{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:29:57Z","timestamp":1775503797821,"version":"3.50.1"},"reference-count":26,"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\/icassp39728.2021.9414638","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"596-600","source":"Crossref","is-referenced-by-count":6,"title":["Learning Contextual Tag Embeddings for Cross-Modal Alignment of Audio and Tags"],"prefix":"10.1109","author":[{"given":"Xavier","family":"Favory","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Konstantinos","family":"Drossos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tuomas","family":"Virtanen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xavier","family":"Serra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020"},{"key":"ref11","article-title":"Contrastive representation learning: A framework and re-view","author":"le-khac","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350940"},{"key":"ref13","article-title":"Improving transformer-based speech recognition using unsupervised pre-training","author":"jiang","year":"2019"},{"key":"ref14","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018"},{"key":"ref15","article-title":"Coala: Co-aligned autoencoders for learning semantically enriched audio representations","author":"favory","year":"2020","journal-title":"International Conference on Machine Learning (ICML) Workshop on Self-supervised learning in Audio and Speech"},{"key":"ref16","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref17","article-title":"Unsupervised representation learning with deep convolutional genera-tive adversarial networks","author":"radford","year":"2016","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref18","article-title":"A guide to convolution arithmetic for deep learning","author":"dumoulin","year":"2016"},{"key":"ref19","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"ref3","article-title":"Musicnn: Pre-trained convolutional neural networks for music audio tagging","author":"pons","year":"2019"},{"key":"ref6","article-title":"Self-supervised learning by cross-modal audio-video clustering","author":"alwassel","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461684"},{"key":"ref8","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683774"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/app8010150"},{"key":"ref9","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489565"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502245"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461822"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref26","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","volume":"70","author":"engel","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2478068"}],"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\/09414638.pdf?arnumber=9414638","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:58Z","timestamp":1652197258000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414638\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414638","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}