{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:38:05Z","timestamp":1730230685817,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446845","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10051-10055","source":"Crossref","is-referenced-by-count":0,"title":["Implicit Enhancement of Target Speaker in Speaker-Adaptive ASR through Efficient Joint Optimization"],"prefix":"10.1109","author":[{"given":"Minghui","family":"Wu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,China"}]},{"given":"Haitao","family":"Tang","sequence":"additional","affiliation":[{"name":"iFLYTEK Research,China"}]},{"given":"Jiahuan","family":"Fan","sequence":"additional","affiliation":[{"name":"iFLYTEK Research,China"}]},{"given":"Ruoyu","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,China"}]},{"given":"Hang","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,China"}]},{"given":"Yanyong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,China"}]},{"given":"Jun","family":"Du","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,China"}]},{"given":"Hengshun","family":"Zhou","sequence":"additional","affiliation":[{"name":"iFLYTEK Research,China"}]},{"given":"Lei","family":"Sun","sequence":"additional","affiliation":[{"name":"iFLYTEK Research,China"}]},{"given":"Xin","family":"Fang","sequence":"additional","affiliation":[{"name":"iFLYTEK Research,China"}]},{"given":"Tian","family":"Gao","sequence":"additional","affiliation":[{"name":"iFLYTEK Research,China"}]},{"given":"Genshun","family":"Wan","sequence":"additional","affiliation":[{"name":"iFLYTEK Research,China"}]},{"given":"Jia","family":"Pan","sequence":"additional","affiliation":[{"name":"iFLYTEK Research,China"}]},{"given":"Jianqing","family":"Gao","sequence":"additional","affiliation":[{"name":"iFLYTEK Research,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1768"},{"article-title":"Overview of the 6th chime challenge","volume-title":"CHiME6 Workshop","author":"Watanabe","key":"ref4"},{"key":"ref5","article-title":"Front-end processing for the chime-5 dinner party scenario","volume-title":"CHiME5 Workshop, Hyderabad, India","volume":"1","author":"Boeddeker"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-42"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2719"},{"article-title":"Investigation of speaker-adaptation methods in transformer based asr","year":"2020","author":"Shetty","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"article-title":"Improving and analyzing neural speaker embeddings for asr","year":"2023","author":"L\u00fcscher","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095040"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10896"},{"issue":"2017-86","key":"ref14","article-title":"Computational optimal transport","author":"Peyr\u00e9","year":"2017","journal-title":"Center for Research in Economics and Statistics Working Papers"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10839"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2023-1"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"article-title":"Musan: A music, speech, and noise corpus","year":"2015","author":"Snyder","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701894"},{"article-title":"Speechbrain: A general-purpose speech toolkit","year":"2021","author":"Ravanelli","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/chime.2023-3"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446845.pdf?arnumber=10446845","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:54:14Z","timestamp":1722574454000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446845\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446845","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}