{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:15:07Z","timestamp":1776885307091,"version":"3.51.2"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889841","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["META-CAT: Speaker-Informed Speech Embeddings via Meta Information Concatenation for Multi-talker ASR"],"prefix":"10.1109","author":[{"given":"Jinhan","family":"Wang","sequence":"first","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiqing","family":"Wang","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kunal","family":"Dhawan","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taejin","family":"Park","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Myungjong","family":"Kim","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ivan","family":"Medennikov","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"He","family":"Huang","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nithin","family":"Koluguri","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jagadeesh","family":"Balam","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boris","family":"Ginsburg","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/chime.2020\u20139"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-8"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746225"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447957"},{"key":"ref5","article-title":"Streaming End-to-End Target Speaker ASR","volume-title":"Proc. INTERSPEECH","author":"Moriya"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-305"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1126"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-0999"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-7"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095115"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1640"},{"key":"ref12","article-title":"Sortformer: Seamless integration of speaker diarization and asr by bridging timestamps and tokens","author":"Park","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389701"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495077"},{"key":"ref16","article-title":"The ami corpus"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101254"},{"key":"ref18","article-title":"The icsi meeting corpus"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2800"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref21","article-title":"Nvidia parakeet rnn-t 0.6b","year":"2024"},{"key":"ref22","article-title":"Nemo toolkit"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref24","article-title":"Callhome american english speech","author":"Canavan","year":"1997"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-101"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889841.pdf?arnumber=10889841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:22Z","timestamp":1774416322000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889841\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889841","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}