{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:04:19Z","timestamp":1776888259852,"version":"3.51.2"},"reference-count":30,"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\/icassp48485.2024.10446724","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11011-11015","source":"Crossref","is-referenced-by-count":2,"title":["Joint Inference of Speaker Diarization and ASR with Multi-Stage Information Sharing"],"prefix":"10.1109","author":[{"given":"Weiqing","family":"Wang","sequence":"first","affiliation":[{"name":"Duke University,Department of Electrical & Computer Engineering,Durham,NC,USA,27708"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danwei","family":"Cai","sequence":"additional","affiliation":[{"name":"Duke University,Department of Electrical & Computer Engineering,Durham,NC,USA,27708"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Cheng","sequence":"additional","affiliation":[{"name":"Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems,Kunshan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Li","sequence":"additional","affiliation":[{"name":"Duke University,Department of Electrical & Computer Engineering,Durham,NC,USA,27708"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101254"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1388"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003826"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3036"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-015-1019-z"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21236\/ADA613971"},{"key":"ref9","first-page":"497","article-title":"The ibm rt07 evaluation systems for speaker diarization on lecture meetings","volume-title":"International Evaluation Workshop on Rich Transcription","author":"Huang"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746531"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-17"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1364"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3039"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415062"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096659"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3419426"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094752"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1602"},{"key":"ref21","article-title":"Nemo: a toolkit for building ai applications using neural modules","author":"Kuchaiev","year":"2019"},{"key":"ref22","article-title":"Mu-san: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1208"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747772"},{"key":"ref27","article-title":"But system description for dihard speech diarization challenge 2019","author":"Landini","year":"2019"},{"key":"ref28","article-title":"The hitachi-jhu dihard iii system: Competitive end-to-end neural diarization and x-vector clustering systems combined by dover-lap","author":"Horiguchi","year":"2021"},{"key":"ref29","article-title":"Ustc-nelslip system description for dihard-iii challenge","author":"Wang","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3265199"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"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\/10446724.pdf?arnumber=10446724","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:25:31Z","timestamp":1722576331000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446724\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446724","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}