{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T16:01:41Z","timestamp":1783008101434,"version":"3.54.5"},"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\/icassp40776.2020.9053845","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"41-45","source":"Crossref","is-referenced-by-count":16,"title":["Improving Voice Separation by Incorporating End-To-End Speech Recognition"],"prefix":"10.1109","author":[{"given":"Naoya","family":"Takahashi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mayank Kumar","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sakya","family":"Basak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Parthasaarathy","family":"Sudarsanam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sriram","family":"Ganapathy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuki","family":"Mitsufuji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref30","article-title":"The 2018 signal separation evaluation campaign","author":"liutkus","year":"2018","journal-title":"Proc LVA\/ICA"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-655","article-title":"Single-channel speech separation using sparse non-negative matrix factorization","author":"schmidt","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-00599-2_81"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-28551-6_44"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854302"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref16","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 separationg","author":"ephrat","year":"2018","journal-title":"Proc Siggraph"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1167"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178063"},{"key":"ref19","article-title":"Decaf: A deep convolutional activation feature for generic visual recognition","author":"donahue","year":"2014","journal-title":"Proc ICML"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1550"},{"key":"ref27","first-page":"5206","article-title":"Librispeech: An asr corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"Proc ICASSP"},{"key":"ref3","article-title":"Tasnet: Surpassing ideal time-frequency masking for speech separation","author":"luo","year":"2018","journal-title":"CoRR"},{"key":"ref6","article-title":"MMDenseL-STM: An efficient combination of convolutional and recurrent neural networks for audio source separation","author":"takahashi","year":"2018","journal-title":"Proc IWAENC"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.241"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1773"},{"key":"ref8","first-page":"1963","article-title":"Learning Spectral Clustering, with Application to Speech Separation","volume":"7","author":"bach","year":"2006","journal-title":"The Journal of Machine Learning Research"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8169987"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1109\/TASL.2012.2215591","article-title":"An Unsupervised Approach to Cochannel Speech Separation","volume":"21","author":"hu","year":"2013","journal-title":"IEEE\/ACM Trans on Audio Speech and Language Processing"},{"key":"ref1","first-page":"31","article-title":"Deep clustering: Discriminative embeddings for segmentation and separation","author":"hershey","year":"2016","journal-title":"Proc ICASSP"},{"key":"ref20","first-page":"4489","article-title":"Learning Spatiotemporal Features with 3D Convolutional Networks","author":"tran","year":"2014","journal-title":"Proc ICCV"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-427","article-title":"Phoneme-dependent nmf for speech enhancement in monaural mixtures","author":"raj","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751969"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-761"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471654"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"}],"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\/09053845.pdf?arnumber=9053845","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T19:31:02Z","timestamp":1696015862000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053845\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053845","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}