{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T14:56:09Z","timestamp":1777733769875,"version":"3.51.4"},"reference-count":21,"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\/icassp49357.2023.10096664","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":19,"title":["Target Speaker Extraction with Ultra-Short Reference Speech by VE-VE Framework"],"prefix":"10.1109","author":[{"given":"Lei","family":"Yang","sequence":"first","affiliation":[{"name":"Samsung Research China – Beijing (SRC-B)"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"Samsung Research China – Beijing (SRC-B)"}]},{"given":"Lufen","family":"Tan","sequence":"additional","affiliation":[{"name":"Samsung Research China – Beijing (SRC-B)"}]},{"given":"Jaemo","family":"Yang","sequence":"additional","affiliation":[{"name":"Mobile Experience Business, Samsung Electronics Co., Ltd"}]},{"given":"Han-Gil","family":"Moon","sequence":"additional","affiliation":[{"name":"Mobile Experience Business, Samsung Electronics Co., Ltd"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413359"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1397"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003983"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2260"},{"key":"ref20","article-title":"Csr-i (wsj0) complete ldc93s6a","volume":"83","author":"garofolo","year":"1993","journal-title":"Web Download Philadelphia Linguistic Data Consortium"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2987429"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683087"},{"key":"ref21","article-title":"Adam: A Method for Stochastic Optimization","author":"kingma","year":"2014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/0899766054322964"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907229"},{"key":"ref17","first-page":"626","article-title":"SDR-half-baked or well done?","author":"le","year":"2019","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2085"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462661"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1513"},{"key":"ref9","first-page":"8","article-title":"Learning speaker representation for neural network based multi-channel speaker extraction","author":"zmolikova","year":"2017","journal-title":"Proc IEEE Workshop Automatic Speech Recognition and Understanding (ASRU)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1193"},{"key":"ref3","article-title":"Voicefilter: Targeted voice separation by speaker-conditioned spectrogram masking","author":"wang","year":"2018","journal-title":"arXiv preprint arXiv 1810 04805"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054683"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2922820"}],"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\/10096664.pdf?arnumber=10096664","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T14:09:51Z","timestamp":1700489391000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096664\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096664","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}