{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:17:35Z","timestamp":1740100655579,"version":"3.37.3"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746354","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"8387-8391","source":"Crossref","is-referenced-by-count":2,"title":["Improving Separation-Based Speaker Diarization Via Iterative Model Refinement And Speaker Embedding Based Post-Processing"],"prefix":"10.1109","author":[{"given":"Shu-Tong","family":"Niu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,Hefei,P. R. China"}]},{"given":"Jun","family":"Du","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,P. R. China"}]},{"given":"Lei","family":"Sun","sequence":"additional","affiliation":[{"name":"iFlytek Research,Hefei,P. R. China"}]},{"given":"Chin-Hui","family":"Lee","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,Atlanta,GA,USA"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"article-title":"Personal vad: Speaker-conditioned voice activity detection","year":"2019","author":"ding","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2558822"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462505"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"article-title":"Separation guided speaker diarization in realistic mismatched conditions","year":"2021","author":"niu","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1416463"},{"year":"2009","key":"ref28","article-title":"The 2009 (rt-09) rich transcription meeting recognition evaluation plan"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682273"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1416463"},{"key":"ref6","first-page":"355","article-title":"Analysis of speaker diarization based on bayesian hmm with eigenvoice priors","volume":"28","author":"diez","year":"2019","journal-title":"IEEE Trans on ASLP"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-516"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2264673"},{"key":"ref8","first-page":"4052","article-title":"Deep neural networks for small footprint text-dependent speaker verification","author":"variani","year":"2014","journal-title":"ICASSP"},{"key":"ref7","first-page":"788","article-title":"Front-end factor analysis for speaker verification","volume":"19","author":"dehak","year":"2010","journal-title":"IEEE Trans on ASLP"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2015698"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"article-title":"A review of speaker diarization: Recent advances with deep learning","year":"2021","author":"park","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054295"},{"key":"ref22","first-page":"5206","article-title":"Librispeech: an asr corpus based on public do-main audio books","author":"panayotov","year":"2015","journal-title":"ICASSP"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413832"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"Voxceleb: a large-scale speaker identification dataset","author":"nagrani","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383490"},{"article-title":"Third dihard challenge evaluation plan","year":"2020","author":"ryant","key":"ref25"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746354.pdf?arnumber=9746354","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:09:13Z","timestamp":1660594153000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746354\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746354","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}