{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:51:48Z","timestamp":1771613508276,"version":"3.50.1"},"reference-count":32,"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\/icassp39728.2021.9413559","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6-10","source":"Crossref","is-referenced-by-count":10,"title":["On Permutation Invariant Training For Speech Source Separation"],"prefix":"10.1109","author":[{"given":"Xiaoyu","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jordi","family":"Pons","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11671","article-title":"Film: Visual reasoning with a general conditioning layer","author":"perez","year":"2018","journal-title":"AAAI"},{"key":"ref31","year":"0","journal-title":"The PASE+ model used in this paper can be retrieved here"},{"key":"ref30","year":"0","journal-title":"The Deep CASA results reported in this paper are based on this code"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref13","first-page":"7264","article-title":"An empirical study of convtasnet","author":"kad?o?lu","year":"2020","journal-title":"ICASSP"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"35","DOI":"10.21437\/SSW.2019-7","article-title":"Problem-agnostic speech embeddings for multi-speaker text- to-speech with SampleRnn","author":"\u00e1lvarez","year":"2019","journal-title":"ISCA Speech Synthesis Workshop"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053602"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052981"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937253"},{"key":"ref28","year":"0","journal-title":"Script to generate the multi-speaker dataset using WSJ0"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461477"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053921"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462471"},{"key":"ref29","article-title":"Librimix: An open-source dataset for generalizable speech separation","author":"cosentino","year":"2020"},{"key":"ref5","article-title":"Wavesplit: End-to-end speech separation by speaker clustering","author":"zeghidour","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053697"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1827"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2941148"},{"key":"ref9","article-title":"Voice separation with an unknown number of multiple speakers","author":"nachmani","year":"2020"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053038"},{"key":"ref22","first-page":"626","article-title":"Sdr–half-baked or well done?","author":"le roux","year":"2019","journal-title":"ICASSP"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3181"},{"key":"ref24","first-page":"4879","article-title":"Generalized end-to-end loss for speaker verification","author":"wan","year":"2018","journal-title":"ICASSP"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054172"},{"key":"ref26","article-title":"End-to-end multi-channel speech separation","author":"gu","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053845"}],"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\/09413559.pdf?arnumber=9413559","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,3]],"date-time":"2023-11-03T18:29:55Z","timestamp":1699036195000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413559\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413559","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}