{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:52:23Z","timestamp":1777654343511,"version":"3.51.4"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054057","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"6829-6833","source":"Crossref","is-referenced-by-count":57,"title":["Disentangled Speech Embeddings Using Cross-Modal Self-Supervision"],"prefix":"10.1109","author":[{"given":"Arsha","family":"Nagrani","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joon Son","family":"Chung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samuel","family":"Albanie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Zisserman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.463"},{"key":"ref10","first-page":"2539","article-title":"Deep convolutional inverse graphics network","author":"kulkarni","year":"2015","journal-title":"NeurIPS"},{"key":"ref11","first-page":"2172","article-title":"Infogan: Interpretable representation learning by information maximizing generative adversarial nets","author":"chen","year":"2016","journal-title":"NeurIPS"},{"key":"ref12","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017","journal-title":"NeurIPS"},{"key":"ref13","article-title":"Variational recurrent auto-encoders","author":"fabius","year":"2014"},{"key":"ref14","article-title":"A recurrent latent variable model for sequential data","author":"chung","year":"2015","journal-title":"NeurIPS"},{"key":"ref15","article-title":"Hierarchical multiscale recurrent neural networks","author":"chung","year":"2016"},{"key":"ref16","first-page":"2199","article-title":"Sequential neural models with stochastic layers","author":"fraccaro","year":"2016","journal-title":"NeurIPS"},{"key":"ref17","first-page":"892","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"NeurIPS"},{"key":"ref18","first-page":"609","article-title":"Look, listen and learn","author":"arandjelovic","year":"2017","journal-title":"ICCV"},{"key":"ref19","article-title":"See, hear, and read: Deep aligned representations","author":"aytar","year":"2017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682524"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"VoxCeleb: a large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"InterSpeech"},{"key":"ref27","article-title":"Return of the devil in the details: Delving deep into convolutional nets","author":"chatfield","year":"2014","journal-title":"Proc BMVC"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683120"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref29","article-title":"Turning a blind eye: Explicit removal of biases and variation from deep neural network embeddings","author":"alvi","year":"2018","journal-title":"ECCV"},{"key":"ref5","article-title":"Darpa timit acoustic-phonetic continous speech corpus cd-rom. nist speech disc 1-1.1","volume":"93","author":"garofolo","year":"1993","journal-title":"NASA STI\/Recon Technical Report N"},{"key":"ref8","article-title":"Rapid and accurate spoken term detection","author":"miller","year":"2007","journal-title":"ISCA"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240578"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486441"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-82"},{"key":"ref1","first-page":"4774","article-title":"State-of-the-art speech recognition with sequence-to-sequence models","author":"chiu","year":"2018","journal-title":"ICASSP"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_48"},{"key":"ref22","first-page":"251","article-title":"Out of time: automated lip sync in the wild","author":"chung","year":"2016","journal-title":"ACCV"},{"key":"ref21","article-title":"Cooperative learning of audio and video models from self-supervised synchronization","author":"korbar","year":"2018","journal-title":"NeurIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_5"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00879"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-879"},{"key":"ref25","article-title":"On learning associations of faces and voices","author":"kim","year":"2018"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054057.pdf?arnumber=9054057","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:09:23Z","timestamp":1656374963000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054057\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054057","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}