{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:33:24Z","timestamp":1730230404096,"version":"3.28.0"},"reference-count":35,"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\/icassp39728.2021.9414352","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"3865-3869","source":"Crossref","is-referenced-by-count":0,"title":["Contrastive Separative Coding for Self-Supervised Representation Learning"],"prefix":"10.1109","author":[{"given":"Jun","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Max W Y.","family":"Lam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.4405-12.2013"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1038\/nature11020","article-title":"Selective cortical representation of attended speaker in multi-talker speech perception","volume":"485","author":"mesgarani","year":"2012","journal-title":"Nature"},{"key":"ref31","article-title":"Effective low-cost time-domain audio separation usingglobally attentive locally recurrent networks","author":"lam","year":"0","journal-title":"To appear in SLT2021"},{"key":"ref30","article-title":"Dual-path rnn: efficient long sequence modeling for time-domain single-channel speech separation","author":"luo","year":"2019","journal-title":"arXiv preprint arXiv 1910 12731"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bht355"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.2674-15.2015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref11","article-title":"Learning deep representations by mutual information estimation and maximization","author":"hjelm","year":"2019","journal-title":"ICLRE"},{"key":"ref12","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018","journal-title":"arXiv preprint arXiv 1807 03748"},{"key":"ref13","article-title":"Distributed representation of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"NIPS"},{"key":"ref14","article-title":"Speech2vec: a sequence-to-sequence framework for learning word embeddings from speech","author":"glass","year":"2018","journal-title":"InterSpeech"},{"key":"ref15","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"arXiv preprint arXiv 1301 3781"},{"key":"ref16","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"ACL"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref18","first-page":"649","article-title":"Colorful image colorization","author":"zhang","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2005.1622"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682255"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2304"},{"key":"ref29","article-title":"Librimix: An open-source dataset for generalizable speech separation","author":"cosentino","year":"2020","journal-title":"arXiv preprint arXiv 2005 13449"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053760"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2357"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/4580"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"ref21","article-title":"Compositional attention networks for machine reasoning","author":"hudson","year":"2018","journal-title":"ICLRE"},{"key":"ref24","first-page":"626","article-title":"Sdr–half-baked or well done?","author":"roux","year":"2019","journal-title":"ICASSP"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1910"},{"key":"ref26","article-title":"Film: Visual reasoning with a general conditioning layer","author":"perez","year":"2017","journal-title":"arXiv preprint arXiv 1709 07492"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","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\/09414352.pdf?arnumber=9414352","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:40:58Z","timestamp":1652182858000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414352\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414352","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}