{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T15:57:44Z","timestamp":1779292664274,"version":"3.51.4"},"reference-count":38,"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\/icassp48485.2024.10446204","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10861-10865","source":"Crossref","is-referenced-by-count":10,"title":["Enhancing Speaker Diarization with Large Language Models: A Contextual Beam Search Approach"],"prefix":"10.1109","author":[{"given":"Tae Jin","family":"Park","sequence":"first","affiliation":[{"name":"NVIDIA,Santa Clara,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kunal","family":"Dhawan","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nithin","family":"Koluguri","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jagadeesh","family":"Balam","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101317"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1602"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2023-1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1943"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746225"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1987.1169844"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICFHR-2018.2018.00052"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref10","first-page":"3","article-title":"Speaker diarization from speech transcripts","volume-title":"Proc. ICSLP","volume":"4","author":"Canseco-Rodriguez"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2005.1566507"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1364"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746531"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746964"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1947"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.884"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2289"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1982"},{"key":"ref19","article-title":"Multi-scale speaker diarization with dynamic scale weighting","volume-title":"Proc. Interspeech","author":"Jin Park"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/chime.2023-11"},{"key":"ref21","article-title":"PyCTCDecode: A fast and lightweight python-based CTC beam search decoder for speech recognition","author":"Technologies","year":"2023"},{"key":"ref22","first-page":"187","article-title":"KenLM: Faster and smaller language model queries","volume-title":"Proc. SMT Workshop","author":"Heafield"},{"key":"ref23","article-title":"Megatron-LM: Training multi-billion parameter language models using model parallelism","author":"Shoeybi","year":"2019"},{"key":"ref24","article-title":"NeMo: a toolkit for building ai applications using neural modules","author":"Kuchaiev","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746806"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref29","first-page":"381","article-title":"Auto-tuning spectral clustering for speaker diarization using normalized maximum eigengap","volume":"27","author":"Jin Park","year":"2019","journal-title":"IEEE SPL"},{"key":"ref30","article-title":"NeMo Megatron Launcher","year":"2023"},{"issue":"8","key":"ref31","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref32","article-title":"The-Stack-Dedup:Datasets at Hugging Face","author":"Face","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.24"},{"key":"ref34","article-title":"Whisper: Robust speech recognition via large-scale weak supervision","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref36","article-title":"The AMI meeting corpus","volume-title":"Proc. International Conference on Methods and Techniques in Behavioral Research","author":"Kraaij"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101254"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"}],"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\/10446204.pdf?arnumber=10446204","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:38:38Z","timestamp":1722573518000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446204\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446204","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}