{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T16:57:17Z","timestamp":1762102637635},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414779","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"source":"Crossref","is-referenced-by-count":4,"title":["Cross-Modal Spectrum Transformation Network for Acoustic Scene Classification"],"prefix":"10.1109","author":[{"given":"Yang","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandras","family":"Neophytou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sunando","family":"Sengupta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric","family":"Sommerlade","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"892","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"Advances in NIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00772"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.09.106"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126723"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.12329","article-title":"Cmc- gan: A uniform framework for cross-modal visual-audio mutual generation","author":"hao","year":"2018","journal-title":"Proceedings of the Conference on Artificial Intelligence"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref16","first-page":"6306","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"bengio","year":"2013","journal-title":"arXiv preprint arXiv 1308 3432"},{"key":"ref18","first-page":"5767","article-title":"Improved training of wasserstein GANs","author":"gulrajani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"3","article-title":"Constant-q transform toolbox for music processing","author":"schorkhuber","year":"2010","journal-title":"Sound and Music Computing Conference"},{"key":"ref4","article-title":"Youtube-8m: A large- scale video classification benchmark","author":"abu-el-haija","year":"2016","journal-title":"arXiv preprint arXiv 1609 09058"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.33682\/m5kp-fa97"},{"key":"ref8","article-title":"Designing acoustic scene classification models with cnn variants","author":"suh","year":"2020","journal-title":"Proc DCASE"},{"key":"ref7","article-title":"CP-JKU submissions to DCASE’19: Acoustic scene classification and audio tagging with receptive- field-regularized cnns","author":"koutini","year":"2019","journal-title":"Proc DCASE"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2696121"},{"key":"ref9","article-title":"Device-robust acoustic scene classification based on two-stage categorization and data augmentation","author":"hu","year":"2020","journal-title":"arXiv preprint arXiv 2007 09948"},{"key":"ref1","article-title":"DCASE 2018 challenge baseline with convolutional neural networks","author":"kong","year":"2018","journal-title":"arXiv preprint arXiv 1808 00508"},{"key":"ref20","article-title":"Gammatone-like spectrograms","author":"ellis","year":"2009"},{"key":"ref22","article-title":"Sequence-to-sequence models can directly translate foreign speech","author":"weiss","year":"2017","journal-title":"arXiv preprint arXiv 1703 08581"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30543-9_71"},{"key":"ref24","article-title":"Acoustic scene classification using deep residual networks with focal loss and mild domain adaptation","author":"gao","year":"2020","journal-title":"Proc DCASE"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462200"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2015.7324337"}],"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\/09414779.pdf?arnumber=9414779","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T08:33:35Z","timestamp":1672130015000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414779\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414779","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}