{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T01:09:37Z","timestamp":1773277777222,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096478","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["Quantitative Evidence on Overlooked Aspects of Enrollment Speaker Embeddings for Target Speaker Separation"],"prefix":"10.1109","author":[{"given":"Xiaoyu","family":"Liu","sequence":"first","affiliation":[{"name":"Dolby Laboratories"}]},{"given":"Xu","family":"Li","sequence":"additional","affiliation":[{"name":"Dolby Laboratories"}]},{"given":"Joan","family":"Serr\u00e0","sequence":"additional","affiliation":[{"name":"Dolby Laboratories"}]}],"member":"263","reference":[{"key":"ref13","first-page":"12449","article-title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","volume":"33","author":"baevski","year":"0","journal-title":"NeurIPS 2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref34","first-page":"626","article-title":"SDR – Half-Baked or Well Done?","author":"le roux","year":"2019","journal-title":"ICASSP"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746303"},{"key":"ref37","article-title":"Attention is All You Need","volume":"30","author":"vaswani","year":"0","journal-title":"NeurIPS 2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref36","year":"0","journal-title":"The DCCRN"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054683"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054311"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-694"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref17","article-title":"BUT System Description to Vox-Celeb Speaker Recognition Challenge 2019","author":"zeinali","year":"2019","journal-title":"arXiv preprint arXiv 1910 12731"},{"key":"ref39","article-title":"CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR Voice Cloning Toolkit (version 0.92)","author":"yamagishi","year":"2019"},{"key":"ref16","first-page":"7264","article-title":"An Empirical Study of Conv-TasNet","author":"kad?o?lu","year":"2020","journal-title":"ICASSP"},{"key":"ref38","year":"0"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref18","first-page":"3830","article-title":"ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification","author":"desplanques","year":"2020","journal-title":"InterSpeech"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747230"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053767"},{"key":"ref41","article-title":"Simplicial Embeddings in Self-Supervised Learning and Downstream Classification","author":"lavoie","year":"2023","journal-title":"ICLRE"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"2616","DOI":"10.21437\/Interspeech.2017-950","article-title":"VoxCeleb: A Large-Scale Speaker Identification Dataset","author":"nagrani","year":"2017","journal-title":"InterSpeech"},{"key":"ref21","first-page":"531","article-title":"A Comparative Study of Feature and Score Normalization for Speaker Verification","author":"zheng","year":"2006","journal-title":"International Conference on Biometrics"},{"key":"ref28","year":"0","journal-title":"The SpeechBrain ECAPA-TDNN"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682245"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747395"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687903"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746962"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10962"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1436"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747765"},{"key":"ref40","article-title":"Towards the Generalization of Contrastive Self-Supervised Learning","author":"huang","year":"2023","journal-title":"ICLRE"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096478.pdf?arnumber=10096478","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:06:39Z","timestamp":1700507199000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096478\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096478","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}