{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:18:12Z","timestamp":1753600692666,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053702","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"646-650","source":"Crossref","is-referenced-by-count":9,"title":["Scene-Dependent Acoustic Event Detection with Scene Conditioning and Fake-Scene-Conditioned Loss"],"prefix":"10.1109","author":[{"given":"Tatsuya","family":"Komatsu","sequence":"first","affiliation":[]},{"given":"Keisuke","family":"Imoto","sequence":"additional","affiliation":[]},{"given":"Masahito","family":"Togami","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"ADSC submission for DCASE 2017: Acoustic scene classification using deep residual convolutional neural networks","author":"zhao","year":"2017","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref11","article-title":"Multichannel acoustic scene classification by blind dereverberation, blind source separation, data augmentation, and model ensembling","author":"tanabe","year":"2018","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref12","article-title":"DCASE 2018 challenge surrey cross-task convolutional neural network baseline","author":"kong","year":"2018","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref13","first-page":"29","article-title":"Acoustic scene classification using multi-scale features","author":"liping","year":"2018","journal-title":"DCAS Workshop"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701861"},{"key":"ref15","first-page":"45","article-title":"Acoustic event detection method using semi-supervised non-negative matrix factorization with a mixture of local dictionaries","author":"komatsu","year":"2016","journal-title":"IEEE AASP DCASE Challenge"},{"key":"ref16","article-title":"Dcase 2016 sound event detection system based on convolutional neural network","author":"gorin","year":"2016","journal-title":"IEEE AASP DCASE Challenge"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2740002"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690575"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521669"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2005.1540194"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2009.5346483"},{"key":"ref5","first-page":"142","article-title":"Histogram of gradients of time–frequency representations for audio scene classification","volume":"23","author":"rakotomamonjy","year":"2014","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process (TASLP)"},{"key":"ref8","article-title":"An i-vector based approach for audio scene detection","author":"elizalde","year":"2013","journal-title":"IEEE AASP DCASE Challenge"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2016SLP0004"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"2609","DOI":"10.21437\/Interspeech.2013-601","article-title":"User activity estimation method based on probabilistic generative model of acoustic event sequence with user activity and its subordinate categories","author":"imoto","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2012.6343802"},{"key":"ref9","article-title":"Convolutional neural networks and x-vector embedding for dcase2018 acoustic scene classification challenge","author":"zeinali","year":"2018","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952260"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937196"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2169"},{"key":"ref23","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053702.pdf?arnumber=9053702","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T19:26:21Z","timestamp":1722713181000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053702\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053702","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}