{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T11:40:42Z","timestamp":1725709242094},"reference-count":26,"publisher":"IEEE","license":[{"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\/icassp39728.2021.9413975","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"5774-5778","source":"Crossref","is-referenced-by-count":2,"title":["Training Noisy Single-Channel Speech Separation with Noisy Oracle Sources: A Large Gap and a Small Step"],"prefix":"10.1109","author":[{"given":"Matthew","family":"Maciejewski","sequence":"first","affiliation":[{"name":"The Johns Hopkins University,Center for Language and Speech Processing,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Shi","sequence":"additional","affiliation":[{"name":"The Johns Hopkins University,Center for Language and Speech Processing,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"The Johns Hopkins University,Center for Language and Speech Processing,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanjeev","family":"Khudanpur","sequence":"additional","affiliation":[{"name":"The Johns Hopkins University,Center for Language and Speech Processing,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Librimix: An open-source dataset for generalizable speech separation","year":"2020","author":"cosentino","key":"ref10"},{"key":"ref11","first-page":"31","article-title":"Deep clustering: Discriminative embeddings for segmentation and separation","author":"hershey","year":"2016","journal-title":"Proc IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054572"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2019.2918706"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1768"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.21437\/CHiME.2020-1","article-title":"CHiME-6 challenge: Tackling multispeaker speech recognition for unsegmented recordings","author":"watanabe","year":"2020"},{"key":"ref17","first-page":"626","article-title":"SDR – half-baked or well done?","author":"le roux","year":"2019","journal-title":"Proc IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003827"},{"article-title":"Wavesplit: End-to-end speech separation by speaker clustering","year":"2020","author":"zeghidour","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053327"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2418"},{"key":"ref2","article-title":"Analysis of overlaps in meetings by dialog factors, hot spots, speakers, and collection site: insights for automatic speech recognition","author":"\u00e7etin","year":"2006","journal-title":"Proc ISCA Interspeech"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937153"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/b105752"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937253"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1002\/9781119279860","author":"vincent","year":"2018","journal-title":"Audio Source Separation and Speech Enhancement"},{"journal-title":"CSR-I (WSJ0) Complete LDC93S6A","year":"1993","author":"garofolo","key":"ref24"},{"article-title":"Unsupervised sound separation using mixtures of mixtures","year":"2020","author":"wisdom","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref25","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc of the 3rd International Conference on Learning Representations (ICLR)"}],"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\/09413975.pdf?arnumber=9413975","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,3]],"date-time":"2023-11-03T18:30:55Z","timestamp":1699036255000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413975\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413975","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}