{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:33:14Z","timestamp":1753601594086,"version":"3.37.3"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62071302,61701306"],"award-info":[{"award-number":["62071302,61701306"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9687903","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"658-662","source":"Crossref","is-referenced-by-count":11,"title":["Attention-Based Scaling Adaptation for Target Speech Extraction"],"prefix":"10.1109","author":[{"given":"Jiangyu","family":"Han","sequence":"first","affiliation":[{"name":"Shanghai Normal University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Rao","sequence":"additional","affiliation":[{"name":"Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanhua","family":"Long","sequence":"additional","affiliation":[{"name":"Shanghai Normal University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaen","family":"Liang","sequence":"additional","affiliation":[{"name":"Unisound AI Technology Co., Ltd.,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053846"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462661"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2987429"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054683"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682245"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054311"},{"key":"ref16","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639593"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683087"},{"key":"ref19","first-page":"626","article-title":"SDR-half-baked or well done?","author":"le roux","year":"2019","journal-title":"2019 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052981"},{"key":"ref5","first-page":"36","article-title":"A multi-phase gammatone filter-bank for speech separation via TasNet","author":"ditter","year":"2020","journal-title":"2020 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref8","first-page":"6364","article-title":"Filter-bank design for end-to-end speech separation","author":"pariente","year":"2020","journal-title":"2020 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053575"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053092"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461639"},{"year":"0","key":"ref22"},{"year":"0","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-298"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref25","article-title":"End-to-end multi-channel speech separation","author":"gu","year":"2019","journal-title":"ArXiv Preprint"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2021,12,13]]},"location":"Cartagena, Colombia","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09687903.pdf?arnumber=9687903","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:41:49Z","timestamp":1652733709000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9687903\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9687903","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}