{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T16:09:29Z","timestamp":1772726969224,"version":"3.50.1"},"reference-count":33,"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\/icassp39728.2021.9413802","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"4180-4184","source":"Crossref","is-referenced-by-count":8,"title":["Collaborative Learning to Generate Audio-Video Jointly"],"prefix":"10.1109","author":[{"given":"Vinod K","family":"Kurmi","sequence":"first","affiliation":[]},{"given":"Vipul","family":"Bajaj","sequence":"additional","affiliation":[]},{"given":"Badri N","family":"Patro","sequence":"additional","affiliation":[]},{"given":"K S","family":"Venkatesh","sequence":"additional","affiliation":[]},{"given":"Vinay P","family":"Namboodiri","sequence":"additional","affiliation":[]},{"given":"Preethi","family":"Jyothi","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","article-title":"Synthesizing audio with generative adversarial networks","author":"donahue","year":"2018"},{"key":"ref32","article-title":"Triangle generative adversarial networks","author":"gan","year":"2017","journal-title":"NIPS"},{"key":"ref31","article-title":"Adversarial audio synthesis","author":"donahue","year":"2018"},{"key":"ref30","article-title":"Spectrogram analysis via self-attention for realizing cross-model visual-audio generation","author":"tan","year":"0","journal-title":"ICASSP 2020"},{"key":"ref10","article-title":"Gansynth: Adversarial neural audio synthesis","author":"engel","year":"2018"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1145\/3197517.3201357","article-title":"Looking to listen at the cocktail party: a speaker-independent audio-visual model for speech separation","author":"ephrat","year":"2018","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref12","first-page":"649","article-title":"Jointly discovering visual objects and spoken words from raw sensory input","author":"harwath","year":"2018","journal-title":"ECCV"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462581"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1428","article-title":"Segan: Speech enhancement generative adversarial network","author":"pascual","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref15","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"0","journal-title":"9th ISCA Speech Synthesis Workshop"},{"key":"ref16","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","author":"engel","year":"2017","journal-title":"ICML"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00374"},{"key":"ref18","article-title":"Conditional wavegan","author":"young lee","year":"2018"},{"key":"ref19","first-page":"435","article-title":"Objects that sound","author":"arandjelovic","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3009820"},{"key":"ref4","article-title":"Progressive growing of gans for improved quality, stability, and variation","author":"karras","year":"2018"},{"key":"ref27","article-title":"Audeo: Audio generation for a silent performance video","author":"su","year":"2020","journal-title":"NeurIPS"},{"key":"ref3","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"NIPS"},{"key":"ref6","first-page":"172","article-title":"Multimodal unsupervised image-to-image translation","author":"huang","year":"2018","journal-title":"ECCV"},{"key":"ref29","article-title":"Sound2sight: Generating visual dynamics from sound and context","author":"cherian","year":"2020","journal-title":"ECCV"},{"key":"ref5","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2015"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682383"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.12329","article-title":"Cmcgan: A uniform framework for cross-modal visual-audio mutual generation","author":"hao","year":"2018","journal-title":"AAAI"},{"key":"ref9","article-title":"Music transformer: Generating music with long-term structure","author":"anna huang","year":"2018"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126723"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref22","first-page":"631","article-title":"Audio-visual scene analysis with self-supervised multisensory features","author":"owens","year":"2018","journal-title":"ECCV"},{"key":"ref21","first-page":"35","article-title":"Learning to separate object sounds by watching unlabeled video","author":"gao","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.264"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00772"},{"key":"ref26","article-title":"Foley music: Learning to generate music from videos","author":"gan","year":"2020","journal-title":"ECCV"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01049"}],"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\/09413802.pdf?arnumber=9413802","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T08:33:13Z","timestamp":1672129993000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413802\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413802","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}