{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T19:18:57Z","timestamp":1780773537942,"version":"3.54.1"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["448568305"],"award-info":[{"award-number":["448568305"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3350887","type":"journal-article","created":{"date-parts":[[2024,1,8]],"date-time":"2024-01-08T20:03:59Z","timestamp":1704744239000},"page":"1185-1197","source":"Crossref","is-referenced-by-count":24,"title":["TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8701-1567","authenticated-orcid":false,"given":"Christoph","family":"Boeddeker","sequence":"first","affiliation":[{"name":"Paderborn University, Paderborn, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4446-001X","authenticated-orcid":false,"given":"Aswin Shanmugam","family":"Subramanian","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8597-6795","authenticated-orcid":false,"given":"Gordon","family":"Wichern","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9468-7330","authenticated-orcid":false,"given":"Reinhold","family":"Haeb-Umbach","sequence":"additional","affiliation":[{"name":"Paderborn University, Paderborn, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3451-171X","authenticated-orcid":false,"given":"Jonathan","family":"Le Roux","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383556"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1268"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638256"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10929"},{"key":"ref7","first-page":"35","article-title":"Front-end processing for the CHiME-5 dinner party scenario","volume-title":"Proc. Int. Workshop Speech Process. Everyday Environments","author":"Boeddeker","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/chime.2020\u20139"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-662"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-667"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414998"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687875"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11408"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414333"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1602"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-62"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-750"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095185"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682245"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3099291"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022924"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2961071"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461639"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471664"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052981"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC53105.2022.9914794"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746757"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1987.4767941"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2025790"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053692"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-318"},{"key":"ref37","first-page":"1561","article-title":"The fifth CHiME speech separation and recognition challenge: Dataset, task and baselines","volume-title":"Proc. ISCA Interspeech","author":"Barker","year":"2018"},{"key":"ref38","article-title":"NIST 2021 speaker recognition evaluation","author":"Sadjadi","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094784"},{"key":"ref40","first-page":"803","article-title":"Multiple dimension levenshtein edit distance calculations for evaluating automatic speech recognition systems during simultaneous speech","volume-title":"Proc. Lang. Resour. Eval. Conf.","author":"Fiscus","year":"2006"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref42","article-title":"ESPnet2 pretrained model, Shinji Watanabe\/librispe ech_asr_train_asr_transformer_e18_raw_bpe_sp_valid. acc.best, fs=16k, lang=en","author":"Watanabe","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10839"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.11.005"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref50","article-title":"The Kaldi speech recognition toolkit","volume-title":"Proc. IEEE Autom. Speech Recognit. Understanding Workshop","author":"Povey","year":"2011"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052251"},{"key":"ref52","first-page":"1","article-title":"NARA-WPE: A python package for weighted prediction error dereverberation in numpy and tensorflow for online and offline processing","volume-title":"Proc. 13th ITG-Symp. Speech Commun.","author":"Drude","year":"2018"},{"key":"ref53","first-page":"226","article-title":"Self-trained audio tagging and sound event detection in domestic environments","volume-title":"Proc. Workshop Detection Classification Acoustic Scenes Events","author":"Ebbers","year":"2021"},{"key":"ref54","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2018"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2014-80"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746896"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-7"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3083405"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746225"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-42"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10382558.pdf?arnumber=10382558","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,2]],"date-time":"2024-02-02T00:24:27Z","timestamp":1706833467000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10382558\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3350887","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}