{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:13:31Z","timestamp":1740100411025,"version":"3.37.3"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T00:00:00Z","timestamp":1629676800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T00:00:00Z","timestamp":1629676800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010661","name":"European Union's Horizon 2020","doi-asserted-by":"publisher","award":["957337"],"award-info":[{"award-number":["957337"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,8,23]]},"DOI":"10.23919\/eusipco54536.2021.9616340","type":"proceedings-article","created":{"date-parts":[[2021,12,8]],"date-time":"2021-12-08T21:55:53Z","timestamp":1639000553000},"page":"576-580","source":"Crossref","is-referenced-by-count":9,"title":["WaveTransformer: An Architecture for Audio Captioning Based on Learning Temporal and Time-Frequency Information"],"prefix":"10.23919","author":[{"given":"An","family":"Tran","sequence":"first","affiliation":[]},{"given":"Konstantinos","family":"Drossos","sequence":"additional","affiliation":[]},{"given":"Tuomas","family":"Virtanen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207532"},{"key":"ref11","article-title":"Effects of word-frequency based pre- and post- processings for audio captioning","author":"takeuchi","year":"2020","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events"},{"key":"ref12","article-title":"Automated audio captioning with temporal attention","author":"wang","year":"2020","journal-title":"Tech Rep DCASE2020 Challenge"},{"key":"ref13","article-title":"Multi-task regularization based on infrequent classes for audio captioning","author":"\u00e7akir","year":"2020","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"1291","DOI":"10.1109\/TASLP.2017.2690575","article-title":"Convolutional recurrent neural networks for polyphonic sound event detection","volume":"25","author":"\u00e7akir","year":"2017","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref15","article-title":"Wavenet: A generative model for raw audio","author":"den oord","year":"2016","journal-title":"9th International Speech Communication Association(ISCA) Speech Synthesis Workshop"},{"key":"ref16","article-title":"Rare sound event detection using ld convolutional recurrent neural networks","author":"lim","year":"2017","journal-title":"Tech Rep DCASE2020 Challenge"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.33682\/sezz-vd31"},{"key":"ref18","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proceedings of the International Conference on Learning Representation (ICLR)"},{"key":"ref19","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"43rd Annual Meeting on Association for Computational Linguistics Association for Computational Linguistics"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref3","article-title":"Temporal sub-sampling of audio feature sequences for automated audio captioning","author":"nguyen","year":"0","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (D CASE 2020)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2087"},{"key":"ref5","article-title":"Task 6 dcase 2020: Listen carefully and tell: An audio captioning system based on residual learning and gammatone audio representation","author":"naranjo-alcazar","year":"2020","journal-title":"Tech Rep DCASE2020 Challenge"},{"key":"ref8","article-title":"Audio captioning with the transformer automated audio captioning","author":"shi","year":"2020","journal-title":"Tech Rep DCASE2020 Challenge"},{"key":"ref7","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"31st Conference on Neural Information Processing Systems (NeurIPS 2017)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682377"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170058"},{"key":"ref9","article-title":"Twin Networks: Matching the future for sequence generation","volume":"abs 1708 6742","author":"serdyuk","year":"2017","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref21","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"}],"event":{"name":"2021 29th European Signal Processing Conference (EUSIPCO)","start":{"date-parts":[[2021,8,23]]},"location":"Dublin, Ireland","end":{"date-parts":[[2021,8,27]]}},"container-title":["2021 29th European Signal Processing Conference (EUSIPCO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9615915\/9615917\/09616340.pdf?arnumber=9616340","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,21]],"date-time":"2022-03-21T20:56:49Z","timestamp":1647896209000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9616340\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,23]]},"references-count":24,"URL":"https:\/\/doi.org\/10.23919\/eusipco54536.2021.9616340","relation":{},"subject":[],"published":{"date-parts":[[2021,8,23]]}}}