.2012.6376996"},{"key":"ref49","first-page":"155","article-title":"Support vector regression machines","volume":"9","author":"drucker","year":"1997","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1121\/1.4734555"},{"key":"ref46","article-title":"Self-attention mechanism based system for Dcase2018 challenge task1 and task4","author":"wang","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461975"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299176"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2558148"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952259"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"ref44","article-title":"DCASE 2018 task 1a: Acoustic scene classification by BI-LSTM-CNN-net multichannel fusion","author":"hao","year":"2018"},{"key":"ref43","article-title":"Unsupervised feature learning for audio analysis","author":"meyer","year":"0"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/08960462.pdf?arnumber=8960462","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:30:50Z","timestamp":1651080650000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8960462\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.2966868","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}