{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T23:13:46Z","timestamp":1770419626119,"version":"3.49.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414406","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"621-625","source":"Crossref","is-referenced-by-count":15,"title":["DCASENET: An Integrated Pretrained Deep Neural Network for Detecting and Classifying Acoustic Scenes and Events"],"prefix":"10.1109","author":[{"given":"Jee-weon","family":"Jung","sequence":"first","affiliation":[{"name":"University of Seoul,School of Computer Science"}]},{"given":"Hye-jin","family":"Shim","sequence":"additional","affiliation":[{"name":"University of Seoul,School of Computer Science"}]},{"given":"Ju-ho","family":"Kim","sequence":"additional","affiliation":[{"name":"University of Seoul,School of Computer Science"}]},{"given":"Ha-Jin","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Seoul,School of Computer Science"}]}],"member":"263","reference":[{"key":"ref32","article-title":"MixUp: Beyond empirical risk minimization","author":"zhang","year":"2018","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref31","article-title":"DCASE 2020 Task 3: Ensemble of Sequence Matching Networks for Dynamic Sound Event Localization, Detection, and Tracking","author":"nguyen","year":"2020","journal-title":"Tech Rep DCASE2020 Challenge"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-0992"},{"key":"ref11","article-title":"Audio Tag Representation Guided Dual Attention Network for Acoustic Scene Classification","author":"kim","year":"2020","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events Workshop (DCASE)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1037\/cjep2007006"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053912"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937196"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref16","article-title":"Aaai2020 invited speaker program","author":"bengio","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.33682\/0avf-bm61"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2326181"},{"key":"ref27","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume":"1","author":"ioffe","year":"2015","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref3","article-title":"Integrating the Data Augmentation Scheme with Various Classifiers for Acoustic Scene Modeling","author":"chen","year":"2019","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref6","article-title":"DNN-based audio scene classification for DCASE 2017: dual input features, balancing cost, and stochastic data duplication","author":"jung","year":"2017","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events Workshop (DCASE)"},{"key":"ref29","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 Re-search"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472918"},{"key":"ref8","author":"plumbley","year":"2018","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2018 Workshop (DCASE)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521242"},{"key":"ref2","article-title":"Generative Adversarial Network Based Acoustic Scene Training Set Augmentation and Selection Using SVM Hyper-Plane","author":"mun","year":"2017","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events Workshop (DCASE)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8902732"},{"key":"ref9","author":"mandel","year":"2019","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2019 Workshop (DCASE2019)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.33682\/gqpj-ac63"},{"key":"ref22","article-title":"Acoustic Scene Classification with Mismatched Recording Devices","author":"primus","year":"2019","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3021711"},{"key":"ref24","article-title":"Calibrating neural networks for secondary recording devices","author":"kosmider","year":"2019","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref23","article-title":"Unsupervised Adversarial Domain Adaptation for Acoustic Scene Classification","author":"gharib","year":"2018","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events Work-shop (DCASE)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.33682\/4jhy-bj81"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1007\/978-3-319-46493-0_38","article-title":"Identity mappings in deep residual networks","volume":"9908 lncs","author":"he","year":"2016","journal-title":"Lecture Notes in Computer Science"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414406.pdf?arnumber=9414406","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:20:10Z","timestamp":1659486010000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414406\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414406","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}